Merge branch 'master' into features

4 years ago · 68fd8a267b
parent 4e61c6a12d 17f4dd2778
commit 68fd8a267b
15 changed files with 1167 additions and 705 deletions
--- a/docs/changes.md
+++ b/docs/changes.md
@ -0,0 +1,62 @@
+### June 11, 2020
+Bunch of changes:
+
+* DenseNet models updated with memory efficient addition from torchvision (fixed a bug), blur pooling and deep stem additions
+* VoVNet V1 and V2 models added, 39 V2 variant (ese_vovnet_39b) trained to 79.3 top-1
+* Activation factory added along with new activations:
+   * select act at model creation time for more flexibility in using activations compatible with scripting or tracing (ONNX export)
+   * hard_mish (experimental) added with memory-efficient grad, along with ME hard_swish
+   * context mgr for setting exportable/scriptable/no_jit states
+* Norm + Activation combo layers added with initial trial support in DenseNet and VoVNet along with impl of EvoNorm and InplaceAbn wrapper that fit the interface
+* Torchscript works for all but two of the model types as long as using Pytorch 1.5+, tests added for this
+* Some import cleanup and classifier reset changes, all models will have classifier reset to nn.Identity on reset_classifer(0) call
+* Prep for 0.1.28 pip release
+
+### May 12, 2020
+* Add ResNeSt models (code adapted from https://github.com/zhanghang1989/ResNeSt, paper https://arxiv.org/abs/2004.08955))
+
+### May 3, 2020
+* Pruned EfficientNet B1, B2, and B3 (https://arxiv.org/abs/2002.08258) contributed by [Yonathan Aflalo](https://github.com/yoniaflalo)
+
+### May 1, 2020
+* Merged a number of execellent contributions in the ResNet model family over the past month
+  * BlurPool2D and resnetblur models initiated by [Chris Ha](https://github.com/VRandme), I trained resnetblur50 to 79.3.
+  * TResNet models and SpaceToDepth, AntiAliasDownsampleLayer layers by [mrT23](https://github.com/mrT23)
+  * ecaresnet (50d, 101d, light) models and two pruned variants using pruning as per (https://arxiv.org/abs/2002.08258) by [Yonathan Aflalo](https://github.com/yoniaflalo)
+* 200 pretrained models in total now with updated results csv in results folder
+
+### April 5, 2020
+* Add some newly trained MobileNet-V2 models trained with latest h-params, rand augment. They compare quite favourably to EfficientNet-Lite
+  * 3.5M param MobileNet-V2 100 @ 73%
+  * 4.5M param MobileNet-V2 110d @ 75%
+  * 6.1M param MobileNet-V2 140 @ 76.5%
+  * 5.8M param MobileNet-V2 120d @ 77.3%
+
+### March 18, 2020
+* Add EfficientNet-Lite models w/ weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite)
+* Add RandAugment trained ResNeXt-50 32x4d weights with 79.8 top-1. Trained by [Andrew Lavin](https://github.com/andravin) (see Training section for hparams)
+
+### Feb 29, 2020
+* New MobileNet-V3 Large weights trained from stratch with this code to 75.77% top-1
+* IMPORTANT CHANGE - default weight init changed for all MobilenetV3 / EfficientNet / related models
+  * overall results similar to a bit better training from scratch on a few smaller models tried
+  * performance early in training seems consistently improved but less difference by end
+  * set `fix_group_fanout=False` in `_init_weight_goog` fn if you need to reproducte past behaviour
+* Experimental LR noise feature added applies a random perturbation to LR each epoch in specified range of training
+
+### Feb 18, 2020
+* Big refactor of model layers and addition of several attention mechanisms. Several additions motivated by 'Compounding the Performance Improvements...' (https://arxiv.org/abs/2001.06268):
+  * Move layer/module impl into `layers` subfolder/module of `models` and organize in a more granular fashion
+  * ResNet downsample paths now properly support dilation (output stride != 32) for avg_pool ('D' variant) and 3x3 (SENets) networks
+  * Add Selective Kernel Nets on top of ResNet base, pretrained weights
+    * skresnet18 - 73% top-1
+    * skresnet34 - 76.9% top-1 
+    * skresnext50_32x4d (equiv to SKNet50) - 80.2% top-1
+  * ECA and CECA (circular padding) attention layer contributed by [Chris Ha](https://github.com/VRandme)
+  * CBAM attention experiment (not the best results so far, may remove)
+  * Attention factory to allow dynamically selecting one of SE, ECA, CBAM in the `.se` position for all ResNets
+  * Add DropBlock and DropPath (formerly DropConnect for EfficientNet/MobileNetv3) support to all ResNet variants
+* Full dataset results updated that incl NoisyStudent weights and 2 of the 3 SK weights
+
+### Feb 12, 2020
+* Add EfficientNet-L2 and B0-B7 NoisyStudent weights ported from [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet)
--- a/docs/index.md
+++ b/docs/index.md
@ -0,0 +1,38 @@
+# Getting Started
+
+
+## Install
+
+The library can be installed with pip:
+
+```
+pip install timm
+```
+
+!!! info "Conda Environment"
+    All development and testing has been done in Conda Python 3 environments
+     on Linux x86-64 systems, specifically Python 3.6.x and 3.7.x. 
+
+    To install `timm` in a conda environment:
+    ```
+    conda create -n torch-env
+    conda activate torch-env
+    conda install -c pytorch pytorch torchvision cudatoolkit=10.1
+    conda install pyyaml
+    pip install timm
+    ```
+
+
+## Load Pretrained Model
+
+Pretrained models can be loaded using `timm.create_model`
+
+```python
+import timm
+
+m = timm.create_model('mobilenetv3_100', pretrained=True)
+m.eval()
+```
+
+To load a different model see [the list of pretrained weights](/models
+/#pretrained-imagenet-weights).
--- a/docs/models.md
+++ b/docs/models.md
@ -0,0 +1,275 @@
+
+## Architectures
+
+### ResNet / ResNeXt
+ (from [torchvision](https://github.com/pytorch/vision/tree
+/master/torchvision/models) with mods by myself)
+
+* ResNet-18, ResNet-34, ResNet-50, ResNet-101, ResNet-152, ResNeXt50 (32x4d), ResNeXt101 (32x4d and 64x4d)
+* 'Bag of Tricks' / Gluon C, D, E, S variations (https://arxiv.org/abs/1812.01187)
+* Instagram trained / ImageNet tuned ResNeXt101-32x8d to 32x48d from from [facebookresearch](https://pytorch.org/hub/facebookresearch_WSL-Images_resnext/)
+* Res2Net (https://github.com/gasvn/Res2Net, https://arxiv.org/abs/1904.01169)
+* Selective Kernel (SK) Nets (https://arxiv.org/abs/1903.06586)
+* ResNeSt (code adapted from https://github.com/zhanghang1989/ResNeSt, paper https://arxiv.org/abs/2004.08955)
+
+### DLA
+
+* Original (https://github.com/ucbdrive/dla, https://arxiv.org/abs/1707.06484)
+* Res2Net (https://github.com/gasvn/Res2Net, https://arxiv.org/abs/1904.01169)
+
+### DenseNet 
+
+(from [torchvision](https://github.com/pytorch/vision/tree/master
+/torchvision/models))
+
+* DenseNet-121, DenseNet-169, DenseNet-201, DenseNet-161
+
+### Squeeze-and-Excitation ResNet/ResNeXt 
+
+(from [Cadene](https://github.com
+/Cadene/pretrained-models.pytorch) with some pretrained weight additions by myself)
+
+* SENet-154, SE-ResNet-18, SE-ResNet-34, SE-ResNet-50, SE-ResNet-101, SE-ResNet-152, SE-ResNeXt-26 (32x4d), SE-ResNeXt50 (32x4d), SE-ResNeXt101 (32x4d)
+
+### Inception-V3 
+
+(from [torchvision](https://github.com/pytorch/vision/tree/master/torchvision/models))
+
+### Inception-ResNet-V2 and Inception-V4 
+
+(from [Cadene](https://github.com/Cadene/pretrained-models.pytorch) )
+
+### Xception
+
+* Original variant from [Cadene](https://github.com/Cadene/pretrained-models.pytorch)
+* MXNet Gluon 'modified aligned' Xception-65 and 71 models from [Gluon ModelZoo](https://github.com/dmlc/gluon-cv/tree/master/gluoncv/model_zoo)
+
+### PNasNet & NASNet-A
+
+ (from [Cadene](https://github.com/Cadene/pretrained-models.pytorch))
+ 
+### DPN
+ 
+ (from [myself](https://github.com/rwightman/pytorch-dpn-pretrained))
+
+* DPN-68, DPN-68b, DPN-92, DPN-98, DPN-131, DPN-107
+
+### EfficientNet 
+
+(from my standalone [GenEfficientNet](https://github.com/rwightman/gen-efficientnet-pytorch)) - A generic model that implements many of the efficient models that utilize similar DepthwiseSeparable and InvertedResidual blocks
+
+* EfficientNet NoisyStudent (B0-B7, L2) (https://arxiv.org/abs/1911.04252)
+* EfficientNet AdvProp (B0-B8) (https://arxiv.org/abs/1911.09665)
+* EfficientNet (B0-B7) (https://arxiv.org/abs/1905.11946)
+* EfficientNet-EdgeTPU (S, M, L) (https://ai.googleblog.com/2019/08/efficientnet-edgetpu-creating.html)
+* MixNet (https://arxiv.org/abs/1907.09595)
+* MNASNet B1, A1 (Squeeze-Excite), and Small (https://arxiv.org/abs/1807.11626)
+* MobileNet-V2 (https://arxiv.org/abs/1801.04381)    
+* FBNet-C (https://arxiv.org/abs/1812.03443)
+* Single-Path NAS (https://arxiv.org/abs/1904.02877)
+
+### MobileNet-V3
+ 
+ (https://arxiv.org/abs/1905.02244)
+
+### HRNet
+
+* code from https://github.com/HRNet/HRNet-Image-Classification, paper https://arxiv.org/abs/1908.07919
+
+### SelecSLS
+
+* code from https://github.com/mehtadushy/SelecSLS-Pytorch, paper https://arxiv.org/abs/1907.00837
+
+### TResNet
+
+* code from https://github.com/mrT23/TResNet, paper https://arxiv.org/abs/2003.13630
+
+### RegNet
+
+* paper `Designing Network Design Spaces` - https://arxiv.org/abs/2003.13678
+* reference code at https://github.com/facebookresearch/pycls/blob/master/pycls/models/regnet.py
+
+### VovNet V2 / V1
+
+* paper `CenterMask : Real-Time Anchor-Free Instance Segmentation` - https://arxiv.org/abs/1911.06667
+* reference code at https://github.com/youngwanLEE/vovnet-detectron2
+
+Use the  `--model` arg to specify model for train, validation, inference scripts. Match the all lowercase
+creation fn for the model you'd like.
+
+
+## Pretrained Imagenet Weights
+
+### Self-trained Weights
+
+|Model | Prec@1 (Err) | Prec@5 (Err) | Param # | Image Scaling  | Image Size |
+|---|---|---|---|---|---|
+| efficientnet_b3a | 81.874 (18.126) | 95.840 (4.160) | 12.23M | bicubic | 320 (1.0 crop) |
+| efficientnet_b3 | 81.498 (18.502) | 95.718 (4.282) | 12.23M | bicubic | 300 |
+| skresnext50d_32x4d | 81.278 (18.722) | 95.366 (4.634) | 27.5M | bicubic | 288 (1.0 crop) |
+| efficientnet_b2a | 80.608 (19.392) | 95.310 (4.690) | 9.11M | bicubic | 288 (1.0 crop) |
+| mixnet_xl | 80.478 (19.522) | 94.932 (5.068) | 11.90M | bicubic | 224 |
+| efficientnet_b2 | 80.402 (19.598) | 95.076 (4.924) | 9.11M | bicubic | 260 |
+| skresnext50d_32x4d | 80.156 (19.844) | 94.642 (5.358) | 27.5M | bicubic | 224 |
+| resnext50_32x4d | 79.762 (20.238) | 94.600 (5.400) | 25M | bicubic | 224 |
+| resnext50d_32x4d | 79.674 (20.326) | 94.868 (5.132) | 25.1M | bicubic | 224 |
+| ese_vovnet39b | 79.320 (20.680) | 94.710 (5.290) | 24.6M | bicubic | 224 |
+| resnetblur50 | 79.290 (20.710) | 94.632 (5.368) | 25.6M | bicubic | 224 |
+| resnet50 | 79.038 (20.962) | 94.390 (5.610) | 25.6M | bicubic | 224 |
+| mixnet_l | 78.976 (21.024 | 94.184 (5.816) | 7.33M | bicubic | 224 |
+| efficientnet_b1 | 78.692 (21.308) | 94.086 (5.914) | 7.79M | bicubic | 240 |
+| efficientnet_es | 78.066 (21.934) | 93.926 (6.074) | 5.44M | bicubic | 224 |
+| seresnext26t_32x4d | 77.998 (22.002) | 93.708 (6.292) | 16.8M | bicubic | 224 |
+| seresnext26tn_32x4d | 77.986 (22.014) | 93.746 (6.254) | 16.8M | bicubic | 224 |
+| efficientnet_b0 | 77.698 (22.302) | 93.532 (6.468) | 5.29M | bicubic | 224 |
+| seresnext26d_32x4d | 77.602 (22.398) | 93.608 (6.392) | 16.8M | bicubic | 224 |
+| mobilenetv2_120d | 77.294 (22.706 | 93.502 (6.498) | 5.8M | bicubic | 224 |
+| mixnet_m | 77.256 (22.744) | 93.418 (6.582) | 5.01M | bicubic | 224 |
+| seresnext26_32x4d | 77.104 (22.896) | 93.316 (6.684) | 16.8M | bicubic | 224 |
+| skresnet34 | 76.912 (23.088) | 93.322 (6.678) | 22.2M | bicubic | 224 |
+| ese_vovnet19b_dw | 76.798 (23.202) | 93.268 (6.732) | 6.5M | bicubic | 224 |
+| resnet26d | 76.68 (23.32) | 93.166 (6.834) | 16M | bicubic | 224 |
+| densenetblur121d | 76.576 (23.424) | 93.190 (6.810) | 8.0M | bicubic | 224 |
+| mobilenetv2_140 | 76.524 (23.476) | 92.990 (7.010) | 6.1M | bicubic | 224 |
+| mixnet_s | 75.988 (24.012) | 92.794 (7.206) | 4.13M | bicubic | 224 |
+| mobilenetv3_large_100 | 75.766 (24.234) | 92.542 (7.458) | 5.5M | bicubic | 224 |
+| mobilenetv3_rw | 75.634 (24.366) | 92.708 (7.292) | 5.5M | bicubic | 224 |
+| mnasnet_a1 | 75.448 (24.552) | 92.604 (7.396) | 3.89M | bicubic | 224 |
+| resnet26 | 75.292 (24.708) | 92.57 (7.43) | 16M | bicubic | 224 |
+| fbnetc_100 | 75.124 (24.876) | 92.386 (7.614) | 5.6M | bilinear | 224 |
+| resnet34 | 75.110 (24.890) | 92.284 (7.716) | 22M | bilinear | 224 |
+| mobilenetv2_110d | 75.052 (24.948) | 92.180 (7.820) | 4.5M | bicubic | 224 |
+| seresnet34 | 74.808 (25.192) | 92.124 (7.876) | 22M | bilinear | 224 |
+| mnasnet_b1 | 74.658 (25.342) | 92.114 (7.886) | 4.38M | bicubic | 224 |
+| spnasnet_100 | 74.084 (25.916)  | 91.818 (8.182) | 4.42M | bilinear | 224 |
+| skresnet18 | 73.038 (26.962) | 91.168 (8.832) | 11.9M | bicubic | 224 |
+| mobilenetv2_100 | 72.978 (27.022) | 91.016 (8.984) | 3.5M | bicubic | 224 |
+| seresnet18 | 71.742 (28.258) | 90.334 (9.666) | 11.8M | bicubic | 224 |
+
+
+
+### Ported Weights
+For the models below, the model code and weight porting from Tensorflow or MXNet Gluon to Pytorch was done by myself. There are weights/models ported by others included in this repository, they are not listed below.
+
+| Model | Prec@1 (Err) | Prec@5 (Err) | Param # | Image Scaling | Image Size |
+|---|---|---|---|---|---|
+| tf_efficientnet_l2_ns *tfp | 88.352 (11.648) | 98.652 (1.348) | 480 | bicubic | 800 |
+| tf_efficientnet_l2_ns      | TBD | TBD | 480 | bicubic | 800 |
+| tf_efficientnet_l2_ns_475      | 88.234 (11.766) | 98.546 (1.454)f | 480 | bicubic | 475 |
+| tf_efficientnet_l2_ns_475 *tfp | 88.172 (11.828) | 98.566 (1.434) | 480 | bicubic | 475 |
+| tf_efficientnet_b7_ns *tfp | 86.844 (13.156) | 98.084 (1.916) | 66.35 | bicubic | 600 |
+| tf_efficientnet_b7_ns      | 86.840 (13.160) | 98.094 (1.906) | 66.35 | bicubic | 600 |
+| tf_efficientnet_b6_ns      | 86.452 (13.548) | 97.882 (2.118) | 43.04 | bicubic | 528 |
+| tf_efficientnet_b6_ns *tfp | 86.444 (13.556) | 97.880 (2.120) | 43.04 | bicubic | 528 |
+| tf_efficientnet_b5_ns *tfp | 86.064 (13.936) | 97.746 (2.254) | 30.39 | bicubic | 456 |
+| tf_efficientnet_b5_ns      | 86.088 (13.912) | 97.752 (2.248) | 30.39 | bicubic | 456 |
+| tf_efficientnet_b8_ap *tfp | 85.436 (14.564) | 97.272 (2.728) | 87.4 | bicubic | 672 |
+| tf_efficientnet_b8 *tfp    | 85.384 (14.616) | 97.394 (2.606) | 87.4 | bicubic | 672 |
+| tf_efficientnet_b8         | 85.370 (14.630) | 97.390 (2.610) | 87.4 | bicubic | 672 |
+| tf_efficientnet_b8_ap      | 85.368 (14.632) | 97.294 (2.706) | 87.4 | bicubic | 672 |
+| tf_efficientnet_b4_ns *tfp | 85.298 (14.702) | 97.504 (2.496) | 19.34 | bicubic | 380 |
+| tf_efficientnet_b4_ns      | 85.162 (14.838) | 97.470 (2.530) | 19.34 | bicubic | 380 |
+| tf_efficientnet_b7_ap *tfp | 85.154 (14.846) | 97.244 (2.756) | 66.35 | bicubic | 600 |
+| tf_efficientnet_b7_ap      | 85.118 (14.882) | 97.252 (2.748) | 66.35 | bicubic | 600 |
+| tf_efficientnet_b7 *tfp    | 84.940 (15.060) | 97.214 (2.786) | 66.35 | bicubic | 600 |
+| tf_efficientnet_b7         | 84.932 (15.068) | 97.208 (2.792) | 66.35 | bicubic | 600 |
+| tf_efficientnet_b6_ap      | 84.786 (15.214) | 97.138 (2.862) | 43.04 | bicubic | 528 |
+| tf_efficientnet_b6_ap *tfp | 84.760 (15.240) | 97.124 (2.876) | 43.04 | bicubic | 528 |
+| tf_efficientnet_b5_ap *tfp | 84.276 (15.724) | 96.932 (3.068) | 30.39 | bicubic | 456 |
+| tf_efficientnet_b5_ap      | 84.254 (15.746) | 96.976 (3.024) | 30.39 | bicubic | 456 |
+| tf_efficientnet_b6 *tfp    | 84.140 (15.860) | 96.852 (3.148) | 43.04 | bicubic | 528 |
+| tf_efficientnet_b6         | 84.110 (15.890) | 96.886 (3.114) | 43.04 | bicubic | 528 |
+| tf_efficientnet_b3_ns *tfp | 84.054 (15.946) | 96.918 (3.082) | 12.23 | bicubic | 300 |
+| tf_efficientnet_b3_ns      | 84.048 (15.952) | 96.910 (3.090) | 12.23 | bicubic | 300 |
+| tf_efficientnet_b5 *tfp    | 83.822 (16.178) | 96.756 (3.244) | 30.39 | bicubic | 456 |
+| tf_efficientnet_b5         | 83.812 (16.188) | 96.748 (3.252) | 30.39 | bicubic | 456 |
+| tf_efficientnet_b4_ap *tfp | 83.278 (16.722) | 96.376 (3.624) | 19.34 | bicubic | 380 |
+| tf_efficientnet_b4_ap      | 83.248 (16.752) | 96.388 (3.612) | 19.34 | bicubic | 380 |
+| tf_efficientnet_b4         | 83.022 (16.978) | 96.300 (3.700) | 19.34 | bicubic | 380 |
+| tf_efficientnet_b4 *tfp    | 82.948 (17.052) | 96.308 (3.692) | 19.34 | bicubic | 380 |
+| tf_efficientnet_b2_ns *tfp | 82.436 (17.564) | 96.268 (3.732) | 9.11 | bicubic | 260 |
+| tf_efficientnet_b2_ns      | 82.380 (17.620) | 96.248 (3.752) | 9.11 | bicubic | 260 |
+| tf_efficientnet_b3_ap *tfp | 81.882 (18.118) | 95.662 (4.338) | 12.23 | bicubic | 300 |
+| tf_efficientnet_b3_ap      | 81.828 (18.172) | 95.624 (4.376) | 12.23 | bicubic | 300 |
+| tf_efficientnet_b3         | 81.636 (18.364) | 95.718 (4.282) | 12.23 | bicubic | 300 |
+| tf_efficientnet_b3 *tfp    | 81.576 (18.424) | 95.662 (4.338) | 12.23 | bicubic | 300 |
+| tf_efficientnet_lite4      | 81.528 (18.472) | 95.668 (4.332) | 13.00  | bilinear | 380 |
+| tf_efficientnet_b1_ns *tfp | 81.514 (18.486) | 95.776 (4.224) | 7.79 | bicubic | 240 |
+| tf_efficientnet_lite4 *tfp | 81.502 (18.498) | 95.676 (4.324) | 13.00  | bilinear | 380 |
+| tf_efficientnet_b1_ns      | 81.388 (18.612) | 95.738 (4.262) | 7.79 | bicubic | 240 |
+| gluon_senet154           | 81.224 (18.776) | 95.356 (4.644) | 115.09 | bicubic | 224 |
+| gluon_resnet152_v1s      | 81.012 (18.988) | 95.416 (4.584) | 60.32  | bicubic | 224 |
+| gluon_seresnext101_32x4d | 80.902 (19.098) | 95.294 (4.706) | 48.96  | bicubic | 224 |
+| gluon_seresnext101_64x4d | 80.890 (19.110) | 95.304 (4.696) | 88.23  | bicubic | 224 |
+| gluon_resnext101_64x4d   | 80.602 (19.398) | 94.994 (5.006) | 83.46  | bicubic | 224 |
+| tf_efficientnet_el       | 80.534 (19.466) | 95.190 (4.810) | 10.59 | bicubic | 300 |
+| tf_efficientnet_el *tfp  | 80.476 (19.524) | 95.200 (4.800) | 10.59 | bicubic | 300 |
+| gluon_resnet152_v1d      | 80.470 (19.530) | 95.206 (4.794) | 60.21  | bicubic | 224 |
+| gluon_resnet101_v1d      | 80.424 (19.576) | 95.020 (4.980) | 44.57  | bicubic | 224 |
+| tf_efficientnet_b2_ap *tfp | 80.420 (19.580) | 95.040 (4.960) | 9.11 | bicubic | 260 |
+| gluon_resnext101_32x4d   | 80.334 (19.666) | 94.926 (5.074) | 44.18  | bicubic | 224 |
+| tf_efficientnet_b2_ap    | 80.306 (19.694) | 95.028 (4.972) | 9.11 | bicubic | 260 |
+| gluon_resnet101_v1s      | 80.300 (19.700) | 95.150 (4.850) | 44.67  | bicubic | 224 |
+| tf_efficientnet_b2 *tfp  | 80.188 (19.812) | 94.974 (5.026) | 9.11  | bicubic | 260 |
+| tf_efficientnet_b2       | 80.086 (19.914) | 94.908 (5.092) | 9.11  | bicubic | 260 |
+| gluon_resnet152_v1c      | 79.916 (20.084) | 94.842 (5.158) | 60.21  | bicubic | 224 |
+| gluon_seresnext50_32x4d  | 79.912 (20.088) | 94.818 (5.182) | 27.56  | bicubic | 224 |
+| tf_efficientnet_lite3       | 79.812 (20.188) | 94.914 (5.086) | 8.20  | bilinear | 300 |
+| tf_efficientnet_lite3 *tfp  | 79.734 (20.266) | 94.838 (5.162) | 8.20  | bilinear | 300 |
+| gluon_resnet152_v1b      | 79.692 (20.308) | 94.738 (5.262) | 60.19  | bicubic | 224 |
+| gluon_xception65         | 79.604 (20.396) | 94.748 (5.252) | 39.92  | bicubic | 299 |
+| gluon_resnet101_v1c      | 79.544 (20.456) | 94.586 (5.414) | 44.57  | bicubic | 224 |
+| tf_efficientnet_b1_ap *tfp | 79.532 (20.468) | 94.378 (5.622) | 7.79 | bicubic | 240 |
+| tf_efficientnet_cc_b1_8e *tfp | 79.464 (20.536)| 94.492 (5.508) | 39.7 | bicubic | 240 |
+| gluon_resnext50_32x4d    | 79.356 (20.644) | 94.424 (5.576) | 25.03  | bicubic | 224 |
+| gluon_resnet101_v1b      | 79.304 (20.696) | 94.524 (5.476) | 44.55  | bicubic | 224 |
+| tf_efficientnet_cc_b1_8e | 79.298 (20.702) | 94.364 (5.636) | 39.7 | bicubic | 240 |
+| tf_efficientnet_b1_ap    | 79.278 (20.722) | 94.308 (5.692) | 7.79 | bicubic | 240 |
+| tf_efficientnet_b1 *tfp  | 79.172 (20.828) | 94.450 (5.550) | 7.79  | bicubic | 240 |
+| gluon_resnet50_v1d       | 79.074 (20.926) | 94.476 (5.524) | 25.58  | bicubic | 224 |
+| tf_efficientnet_em *tfp  | 78.958 (21.042) | 94.458 (5.542) | 6.90 | bicubic | 240 |
+| tf_mixnet_l *tfp         | 78.846 (21.154) | 94.212 (5.788) | 7.33  | bilinear | 224 |
+| tf_efficientnet_b1       | 78.826 (21.174) | 94.198 (5.802) | 7.79  | bicubic | 240 |
+| tf_efficientnet_b0_ns *tfp | 78.806 (21.194) | 94.496 (5.504) | 5.29 | bicubic | 224 |
+| gluon_inception_v3       | 78.804 (21.196) | 94.380 (5.620) | 27.16M | bicubic | 299 |
+| tf_mixnet_l              | 78.770 (21.230) | 94.004 (5.996) | 7.33  | bicubic | 224 |
+| tf_efficientnet_em       | 78.742 (21.258) | 94.332 (5.668) | 6.90 | bicubic | 240 |
+| gluon_resnet50_v1s       | 78.712 (21.288) | 94.242 (5.758) | 25.68  | bicubic | 224 |
+| tf_efficientnet_b0_ns    | 78.658 (21.342) | 94.376 (5.624) | 5.29 | bicubic | 224 |
+| tf_efficientnet_cc_b0_8e *tfp | 78.314 (21.686) | 93.790 (6.210) | 24.0 | bicubic | 224 |
+| gluon_resnet50_v1c       | 78.010 (21.990) | 93.988 (6.012) | 25.58  | bicubic | 224 |
+| tf_efficientnet_cc_b0_8e | 77.908 (22.092) | 93.656 (6.344) | 24.0 | bicubic | 224 |
+| tf_inception_v3          | 77.856 (22.144) | 93.644 (6.356) | 27.16M | bicubic | 299 |
+| tf_efficientnet_cc_b0_4e *tfp | 77.746 (22.254) | 93.552 (6.448) | 13.3 | bicubic | 224 |
+| tf_efficientnet_es *tfp  | 77.616 (22.384) | 93.750 (6.250) | 5.44 | bicubic | 224 |
+| gluon_resnet50_v1b       | 77.578 (22.422) | 93.718 (6.282) | 25.56  | bicubic | 224 |
+| adv_inception_v3         | 77.576 (22.424) | 93.724 (6.276) | 27.16M | bicubic | 299 |
+| tf_efficientnet_lite2 *tfp  | 77.544 (22.456) | 93.800 (6.200) | 6.09  | bilinear | 260 |
+| tf_efficientnet_lite2       | 77.460 (22.540) | 93.746 (6.254) | 6.09  | bicubic | 260 |
+| tf_efficientnet_b0_ap *tfp | 77.514 (22.486) | 93.576 (6.424) | 5.29  | bicubic | 224 |
+| tf_efficientnet_cc_b0_4e | 77.304 (22.696) | 93.332 (6.668) | 13.3 | bicubic | 224 |
+| tf_efficientnet_es       | 77.264 (22.736) | 93.600 (6.400) | 5.44 | bicubic | 224 |
+| tf_efficientnet_b0 *tfp  | 77.258 (22.742) | 93.478 (6.522) | 5.29  | bicubic | 224 |
+| tf_efficientnet_b0_ap    | 77.084 (22.916) | 93.254 (6.746) | 5.29  | bicubic | 224 |
+| tf_mixnet_m *tfp         | 77.072 (22.928) | 93.368 (6.632) | 5.01  | bilinear | 224 |
+| tf_mixnet_m              | 76.950 (23.050) | 93.156 (6.844) | 5.01  | bicubic | 224 |
+| tf_efficientnet_b0       | 76.848 (23.152) | 93.228 (6.772) | 5.29  | bicubic | 224 |
+| tf_efficientnet_lite1 *tfp  | 76.764 (23.236) | 93.326 (6.674) | 5.42  | bilinear | 240 |
+| tf_efficientnet_lite1       | 76.638 (23.362) | 93.232 (6.768) | 5.42  | bicubic | 240 |
+| tf_mixnet_s *tfp         | 75.800 (24.200) | 92.788 (7.212) | 4.13  | bilinear | 224 |
+| tf_mobilenetv3_large_100 *tfp | 75.768 (24.232) | 92.710 (7.290) | 5.48 | bilinear | 224 |
+| tf_mixnet_s              | 75.648 (24.352) | 92.636 (7.364) | 4.13  | bicubic | 224 |
+| tf_mobilenetv3_large_100 | 75.516 (24.484) | 92.600 (7.400) | 5.48 | bilinear | 224 |
+| tf_efficientnet_lite0 *tfp  | 75.074 (24.926) | 92.314 (7.686) | 4.65  | bilinear | 224 |
+| tf_efficientnet_lite0       | 74.842 (25.158) | 92.170 (7.830) | 4.65  | bicubic | 224 |
+| gluon_resnet34_v1b       | 74.580 (25.420) | 91.988 (8.012) | 21.80 | bicubic | 224 |
+| tf_mobilenetv3_large_075 *tfp | 73.730 (26.270) | 91.616 (8.384) | 3.99 | bilinear | 224 |
+| tf_mobilenetv3_large_075 | 73.442 (26.558) | 91.352 (8.648) | 3.99 | bilinear | 224 |
+| tf_mobilenetv3_large_minimal_100 *tfp | 72.678 (27.322) | 90.860 (9.140) | 3.92 | bilinear | 224 |
+| tf_mobilenetv3_large_minimal_100 | 72.244 (27.756) | 90.636 (9.364) | 3.92 | bilinear | 224 |
+| tf_mobilenetv3_small_100 *tfp | 67.918 (32.082) | 87.958 (12.042 | 2.54 | bilinear | 224 |
+| tf_mobilenetv3_small_100 | 67.918 (32.082) | 87.662 (12.338) | 2.54 | bilinear | 224 |
+| tf_mobilenetv3_small_075 *tfp | 66.142 (33.858) | 86.498 (13.502) | 2.04 | bilinear | 224 |
+| tf_mobilenetv3_small_075 | 65.718 (34.282) | 86.136 (13.864) | 2.04 | bilinear | 224 |
+| tf_mobilenetv3_small_minimal_100 *tfp | 63.378 (36.622) | 84.802 (15.198) | 2.04 | bilinear | 224 |
+| tf_mobilenetv3_small_minimal_100 | 62.898 (37.102) | 84.230 (15.770) | 2.04 | bilinear | 224 |
--- a/mkdocs.yml
+++ b/mkdocs.yml
@ -0,0 +1,34 @@
+site_name: 'Pytorch Image Models'
+site_description: 'Pretained Image Recognition Models'
+repo_name: 'rwightman/pytorch-image-models'
+repo_url: 'https://github.com/rwightman/pytorch-image-models'
+nav:
+  - index.md
+  - models.md
+  - changes.md
+theme:
+  name: 'material'
+  feature:
+    tabs: false
+extra_javascript:
+  - 'https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-MML-AM_CHTML'
+markdown_extensions:
+  - codehilite:
+      linenums: true
+  - admonition
+  - pymdownx.arithmatex
+  - pymdownx.betterem:
+      smart_enable: all
+  - pymdownx.caret
+  - pymdownx.critic
+  - pymdownx.details
+  - pymdownx.emoji:
+      emoji_generator: !!python/name:pymdownx.emoji.to_svg
+  - pymdownx.inlinehilite
+  - pymdownx.magiclink
+  - pymdownx.mark
+  - pymdownx.smartsymbols
+  - pymdownx.superfences
+  - pymdownx.tasklist:
+      custom_checkbox: true
+  - pymdownx.tilde
--- a/requirements-docs.txt
+++ b/requirements-docs.txt
@ -0,0 +1,2 @@
+mkdocs==1.1.2
+mkdocs-material==5.4.0
--- a/results/README.md
+++ b/results/README.md
@ -35,5 +35,4 @@ An ImageNet test set of 10,000 images sampled from new images roughly 10 years a
 A collection of 7500 images covering 200 of the 1000 ImageNet classes. Images are naturally occuring adversarial examples that confuse typical ImageNet classifiers. This is a challenging dataset, your typical ResNet-50 will score 0% top-1.

 ## TODO
-* Add rank difference, and top-1/top-5 difference from ImageNet-1k validation for the 3 additional test sets
 * Explore adding a reduced version of ImageNet-C (Corruptions) and ImageNet-P (Perturbations) from https://github.com/hendrycks/robustness. The originals are huge and image size specific.
--- a/results/generate_csv_results.py
+++ b/results/generate_csv_results.py
@ -0,0 +1,52 @@
+import numpy as np
+import pandas as pd
+
+results = {
+    'results-imagenet.csv'                    : pd.read_csv('results-imagenet.csv'), 
+    'results-imagenetv2-matched-frequency.csv': pd.read_csv('results-imagenetv2-matched-frequency.csv'),
+    'results-sketch.csv'                      : pd.read_csv('results-sketch.csv'),
+    'results-imagenet-a.csv'                  : pd.read_csv('results-imagenet-a.csv'),
+}
+
+def diff(csv_file):    
+    base_models = results['results-imagenet.csv']['model'].values
+    csv_models  = results[csv_file]['model'].values
+
+    rank_diff = np.zeros_like(csv_models, dtype='object')
+    top1_diff = np.zeros_like(csv_models, dtype='object')
+    top5_diff = np.zeros_like(csv_models, dtype='object')
+    
+    for rank, model in enumerate(csv_models):
+        if model in base_models:            
+            base_rank = int(np.where(base_models==model)[0])
+            top1_d = results[csv_file]['top1'][rank]-results['results-imagenet.csv']['top1'][base_rank]
+            top5_d = results[csv_file]['top5'][rank]-results['results-imagenet.csv']['top5'][base_rank]
+            
+            # rank_diff
+            if   rank == base_rank: rank_diff[rank] = f'='
+            elif rank >  base_rank: rank_diff[rank] = f'-{rank-base_rank}'
+            else:                   rank_diff[rank] = f'+{base_rank-rank}'
+                
+            # top1_diff
+            if top1_d >= .0: top1_diff[rank] = f'+{top1_d:.3f}'
+            else           : top1_diff[rank] = f'-{abs(top1_d):.3f}'
+            
+            # top5_diff
+            if top5_d >= .0: top5_diff[rank] = f'+{top5_d:.3f}'
+            else           : top5_diff[rank] = f'-{abs(top5_d):.3f}'
+                
+        else: 
+            rank_diff[rank] = 'X'
+            top1_diff[rank] = 'X'
+            top5_diff[rank] = 'X'
+    
+    results[csv_file]['rank_diff'] = rank_diff
+    results[csv_file]['top1_diff'] = top1_diff
+    results[csv_file]['top5_diff'] = top5_diff
+    
+    results[csv_file]['param_count'] = results[csv_file]['param_count'].map('{:,.2f}'.format)
+
+    results[csv_file].to_csv(csv_file, index=False, float_format='%.3f')
+
+for csv_file in results:
+    if csv_file != 'results-imagenet.csv': diff(csv_file)
--- a/results/results-imagenet-a.csv
+++ b/results/results-imagenet-a.csv
@ -1,239 +1,239 @@
-model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation
-tf_efficientnet_l2_ns_475,62.3867,37.6133,87.1067,12.8933,480.31,475,0.936,bicubic
-tf_efficientnet_l2_ns,62.0267,37.9733,87.96,12.04,480.31,800,0.96,bicubic
-tf_efficientnet_b7_ns,45.72,54.28,74.2,25.8,66.35,600,0.949,bicubic
-ig_resnext101_32x48d,41.5733,58.4267,66.6133,33.3867,828.41,224,0.875,bilinear
-tf_efficientnet_b6_ns,40.4267,59.5733,68.84,31.16,43.04,528,0.942,bicubic
-ig_resnext101_32x32d,39.4133,60.5867,63.76,36.24,468.53,224,0.875,bilinear
-tf_efficientnet_b5_ns,39.0133,60.9867,68.04,31.96,30.39,456,0.934,bicubic
-ig_resnext101_32x16d,36.0533,63.9467,59.04,40.96,194.03,224,0.875,bilinear
-swsl_resnext101_32x8d,32.0667,67.9333,59.4,40.6,88.79,224,0.875,bilinear
-tf_efficientnet_b4_ns,30.8,69.2,59.44,40.56,19.34,380,0.922,bicubic
-tf_efficientnet_b8_ap,29.6,70.4,56.9333,43.0667,87.41,672,0.954,bicubic
-tf_efficientnet_b8,29.3733,70.6267,57.0667,42.9333,87.41,672,0.954,bicubic
-ig_resnext101_32x8d,28.7067,71.2933,52.32,47.68,88.79,224,0.875,bilinear
-swsl_resnext101_32x16d,27.9467,72.0533,52.32,47.68,194.03,224,0.875,bilinear
-tf_efficientnet_b7_ap,27.8133,72.1867,54.7733,45.2267,66.35,600,0.949,bicubic
-resnest269e,27.6133,72.3867,53.1067,46.8933,110.93,416,0.875,bilinear
-tresnet_xl_448,26.88,73.12,51.0933,48.9067,78.44,448,0.875,bilinear
-resnest200e,26.4267,73.5733,51.9333,48.0667,70.2,320,0.875,bilinear
-swsl_resnext101_32x4d,25.3467,74.6533,49.6267,50.3733,44.18,224,0.875,bilinear
-tf_efficientnet_b7,25.2533,74.7467,51.6667,48.3333,66.35,600,0.949,bicubic
-tresnet_l_448,24.5733,75.4267,48.6,51.4,55.99,448,0.875,bilinear
-tf_efficientnet_b6_ap,24.3467,75.6533,50.4267,49.5733,43.04,528,0.942,bicubic
-tf_efficientnet_b6,20.3733,79.6267,45.4933,54.5067,43.04,528,0.942,bicubic
-tresnet_m_448,19.68,80.32,42.76,57.24,31.39,448,0.875,bilinear
-tf_efficientnet_b5_ap,19.4667,80.5333,44.72,55.28,30.39,456,0.934,bicubic
-tf_efficientnet_b3_ns,19.4133,80.5867,44.6267,55.3733,12.23,300,0.904,bicubic
-swsl_resnext50_32x4d,18.0667,81.9333,41.8667,58.1333,25.03,224,0.875,bilinear
-ssl_resnext101_32x16d,17.2133,82.7867,39.9467,60.0533,194.03,224,0.875,bilinear
-tf_efficientnet_b5,17.0667,82.9333,41.9067,58.0933,30.39,456,0.934,bicubic
-resnest101e,16.4933,83.5067,40.7467,59.2533,48.28,256,0.875,bilinear
-swsl_resnet50,15.9867,84.0133,38.8533,61.1467,25.56,224,0.875,bilinear
-ssl_resnext101_32x8d,15.12,84.88,37.72,62.28,88.79,224,0.875,bilinear
-tf_efficientnet_b4_ap,13.68,86.32,35.92,64.08,19.34,380,0.922,bicubic
-ecaresnet101d,13.3067,86.6933,35.5333,64.4667,44.57,224,0.875,bicubic
-tf_efficientnet_b4,13.3067,86.6933,35.52,64.48,19.34,380,0.922,bicubic
-pnasnet5large,13.08,86.92,32.2133,67.7867,86.06,331,0.875,bicubic
-nasnetalarge,12.5733,87.4267,33.4133,66.5867,88.75,331,0.875,bicubic
-ssl_resnext101_32x4d,12.12,87.88,31.8933,68.1067,44.18,224,0.875,bilinear
-tf_efficientnet_b2_ns,11.7867,88.2133,32.96,67.04,9.11,260,0.89,bicubic
-gluon_senet154,9.9067,90.0933,26.4533,73.5467,115.09,224,0.875,bicubic
-resnest50d_4s2x40d,9.7867,90.2133,29.1467,70.8533,30.42,224,0.875,bicubic
-ssl_resnext50_32x4d,9.6667,90.3333,28.4267,71.5733,25.03,224,0.875,bilinear
-senet154,9.4533,90.5467,26.44,73.56,115.09,224,0.875,bilinear
-tresnet_xl,9.3067,90.6933,28.4133,71.5867,78.44,224,0.875,bilinear
-efficientnet_b3a,9.2667,90.7333,28.4267,71.5733,12.23,320,1.0,bicubic
-efficientnet_b3,8.9467,91.0533,28.2133,71.7867,12.23,300,0.904,bicubic
-inception_v4,8.92,91.08,24.7067,75.2933,42.68,299,0.875,bicubic
-gluon_seresnext101_64x4d,8.8667,91.1333,27.32,72.68,88.23,224,0.875,bicubic
-tf_efficientnet_b1_ns,8.6133,91.3867,27.28,72.72,7.79,240,0.882,bicubic
-resnest50d_1s4x24d,8.52,91.48,26.7867,73.2133,25.68,224,0.875,bicubic
-ecaresnet50d,8.5067,91.4933,26.2667,73.7333,25.58,224,0.875,bicubic
-gluon_xception65,8.4667,91.5333,25.1333,74.8667,39.92,299,0.875,bicubic
-gluon_resnet152_v1d,8.4133,91.5867,23.4533,76.5467,60.21,224,0.875,bicubic
-inception_resnet_v2,8.16,91.84,23.5333,76.4667,55.84,299,0.8975,bicubic
-tf_efficientnet_b3_ap,8.1333,91.8667,26.28,73.72,12.23,300,0.904,bicubic
-gluon_seresnext101_32x4d,8.04,91.96,24.7333,75.2667,48.96,224,0.875,bicubic
-tf_efficientnet_b3,8.0133,91.9867,25.4667,74.5333,12.23,300,0.904,bicubic
-ens_adv_inception_resnet_v2,7.9867,92.0133,23.8267,76.1733,55.84,299,0.8975,bicubic
-tf_efficientnet_lite4,7.9333,92.0667,25.56,74.44,13.01,380,0.92,bilinear
-tresnet_l,7.88,92.12,25.1867,74.8133,55.99,224,0.875,bilinear
-gluon_resnet152_v1s,7.8667,92.1333,23.1733,76.8267,60.32,224,0.875,bicubic
-resnest50d,7.7467,92.2533,25.2933,74.7067,27.48,224,0.875,bilinear
-gluon_resnext101_64x4d,7.7067,92.2933,23.24,76.76,83.46,224,0.875,bicubic
-skresnext50_32x4d,7.08,92.92,23.0267,76.9733,27.48,224,0.875,bicubic
-ssl_resnet50,7.0,93.0,23.92,76.08,25.56,224,0.875,bilinear
-regnety_320,6.92,93.08,23.04,76.96,145.05,224,0.875,bicubic
-ecaresnet101d_pruned,6.8,93.2,24.2,75.8,24.88,224,0.875,bicubic
-ecaresnetlight,6.76,93.24,22.56,77.44,30.16,224,0.875,bicubic
-efficientnet_b2a,6.76,93.24,23.4933,76.5067,9.11,288,1.0,bicubic
-seresnext101_32x4d,6.4133,93.5867,21.52,78.48,48.96,224,0.875,bilinear
-efficientnet_b2,6.0933,93.9067,21.9333,78.0667,9.11,260,0.875,bicubic
-gluon_resnext101_32x4d,6.04,93.96,21.1333,78.8667,44.18,224,0.875,bicubic
-regnetx_320,5.9867,94.0133,19.88,80.12,107.81,224,0.875,bicubic
-ese_vovnet39b,5.9733,94.0267,21.2933,78.7067,24.57,224,0.875,bicubic
-gluon_resnet101_v1d,5.92,94.08,19.9467,80.0533,44.57,224,0.875,bicubic
-gluon_seresnext50_32x4d,5.7867,94.2133,21.4267,78.5733,27.56,224,0.875,bicubic
-efficientnet_b3_pruned,5.7333,94.2667,21.36,78.64,9.86,300,0.904,bicubic
-regnety_160,5.64,94.36,19.3467,80.6533,83.59,224,0.875,bicubic
-gluon_inception_v3,5.5067,94.4933,19.9467,80.0533,23.83,299,0.875,bicubic
-mixnet_xl,5.48,94.52,21.0933,78.9067,11.9,224,0.875,bicubic
-tresnet_m,5.44,94.56,19.96,80.04,31.39,224,0.875,bilinear
-regnety_120,5.4133,94.5867,19.8533,80.1467,51.82,224,0.875,bicubic
-gluon_resnet101_v1s,5.28,94.72,19.5467,80.4533,44.67,224,0.875,bicubic
-hrnet_w64,5.1333,94.8667,19.4533,80.5467,128.06,224,0.875,bilinear
-regnety_080,5.0,95.0,18.6,81.4,39.18,224,0.875,bicubic
-efficientnet_b2_pruned,4.9467,95.0533,19.3467,80.6533,8.31,260,0.89,bicubic
-dpn107,4.88,95.12,17.6133,82.3867,86.92,224,0.875,bicubic
-gluon_resnet152_v1c,4.8667,95.1333,17.7733,82.2267,60.21,224,0.875,bicubic
-adv_inception_v3,4.7467,95.2533,17.5467,82.4533,23.83,299,0.875,bicubic
-dla102x2,4.7467,95.2533,18.96,81.04,41.75,224,0.875,bilinear
-tf_inception_v3,4.7467,95.2533,17.7467,82.2533,23.83,299,0.875,bicubic
-hrnet_w48,4.72,95.28,18.44,81.56,77.47,224,0.875,bilinear
-dpn131,4.64,95.36,16.8667,83.1333,79.25,224,0.875,bicubic
-gluon_resnet152_v1b,4.5867,95.4133,16.5333,83.4667,60.19,224,0.875,bicubic
-ecaresnet50d_pruned,4.5467,95.4533,18.5467,81.4533,19.94,224,0.875,bicubic
-dpn92,4.4933,95.5067,18.2,81.8,37.67,224,0.875,bicubic
-hrnet_w44,4.4933,95.5067,17.3467,82.6533,67.06,224,0.875,bilinear
-regnetx_160,4.3733,95.6267,17.0933,82.9067,54.28,224,0.875,bicubic
-resnext50d_32x4d,4.3467,95.6533,17.7733,82.2267,25.05,224,0.875,bicubic
-xception,4.3467,95.6533,16.76,83.24,22.86,299,0.8975,bicubic
-seresnext50_32x4d,4.28,95.72,17.8133,82.1867,27.56,224,0.875,bilinear
-resnext50_32x4d,4.2533,95.7467,18.3867,81.6133,25.03,224,0.875,bicubic
-tf_efficientnet_cc_b1_8e,4.24,95.76,15.9467,84.0533,39.72,240,0.882,bicubic
-regnety_064,4.2267,95.7733,17.1867,82.8133,30.58,224,0.875,bicubic
-tf_efficientnet_el,4.2267,95.7733,18.1733,81.8267,10.59,300,0.904,bicubic
-inception_v3,4.1867,95.8133,16.2933,83.7067,23.83,299,0.875,bicubic
-tf_efficientnet_b2_ap,4.1733,95.8267,18.32,81.68,9.11,260,0.89,bicubic
-seresnet152,4.1467,95.8533,15.8933,84.1067,66.82,224,0.875,bilinear
-resnext101_32x8d,4.1333,95.8667,16.9867,83.0133,88.79,224,0.875,bilinear
-tf_efficientnet_b0_ns,4.1333,95.8667,17.68,82.32,5.29,224,0.875,bicubic
-dpn98,4.08,95.92,15.9467,84.0533,61.57,224,0.875,bicubic
-res2net101_26w_4s,4.0,96.0,14.8267,85.1733,45.21,224,0.875,bilinear
-efficientnet_b1,3.9733,96.0267,15.76,84.24,7.79,240,0.875,bicubic
-tf_efficientnet_lite3,3.9333,96.0667,16.52,83.48,8.2,300,0.904,bilinear
-tf_efficientnet_b2,3.7733,96.2267,16.6133,83.3867,9.11,260,0.89,bicubic
-regnety_040,3.7467,96.2533,16.4,83.6,20.65,224,0.875,bicubic
-hrnet_w30,3.68,96.32,15.5733,84.4267,37.71,224,0.875,bilinear
-hrnet_w32,3.6533,96.3467,14.7867,85.2133,41.23,224,0.875,bilinear
-hrnet_w40,3.6533,96.3467,15.44,84.56,57.56,224,0.875,bilinear
-regnetx_120,3.6267,96.3733,15.9733,84.0267,46.11,224,0.875,bicubic
-seresnext26t_32x4d,3.6133,96.3867,15.8933,84.1067,16.82,224,0.875,bicubic
-tf_efficientnet_b1_ap,3.5467,96.4533,15.0667,84.9333,7.79,240,0.882,bicubic
-seresnext26tn_32x4d,3.5067,96.4933,15.76,84.24,16.81,224,0.875,bicubic
-resnest26d,3.4933,96.5067,15.6667,84.3333,17.07,224,0.875,bilinear
-dla169,3.4667,96.5333,15.3333,84.6667,53.99,224,0.875,bilinear
-gluon_resnext50_32x4d,3.4533,96.5467,16.12,83.88,25.03,224,0.875,bicubic
-mixnet_l,3.44,96.56,15.3067,84.6933,7.33,224,0.875,bicubic
-seresnext26d_32x4d,3.4,96.6,16.16,83.84,16.81,224,0.875,bicubic
-res2net50_26w_8s,3.3333,96.6667,14.04,85.96,48.4,224,0.875,bilinear
-resnetblur50,3.3333,96.6667,15.5867,84.4133,25.56,224,0.875,bicubic
-dla102x,3.3067,96.6933,15.12,84.88,26.77,224,0.875,bilinear
-gluon_resnet101_v1c,3.3067,96.6933,14.12,85.88,44.57,224,0.875,bicubic
-seresnet101,3.2533,96.7467,15.4533,84.5467,49.33,224,0.875,bilinear
-densenetblur121d,3.0667,96.9333,14.28,85.72,8.0,224,0.875,bicubic
-dla60_res2next,3.04,96.96,14.4533,85.5467,17.33,224,0.875,bilinear
-regnety_032,3.0267,96.9733,14.24,85.76,19.44,224,0.875,bicubic
-gluon_resnet50_v1d,3.0133,96.9867,14.6267,85.3733,25.58,224,0.875,bicubic
-wide_resnet101_2,2.96,97.04,13.9467,86.0533,126.89,224,0.875,bilinear
-efficientnet_b1_pruned,2.9333,97.0667,14.4133,85.5867,6.33,240,0.882,bicubic
-gluon_resnet50_v1s,2.92,97.08,13.12,86.88,25.68,224,0.875,bicubic
-tf_efficientnet_b1,2.8667,97.1333,13.5067,86.4933,7.79,240,0.882,bicubic
-res2net50_26w_6s,2.84,97.16,12.6,87.4,37.05,224,0.875,bilinear
-efficientnet_b0,2.8133,97.1867,13.9067,86.0933,5.29,224,0.875,bicubic
-tf_mixnet_l,2.8133,97.1867,13.04,86.96,7.33,224,0.875,bicubic
-regnetx_064,2.7867,97.2133,13.88,86.12,26.21,224,0.875,bicubic
-dpn68b,2.7067,97.2933,12.64,87.36,12.61,224,0.875,bicubic
-selecsls60b,2.6933,97.3067,13.1733,86.8267,32.77,224,0.875,bicubic
-tf_efficientnet_cc_b0_8e,2.68,97.32,12.7733,87.2267,24.01,224,0.875,bicubic
-dla60_res2net,2.64,97.36,14.2,85.8,21.15,224,0.875,bilinear
-gluon_resnet101_v1b,2.6267,97.3733,13.5733,86.4267,44.55,224,0.875,bicubic
-dla60x,2.6133,97.3867,13.3333,86.6667,17.65,224,0.875,bilinear
-mixnet_m,2.5467,97.4533,12.4267,87.5733,5.01,224,0.875,bicubic
-skresnet34,2.52,97.48,12.7733,87.2267,22.28,224,0.875,bicubic
-efficientnet_es,2.3733,97.6267,13.88,86.12,5.44,224,0.875,bicubic
-resnet152,2.36,97.64,12.2,87.8,60.19,224,0.875,bilinear
-regnetx_080,2.3467,97.6533,12.6933,87.3067,39.57,224,0.875,bicubic
-swsl_resnet18,2.3333,97.6667,11.2133,88.7867,11.69,224,0.875,bilinear
-wide_resnet50_2,2.32,97.68,11.8,88.2,68.88,224,0.875,bilinear
-seresnext26_32x4d,2.2933,97.7067,12.44,87.56,16.79,224,0.875,bicubic
-hrnet_w18,2.2667,97.7333,11.8533,88.1467,21.3,224,0.875,bilinear
-dla102,2.2533,97.7467,12.12,87.88,33.73,224,0.875,bilinear
-resnet50,2.2267,97.7733,11.3333,88.6667,25.56,224,0.875,bicubic
-regnety_016,2.1733,97.8267,11.44,88.56,11.2,224,0.875,bicubic
-regnetx_040,2.16,97.84,11.8,88.2,22.12,224,0.875,bicubic
-resnest14d,2.1467,97.8533,10.4,89.6,10.61,224,0.875,bilinear
-selecsls60,2.08,97.92,12.84,87.16,30.67,224,0.875,bicubic
-tf_efficientnet_cc_b0_4e,2.08,97.92,10.9733,89.0267,13.31,224,0.875,bicubic
-res2next50,2.0667,97.9333,11.4533,88.5467,24.67,224,0.875,bilinear
-seresnet50,2.0667,97.9333,12.2667,87.7333,28.09,224,0.875,bilinear
-densenet161,1.9733,98.0267,10.5867,89.4133,28.68,224,0.875,bicubic
-tf_efficientnet_b0_ap,1.96,98.04,10.8,89.2,5.29,224,0.875,bicubic
-regnetx_032,1.92,98.08,10.9467,89.0533,15.3,224,0.875,bicubic
-tf_efficientnet_em,1.8133,98.1867,11.6267,88.3733,6.9,240,0.882,bicubic
-tf_mixnet_m,1.8133,98.1867,10.5467,89.4533,5.01,224,0.875,bicubic
-tf_efficientnet_lite2,1.8,98.2,11.1467,88.8533,6.09,260,0.89,bicubic
-res2net50_14w_8s,1.7867,98.2133,10.3467,89.6533,25.06,224,0.875,bilinear
-res2net50_26w_4s,1.7733,98.2267,10.44,89.56,25.7,224,0.875,bilinear
-mobilenetv3_large_100,1.76,98.24,10.2933,89.7067,5.48,224,0.875,bicubic
-densenet121,1.7333,98.2667,10.8533,89.1467,7.98,224,0.875,bicubic
-tf_efficientnet_b0,1.6933,98.3067,9.7333,90.2667,5.29,224,0.875,bicubic
-tv_resnext50_32x4d,1.68,98.32,10.6,89.4,25.03,224,0.875,bilinear
-mobilenetv3_rw,1.6667,98.3333,10.7333,89.2667,5.48,224,0.875,bicubic
-resnet101,1.6667,98.3333,9.8133,90.1867,44.55,224,0.875,bilinear
-mobilenetv2_120d,1.64,98.36,10.4533,89.5467,5.83,224,0.875,bicubic
-mixnet_s,1.5867,98.4133,10.2533,89.7467,4.13,224,0.875,bicubic
-densenet201,1.5467,98.4533,9.6267,90.3733,20.01,224,0.875,bicubic
-gluon_resnet50_v1c,1.5467,98.4533,10.6133,89.3867,25.58,224,0.875,bicubic
-semnasnet_100,1.5467,98.4533,9.32,90.68,3.89,224,0.875,bicubic
-selecsls42b,1.4667,98.5333,10.44,89.56,32.46,224,0.875,bicubic
-tf_efficientnet_lite1,1.4533,98.5467,9.7067,90.2933,5.42,240,0.882,bicubic
-regnety_008,1.4267,98.5733,8.9467,91.0533,6.26,224,0.875,bicubic
-ssl_resnet18,1.3867,98.6133,8.16,91.84,11.69,224,0.875,bilinear
-dla60,1.3467,98.6533,9.4667,90.5333,22.33,224,0.875,bilinear
-dpn68,1.3467,98.6533,8.8133,91.1867,12.61,224,0.875,bicubic
-res2net50_48w_2s,1.3067,98.6933,8.92,91.08,25.29,224,0.875,bilinear
-tf_mixnet_s,1.28,98.72,8.7467,91.2533,4.13,224,0.875,bicubic
-mobilenetv2_140,1.2533,98.7467,9.1067,90.8933,6.11,224,0.875,bicubic
-fbnetc_100,1.2267,98.7733,8.7467,91.2533,5.57,224,0.875,bilinear
-resnet26d,1.2267,98.7733,9.28,90.72,16.01,224,0.875,bicubic
-densenet169,1.1867,98.8133,8.32,91.68,14.15,224,0.875,bicubic
-tf_mobilenetv3_large_100,1.1867,98.8133,7.9467,92.0533,5.48,224,0.875,bilinear
-gluon_resnet50_v1b,1.16,98.84,9.0267,90.9733,25.56,224,0.875,bicubic
-seresnet34,1.12,98.88,7.4,92.6,21.96,224,0.875,bilinear
-tf_efficientnet_es,1.12,98.88,8.6,91.4,5.44,224,0.875,bicubic
-spnasnet_100,1.1067,98.8933,8.2533,91.7467,4.42,224,0.875,bilinear
-tf_efficientnet_lite0,1.1067,98.8933,7.4933,92.5067,4.65,224,0.875,bicubic
-regnetx_016,1.0933,98.9067,8.6267,91.3733,9.19,224,0.875,bicubic
-dla34,1.08,98.92,7.6933,92.3067,15.78,224,0.875,bilinear
-regnety_006,1.0533,98.9467,8.4,91.6,6.06,224,0.875,bicubic
-regnety_004,1.0133,98.9867,7.3333,92.6667,4.34,224,0.875,bicubic
-resnet34,0.9867,99.0133,7.5333,92.4667,21.8,224,0.875,bilinear
-mobilenetv2_110d,0.9333,99.0667,8.1067,91.8933,4.52,224,0.875,bicubic
-gluon_resnet34_v1b,0.8933,99.1067,6.6,93.4,21.8,224,0.875,bicubic
-hrnet_w18_small_v2,0.8933,99.1067,7.3867,92.6133,15.6,224,0.875,bilinear
-regnetx_008,0.8933,99.1067,6.9067,93.0933,7.26,224,0.875,bicubic
-skresnet18,0.88,99.12,7.3867,92.6133,11.96,224,0.875,bicubic
-mnasnet_100,0.8667,99.1333,7.8667,92.1333,4.38,224,0.875,bicubic
-tf_mobilenetv3_large_075,0.8667,99.1333,6.72,93.28,3.99,224,0.875,bilinear
-regnetx_006,0.76,99.24,6.4933,93.5067,6.2,224,0.875,bicubic
-tf_mobilenetv3_small_100,0.7467,99.2533,4.6667,95.3333,2.54,224,0.875,bilinear
-seresnet18,0.72,99.28,6.0267,93.9733,11.78,224,0.875,bicubic
-regnetx_004,0.6933,99.3067,5.5067,94.4933,5.16,224,0.875,bicubic
-tv_densenet121,0.68,99.32,6.9067,93.0933,7.98,224,0.875,bicubic
-regnety_002,0.6667,99.3333,5.5333,94.4667,3.16,224,0.875,bicubic
-tf_mobilenetv3_small_075,0.6267,99.3733,4.1733,95.8267,2.04,224,0.875,bilinear
-resnet26,0.6,99.4,6.88,93.12,16.0,224,0.875,bicubic
-tv_resnet34,0.6,99.4,5.52,94.48,21.8,224,0.875,bilinear
-mobilenetv2_100,0.5333,99.4667,6.1867,93.8133,3.5,224,0.875,bicubic
-dla46_c,0.52,99.48,4.1867,95.8133,1.31,224,0.875,bilinear
-tf_mobilenetv3_large_minimal_100,0.48,99.52,4.88,95.12,3.92,224,0.875,bilinear
-dla60x_c,0.4667,99.5333,5.2133,94.7867,1.34,224,0.875,bilinear
-hrnet_w18_small,0.4533,99.5467,4.84,95.16,13.19,224,0.875,bilinear
-dla46x_c,0.4133,99.5867,4.44,95.56,1.08,224,0.875,bilinear
-gluon_resnet18_v1b,0.3867,99.6133,4.7867,95.2133,11.69,224,0.875,bicubic
-tf_mobilenetv3_small_minimal_100,0.36,99.64,2.8667,97.1333,2.04,224,0.875,bilinear
-resnet18,0.2933,99.7067,4.04,95.96,11.69,224,0.875,bilinear
-regnetx_002,0.2267,99.7733,3.9867,96.0133,2.68,224,0.875,bicubic
-tv_resnet50,0.0,100.0,2.8933,97.1067,25.56,224,0.875,bilinear
+model,rank_diff,top1,top1_diff,top1_err,top5,top5_diff,top5_err,param_count,img_size,cropt_pct,interpolation
+tf_efficientnet_l2_ns_475,+1,62.387,-25.847,37.613,87.107,-11.439,12.893,480.31,475,0.936,bicubic
+tf_efficientnet_l2_ns,-1,62.027,-26.325,37.973,87.960,-10.688,12.040,480.31,800,0.960,bicubic
+tf_efficientnet_b7_ns,=,45.720,-41.118,54.280,74.200,-23.894,25.800,66.35,600,0.949,bicubic
+ig_resnext101_32x48d,+2,41.573,-43.869,58.427,66.613,-30.959,33.387,828.41,224,0.875,bilinear
+tf_efficientnet_b6_ns,-1,40.427,-46.035,59.573,68.840,-29.044,31.160,43.04,528,0.942,bicubic
+ig_resnext101_32x32d,+5,39.413,-45.679,60.587,63.760,-33.676,36.240,468.53,224,0.875,bilinear
+tf_efficientnet_b5_ns,-2,39.013,-47.067,60.987,68.040,-29.714,31.960,30.39,456,0.934,bicubic
+ig_resnext101_32x16d,+9,36.053,-48.123,63.947,59.040,-38.156,40.960,194.03,224,0.875,bilinear
+swsl_resnext101_32x8d,+5,32.067,-52.227,67.933,59.400,-37.774,40.600,88.79,224,0.875,bilinear
+tf_efficientnet_b4_ns,-1,30.800,-54.358,69.200,59.440,-38.028,40.560,19.34,380,0.922,bicubic
+tf_efficientnet_b8_ap,-3,29.600,-55.768,70.400,56.933,-40.361,43.067,87.41,672,0.954,bicubic
+tf_efficientnet_b8,-5,29.373,-55.997,70.627,57.067,-40.325,42.933,87.41,672,0.954,bicubic
+ig_resnext101_32x8d,+16,28.707,-53.981,71.293,52.320,-44.312,47.680,88.79,224,0.875,bilinear
+swsl_resnext101_32x16d,+8,27.947,-55.391,72.053,52.320,-44.532,47.680,194.03,224,0.875,bilinear
+tf_efficientnet_b7_ap,-5,27.813,-57.305,72.187,54.773,-42.479,45.227,66.35,600,0.949,bicubic
+resnest269e,=,27.613,-56.573,72.387,53.107,-43.815,46.893,110.93,416,0.875,bilinear
+tresnet_xl_448,+8,26.880,-56.168,73.120,51.093,-45.081,48.907,78.44,448,0.875,bilinear
+resnest200e,+2,26.427,-57.407,73.573,51.933,-44.905,48.067,70.20,320,0.875,bilinear
+swsl_resnext101_32x4d,+5,25.347,-57.887,74.653,49.627,-47.129,50.373,44.18,224,0.875,bilinear
+tf_efficientnet_b7,-8,25.253,-59.679,74.747,51.667,-45.541,48.333,66.35,600,0.949,bicubic
+tresnet_l_448,+11,24.573,-57.695,75.427,48.600,-47.378,51.400,55.99,448,0.875,bilinear
+tf_efficientnet_b6_ap,-9,24.347,-60.439,75.653,50.427,-46.711,49.573,43.04,528,0.942,bicubic
+tf_efficientnet_b6,-5,20.373,-63.739,79.627,45.493,-51.391,54.507,43.04,528,0.942,bicubic
+tresnet_m_448,+15,19.680,-62.032,80.320,42.760,-52.810,57.240,31.39,448,0.875,bilinear
+tf_efficientnet_b5_ap,-10,19.467,-64.787,80.533,44.720,-52.256,55.280,30.39,456,0.934,bicubic
+tf_efficientnet_b3_ns,-7,19.413,-64.641,80.587,44.627,-52.285,55.373,12.23,300,0.904,bicubic
+swsl_resnext50_32x4d,+6,18.067,-64.113,81.933,41.867,-54.361,58.133,25.03,224,0.875,bilinear
+ssl_resnext101_32x16d,+9,17.213,-64.623,82.787,39.947,-56.147,60.053,194.03,224,0.875,bilinear
+tf_efficientnet_b5,-8,17.067,-66.749,82.933,41.907,-54.843,58.093,30.39,456,0.934,bicubic
+resnest101e,-3,16.493,-66.397,83.507,40.747,-55.577,59.253,48.28,256,0.875,bilinear
+swsl_resnet50,+17,15.987,-65.193,84.013,38.853,-57.133,61.147,25.56,224,0.875,bilinear
+ssl_resnext101_32x8d,+9,15.120,-66.506,84.880,37.720,-58.318,62.280,88.79,224,0.875,bilinear
+tf_efficientnet_b4_ap,-10,13.680,-69.568,86.320,35.920,-60.468,64.080,19.34,380,0.922,bicubic
+ecaresnet101d,=,13.307,-68.859,86.693,35.533,-60.519,64.467,44.57,224,0.875,bicubic
+tf_efficientnet_b4,-9,13.307,-69.709,86.693,35.520,-60.778,64.480,19.34,380,0.922,bicubic
+pnasnet5large,-8,13.080,-69.660,86.920,32.213,-63.827,67.787,86.06,331,0.875,bicubic
+nasnetalarge,-7,12.573,-69.985,87.427,33.413,-62.623,66.587,88.75,331,0.875,bicubic
+ssl_resnext101_32x4d,+15,12.120,-68.808,87.880,31.893,-63.835,68.107,44.18,224,0.875,bilinear
+tf_efficientnet_b2_ns,-8,11.787,-70.593,88.213,32.960,-63.292,67.040,9.11,260,0.890,bicubic
+gluon_senet154,+7,9.907,-71.317,90.093,26.453,-68.903,73.547,115.09,224,0.875,bicubic
+resnest50d_4s2x40d,+8,9.787,-71.327,90.213,29.147,-66.421,70.853,30.42,224,0.875,bicubic
+ssl_resnext50_32x4d,+30,9.667,-70.661,90.333,28.427,-66.977,71.573,25.03,224,0.875,bilinear
+senet154,+3,9.453,-71.851,90.547,26.440,-69.058,73.560,115.09,224,0.875,bilinear
+tresnet_xl,-9,9.307,-72.763,90.693,28.413,-67.515,71.587,78.44,224,0.875,bilinear
+efficientnet_b3a,-9,9.267,-72.607,90.733,28.427,-67.413,71.573,12.23,320,1.000,bicubic
+efficientnet_b3,-3,8.947,-72.551,91.053,28.213,-67.505,71.787,12.23,300,0.904,bicubic
+inception_v4,+32,8.920,-71.236,91.080,24.707,-70.267,75.293,42.68,299,0.875,bicubic
+gluon_seresnext101_64x4d,+7,8.867,-72.023,91.133,27.320,-67.984,72.680,88.23,224,0.875,bicubic
+tf_efficientnet_b1_ns,-4,8.613,-72.773,91.387,27.280,-68.458,72.720,7.79,240,0.882,bicubic
+resnest50d_1s4x24d,+1,8.520,-72.470,91.480,26.787,-68.535,73.213,25.68,224,0.875,bicubic
+ecaresnet50d,+10,8.507,-72.097,91.493,26.267,-69.055,73.733,25.58,224,0.875,bicubic
+gluon_xception65,+45,8.467,-71.137,91.533,25.133,-69.615,74.867,39.92,299,0.875,bicubic
+gluon_resnet152_v1d,+11,8.413,-72.057,91.587,23.453,-71.753,76.547,60.21,224,0.875,bicubic
+inception_resnet_v2,+11,8.160,-72.300,91.840,23.533,-71.777,76.467,55.84,299,0.897,bicubic
+tf_efficientnet_b3_ap,-17,8.133,-73.695,91.867,26.280,-69.344,73.720,12.23,300,0.904,bicubic
+gluon_seresnext101_32x4d,-2,8.040,-72.862,91.960,24.733,-70.561,75.267,48.96,224,0.875,bicubic
+tf_efficientnet_b3,-17,8.013,-73.627,91.987,25.467,-70.255,74.533,12.23,300,0.904,bicubic
+ens_adv_inception_resnet_v2,+25,7.987,-71.989,92.013,23.827,-71.119,76.173,55.84,299,0.897,bicubic
+tf_efficientnet_lite4,-17,7.933,-73.595,92.067,25.560,-70.108,74.440,13.01,380,0.920,bilinear
+tresnet_l,-16,7.880,-73.608,92.120,25.187,-70.441,74.813,55.99,224,0.875,bilinear
+gluon_resnet152_v1s,-11,7.867,-73.145,92.133,23.173,-72.243,76.827,60.32,224,0.875,bicubic
+resnest50d,-10,7.747,-73.211,92.253,25.293,-70.089,74.707,27.48,224,0.875,bilinear
+gluon_resnext101_64x4d,-1,7.707,-72.895,92.293,23.240,-71.754,76.760,83.46,224,0.875,bicubic
+skresnext50_32x4d,+16,7.080,-73.070,92.920,23.027,-71.617,76.973,27.48,224,0.875,bicubic
+ssl_resnet50,+45,7.000,-72.228,93.000,23.920,-70.912,76.080,25.56,224,0.875,bilinear
+regnety_320,-9,6.920,-73.894,93.080,23.040,-72.200,76.960,145.05,224,0.875,bicubic
+ecaresnet101d_pruned,-9,6.800,-74.008,93.200,24.200,-71.428,75.800,24.88,224,0.875,bicubic
+ecaresnetlight,-2,6.760,-73.694,93.240,22.560,-72.696,77.440,30.16,224,0.875,bicubic
+efficientnet_b2a,-9,6.760,-73.848,93.240,23.493,-71.817,76.507,9.11,288,1.000,bicubic
+seresnext101_32x4d,+7,6.413,-73.823,93.587,21.520,-73.508,78.480,48.96,224,0.875,bilinear
+efficientnet_b2,-2,6.093,-74.309,93.907,21.933,-73.143,78.067,9.11,260,0.875,bicubic
+gluon_resnext101_32x4d,-1,6.040,-74.294,93.960,21.133,-73.793,78.867,44.18,224,0.875,bicubic
+regnetx_320,+3,5.987,-74.259,94.013,19.880,-75.142,80.120,107.81,224,0.875,bicubic
+ese_vovnet39b,+29,5.973,-73.347,94.027,21.293,-73.417,78.707,24.57,224,0.875,bicubic
+gluon_resnet101_v1d,-7,5.920,-74.504,94.080,19.947,-75.073,80.053,44.57,224,0.875,bicubic
+gluon_seresnext50_32x4d,+10,5.787,-74.125,94.213,21.427,-73.391,78.573,27.56,224,0.875,bicubic
+efficientnet_b3_pruned,-21,5.733,-75.123,94.267,21.360,-73.880,78.640,9.86,300,0.904,bicubic
+regnety_160,-3,5.640,-74.660,94.360,19.347,-75.615,80.653,83.59,224,0.875,bicubic
+gluon_inception_v3,+47,5.507,-73.297,94.493,19.947,-74.433,80.053,23.83,299,0.875,bicubic
+mixnet_xl,-17,5.480,-74.998,94.520,21.093,-73.839,78.907,11.90,224,0.875,bicubic
+tresnet_m,-22,5.440,-75.356,94.560,19.960,-74.896,80.040,31.39,224,0.875,bilinear
+regnety_120,-12,5.413,-74.969,94.587,19.853,-75.275,80.147,51.82,224,0.875,bicubic
+gluon_resnet101_v1s,-9,5.280,-75.020,94.720,19.547,-75.603,80.453,44.67,224,0.875,bicubic
+hrnet_w64,+16,5.133,-74.339,94.867,19.453,-75.197,80.547,128.06,224,0.875,bilinear
+regnety_080,+2,5.000,-74.868,95.000,18.600,-76.232,81.400,39.18,224,0.875,bicubic
+efficientnet_b2_pruned,-2,4.947,-74.971,95.053,19.347,-75.501,80.653,8.31,260,0.890,bicubic
+dpn107,-9,4.880,-75.284,95.120,17.613,-77.299,82.387,86.92,224,0.875,bicubic
+gluon_resnet152_v1c,-3,4.867,-75.049,95.133,17.773,-77.069,82.227,60.21,224,0.875,bicubic
+adv_inception_v3,+76,4.747,-72.833,95.253,17.547,-76.177,82.453,23.83,299,0.875,bicubic
+dla102x2,+11,4.747,-74.705,95.253,18.960,-75.684,81.040,41.75,224,0.875,bilinear
+tf_inception_v3,+68,4.747,-73.109,95.253,17.747,-75.897,82.253,23.83,299,0.875,bicubic
+hrnet_w48,+13,4.720,-74.590,95.280,18.440,-76.078,81.560,77.47,224,0.875,bilinear
+dpn131,-4,4.640,-75.188,95.360,16.867,-77.837,83.133,79.25,224,0.875,bicubic
+gluon_resnet152_v1b,=,4.587,-75.105,95.413,16.533,-78.205,83.467,60.19,224,0.875,bicubic
+ecaresnet50d_pruned,-3,4.547,-75.171,95.453,18.547,-76.343,81.453,19.94,224,0.875,bicubic
+dpn92,-14,4.493,-75.523,95.507,18.200,-76.638,81.800,37.67,224,0.875,bicubic
+hrnet_w44,+25,4.493,-74.401,95.507,17.347,-77.023,82.653,67.06,224,0.875,bilinear
+regnetx_160,-10,4.373,-75.493,95.627,17.093,-77.735,82.907,54.28,224,0.875,bicubic
+resnext50d_32x4d,-4,4.347,-75.327,95.653,17.773,-77.095,82.227,25.05,224,0.875,bicubic
+xception,+18,4.347,-74.701,95.653,16.760,-77.632,83.240,22.86,299,0.897,bicubic
+seresnext50_32x4d,+14,4.280,-74.796,95.720,17.813,-76.621,82.187,27.56,224,0.875,bilinear
+resnext50_32x4d,-11,4.253,-75.509,95.747,18.387,-76.213,81.613,25.03,224,0.875,bicubic
+tf_efficientnet_cc_b1_8e,+4,4.240,-75.058,95.760,15.947,-78.417,84.053,39.72,240,0.882,bicubic
+regnety_064,-11,4.227,-75.485,95.773,17.187,-77.587,82.813,30.58,224,0.875,bicubic
+tf_efficientnet_el,-38,4.227,-76.221,95.773,18.173,-76.987,81.827,10.59,300,0.904,bicubic
+inception_v3,+64,4.187,-73.249,95.813,16.293,-77.183,83.707,23.83,299,0.875,bicubic
+tf_efficientnet_b2_ap,-34,4.173,-76.133,95.827,18.320,-76.708,81.680,9.11,260,0.890,bicubic
+seresnet152,+24,4.147,-74.511,95.853,15.893,-78.481,84.107,66.82,224,0.875,bilinear
+resnext101_32x8d,-5,4.133,-75.179,95.867,16.987,-77.539,83.013,88.79,224,0.875,bilinear
+tf_efficientnet_b0_ns,+23,4.133,-74.519,95.867,17.680,-76.688,82.320,5.29,224,0.875,bicubic
+dpn98,-15,4.080,-75.556,95.920,15.947,-78.647,84.053,61.57,224,0.875,bicubic
+res2net101_26w_4s,+2,4.000,-75.196,96.000,14.827,-79.613,85.173,45.21,224,0.875,bilinear
+efficientnet_b1,+17,3.973,-74.725,96.027,15.760,-78.392,84.240,7.79,240,0.875,bicubic
+tf_efficientnet_lite3,-24,3.933,-75.879,96.067,16.520,-78.394,83.480,8.20,300,0.904,bilinear
+tf_efficientnet_b2,-34,3.773,-76.317,96.227,16.613,-78.293,83.387,9.11,260,0.890,bicubic
+regnety_040,-5,3.747,-75.475,96.253,16.400,-78.256,83.600,20.65,224,0.875,bicubic
+hrnet_w30,+31,3.680,-74.516,96.320,15.573,-78.647,84.427,37.71,224,0.875,bilinear
+hrnet_w32,+23,3.653,-74.795,96.347,14.787,-79.401,85.213,41.23,224,0.875,bilinear
+hrnet_w40,+2,3.653,-75.281,96.347,15.440,-79.026,84.560,57.56,224,0.875,bilinear
+regnetx_120,-22,3.627,-75.963,96.373,15.973,-78.767,84.027,46.11,224,0.875,bicubic
+seresnext26t_32x4d,+34,3.613,-74.375,96.387,15.893,-77.813,84.107,16.82,224,0.875,bicubic
+tf_efficientnet_b1_ap,-13,3.547,-75.731,96.453,15.067,-79.241,84.933,7.79,240,0.882,bicubic
+seresnext26tn_32x4d,+31,3.507,-74.483,96.493,15.760,-77.988,84.240,16.81,224,0.875,bicubic
+resnest26d,+13,3.493,-74.989,96.507,15.667,-78.623,84.333,17.07,224,0.875,bilinear
+dla169,+4,3.467,-75.243,96.533,15.333,-79.005,84.667,53.99,224,0.875,bilinear
+gluon_resnext50_32x4d,-24,3.453,-75.903,96.547,16.120,-78.304,83.880,25.03,224,0.875,bicubic
+mixnet_l,-7,3.440,-75.536,96.560,15.307,-78.877,84.693,7.33,224,0.875,bicubic
+seresnext26d_32x4d,+36,3.400,-74.204,96.600,16.160,-77.452,83.840,16.81,224,0.875,bicubic
+res2net50_26w_8s,-17,3.333,-75.877,96.667,14.040,-80.322,85.960,48.40,224,0.875,bilinear
+resnetblur50,-22,3.333,-75.957,96.667,15.587,-79.045,84.413,25.56,224,0.875,bicubic
+dla102x,+4,3.307,-75.201,96.693,15.120,-79.114,84.880,26.77,224,0.875,bilinear
+gluon_resnet101_v1c,-33,3.307,-76.237,96.693,14.120,-80.466,85.880,44.57,224,0.875,bicubic
+seresnet101,+10,3.253,-75.143,96.747,15.453,-78.805,84.547,49.33,224,0.875,bilinear
+densenetblur121d,+55,3.067,-73.509,96.933,14.280,-78.910,85.720,8.00,224,0.875,bicubic
+dla60_res2next,+5,3.040,-75.408,96.960,14.453,-79.691,85.547,17.33,224,0.875,bilinear
+regnety_032,-13,3.027,-75.843,96.973,14.240,-80.162,85.760,19.44,224,0.875,bicubic
+gluon_resnet50_v1d,-21,3.013,-76.061,96.987,14.627,-79.849,85.373,25.58,224,0.875,bicubic
+wide_resnet101_2,-14,2.960,-75.886,97.040,13.947,-80.337,86.053,126.89,224,0.875,bilinear
+efficientnet_b1_pruned,+7,2.933,-75.309,97.067,14.413,-79.419,85.587,6.33,240,0.882,bicubic
+gluon_resnet50_v1s,-12,2.920,-75.792,97.080,13.120,-81.122,86.880,25.68,224,0.875,bicubic
+tf_efficientnet_b1,-16,2.867,-75.965,97.133,13.507,-80.689,86.493,7.79,240,0.882,bicubic
+res2net50_26w_6s,-8,2.840,-75.734,97.160,12.600,-81.526,87.400,37.05,224,0.875,bilinear
+efficientnet_b0,+18,2.813,-74.879,97.187,13.907,-79.625,86.093,5.29,224,0.875,bicubic
+tf_mixnet_l,-17,2.813,-75.957,97.187,13.040,-80.964,86.960,7.33,224,0.875,bicubic
+regnetx_064,-28,2.787,-76.279,97.213,13.880,-80.576,86.120,26.21,224,0.875,bicubic
+dpn68b,+21,2.707,-74.807,97.293,12.640,-81.182,87.360,12.61,224,0.875,bicubic
+selecsls60b,-5,2.693,-75.725,97.307,13.173,-80.993,86.827,32.77,224,0.875,bicubic
+tf_efficientnet_cc_b0_8e,+10,2.680,-75.228,97.320,12.773,-80.883,87.227,24.01,224,0.875,bicubic
+dla60_res2net,-11,2.640,-75.832,97.360,14.200,-80.004,85.800,21.15,224,0.875,bilinear
+gluon_resnet101_v1b,-44,2.627,-76.677,97.373,13.573,-80.951,86.427,44.55,224,0.875,bicubic
+dla60x,-6,2.613,-75.629,97.387,13.333,-80.689,86.667,17.65,224,0.875,bilinear
+mixnet_m,+25,2.547,-74.709,97.453,12.427,-80.991,87.573,5.01,224,0.875,bicubic
+skresnet34,+31,2.520,-74.390,97.480,12.773,-80.543,87.227,22.28,224,0.875,bicubic
+efficientnet_es,-3,2.373,-75.681,97.627,13.880,-80.050,86.120,5.44,224,0.875,bicubic
+resnet152,-11,2.360,-75.952,97.640,12.200,-81.846,87.800,60.19,224,0.875,bilinear
+regnetx_080,-43,2.347,-76.851,97.653,12.693,-81.865,87.307,39.57,224,0.875,bicubic
+swsl_resnet18,+64,2.333,-70.953,97.667,11.213,-80.519,88.787,11.69,224,0.875,bilinear
+wide_resnet50_2,-19,2.320,-76.148,97.680,11.800,-82.286,88.200,68.88,224,0.875,bilinear
+seresnext26_32x4d,+20,2.293,-74.807,97.707,12.440,-80.870,87.560,16.79,224,0.875,bicubic
+hrnet_w18,+26,2.267,-74.489,97.733,11.853,-81.589,88.147,21.30,224,0.875,bilinear
+dla102,-9,2.253,-75.773,97.747,12.120,-81.830,87.880,33.73,224,0.875,bilinear
+resnet50,-43,2.227,-76.805,97.773,11.333,-83.051,88.667,25.56,224,0.875,bicubic
+regnety_016,-3,2.173,-75.679,97.827,11.440,-82.276,88.560,11.20,224,0.875,bicubic
+regnetx_040,-28,2.160,-76.326,97.840,11.800,-82.442,88.200,22.12,224,0.875,bicubic
+resnest14d,+36,2.147,-73.357,97.853,10.400,-82.114,89.600,10.61,224,0.875,bilinear
+selecsls60,-10,2.080,-75.902,97.920,12.840,-80.992,87.160,30.67,224,0.875,bicubic
+tf_efficientnet_cc_b0_4e,+6,2.080,-75.224,97.920,10.973,-82.359,89.027,13.31,224,0.875,bicubic
+res2next50,-21,2.067,-76.175,97.933,11.453,-82.439,88.547,24.67,224,0.875,bilinear
+seresnet50,-7,2.067,-75.569,97.933,12.267,-81.485,87.733,28.09,224,0.875,bilinear
+densenet161,+2,1.973,-75.375,98.027,10.587,-83.061,89.413,28.68,224,0.875,bicubic
+tf_efficientnet_b0_ap,+9,1.960,-75.124,98.040,10.800,-82.454,89.200,5.29,224,0.875,bicubic
+regnetx_032,-23,1.920,-76.246,98.080,10.947,-83.133,89.053,15.30,224,0.875,bicubic
+tf_efficientnet_em,-42,1.813,-76.885,98.187,11.627,-82.693,88.373,6.90,240,0.882,bicubic
+tf_mixnet_m,+8,1.813,-75.137,98.187,10.547,-82.609,89.453,5.01,224,0.875,bicubic
+tf_efficientnet_lite2,-6,1.800,-75.660,98.200,11.147,-82.599,88.853,6.09,260,0.890,bicubic
+res2net50_14w_8s,-26,1.787,-76.365,98.213,10.347,-83.495,89.653,25.06,224,0.875,bilinear
+res2net50_26w_4s,-20,1.773,-76.173,98.227,10.440,-83.412,89.560,25.70,224,0.875,bilinear
+mobilenetv3_large_100,+18,1.760,-74.008,98.240,10.293,-82.247,89.707,5.48,224,0.875,bicubic
+densenet121,+20,1.733,-73.841,98.267,10.853,-81.803,89.147,7.98,224,0.875,bicubic
+tf_efficientnet_b0,+5,1.693,-75.147,98.307,9.733,-83.493,90.267,5.29,224,0.875,bicubic
+tv_resnext50_32x4d,-18,1.680,-75.938,98.320,10.600,-83.098,89.400,25.03,224,0.875,bilinear
+mobilenetv3_rw,+16,1.667,-73.961,98.333,10.733,-81.977,89.267,5.48,224,0.875,bicubic
+resnet101,-12,1.667,-75.707,98.333,9.813,-83.733,90.187,44.55,224,0.875,bilinear
+mobilenetv2_120d,-10,1.640,-75.654,98.360,10.453,-83.049,89.547,5.83,224,0.875,bicubic
+mixnet_s,+9,1.587,-74.401,98.413,10.253,-82.541,89.747,4.13,224,0.875,bicubic
+densenet201,-11,1.547,-75.743,98.453,9.627,-83.851,90.373,20.01,224,0.875,bicubic
+gluon_resnet50_v1c,-34,1.547,-76.463,98.453,10.613,-83.375,89.387,25.58,224,0.875,bicubic
+semnasnet_100,+14,1.547,-73.909,98.453,9.320,-83.272,90.680,3.89,224,0.875,bicubic
+selecsls42b,-11,1.467,-75.709,98.533,10.440,-82.952,89.560,32.46,224,0.875,bicubic
+tf_efficientnet_lite1,-2,1.453,-75.185,98.547,9.707,-83.525,90.293,5.42,240,0.882,bicubic
+regnety_008,=,1.427,-74.887,98.573,8.947,-84.115,91.053,6.26,224,0.875,bicubic
+ssl_resnet18,+32,1.387,-71.213,98.613,8.160,-83.256,91.840,11.69,224,0.875,bilinear
+dla60,-12,1.347,-75.677,98.653,9.467,-83.841,90.533,22.33,224,0.875,bilinear
+dpn68,-2,1.347,-74.959,98.653,8.813,-84.157,91.187,12.61,224,0.875,bicubic
+res2net50_48w_2s,-27,1.307,-76.207,98.693,8.920,-84.628,91.080,25.29,224,0.875,bilinear
+tf_mixnet_s,+1,1.280,-74.368,98.720,8.747,-83.889,91.253,4.13,224,0.875,bicubic
+mobilenetv2_140,-7,1.253,-75.271,98.747,9.107,-83.883,90.893,6.11,224,0.875,bicubic
+fbnetc_100,+8,1.227,-73.893,98.773,8.747,-83.639,91.253,5.57,224,0.875,bilinear
+resnet26d,-12,1.227,-75.453,98.773,9.280,-83.886,90.720,16.01,224,0.875,bicubic
+densenet169,-5,1.187,-74.725,98.813,8.320,-84.704,91.680,14.15,224,0.875,bicubic
+tf_mobilenetv3_large_100,-1,1.187,-74.329,98.813,7.947,-84.653,92.053,5.48,224,0.875,bilinear
+gluon_resnet50_v1b,-36,1.160,-76.418,98.840,9.027,-84.691,90.973,25.56,224,0.875,bicubic
+seresnet34,+8,1.120,-73.688,98.880,7.400,-84.726,92.600,21.96,224,0.875,bilinear
+tf_efficientnet_es,-28,1.120,-76.144,98.880,8.600,-85.000,91.400,5.44,224,0.875,bicubic
+spnasnet_100,+11,1.107,-72.973,98.893,8.253,-83.579,91.747,4.42,224,0.875,bilinear
+tf_efficientnet_lite0,+4,1.107,-73.735,98.893,7.493,-84.677,92.507,4.65,224,0.875,bicubic
+regnetx_016,-24,1.093,-75.837,98.907,8.627,-84.791,91.373,9.19,224,0.875,bicubic
+dla34,+6,1.080,-73.556,98.920,7.693,-84.371,92.307,15.78,224,0.875,bilinear
+regnety_006,-5,1.053,-74.207,98.947,8.400,-84.128,91.600,6.06,224,0.875,bicubic
+regnety_004,+7,1.013,-73.013,98.987,7.333,-84.415,92.667,4.34,224,0.875,bicubic
+resnet34,-4,0.987,-74.125,99.013,7.533,-84.755,92.467,21.80,224,0.875,bilinear
+mobilenetv2_110d,-4,0.933,-74.119,99.067,8.107,-84.073,91.893,4.52,224,0.875,bicubic
+gluon_resnet34_v1b,+2,0.893,-73.687,99.107,6.600,-85.388,93.400,21.80,224,0.875,bicubic
+hrnet_w18_small_v2,-9,0.893,-74.233,99.107,7.387,-85.029,92.613,15.60,224,0.875,bilinear
+regnetx_008,-6,0.893,-74.129,99.107,6.907,-85.437,93.093,7.26,224,0.875,bicubic
+skresnet18,+6,0.880,-72.164,99.120,7.387,-83.791,92.613,11.96,224,0.875,bicubic
+mnasnet_100,-4,0.867,-73.789,99.133,7.867,-84.259,92.133,4.38,224,0.875,bicubic
+tf_mobilenetv3_large_075,+1,0.867,-72.575,99.133,6.720,-84.632,93.280,3.99,224,0.875,bilinear
+regnetx_006,-1,0.760,-73.102,99.240,6.493,-85.187,93.507,6.20,224,0.875,bicubic
+tf_mobilenetv3_small_100,+13,0.747,-67.171,99.253,4.667,-82.995,95.333,2.54,224,0.875,bilinear
+seresnet18,+7,0.720,-71.038,99.280,6.027,-84.307,93.973,11.78,224,0.875,bicubic
+regnetx_004,+3,0.693,-71.713,99.307,5.507,-85.323,94.493,5.16,224,0.875,bicubic
+tv_densenet121,-11,0.680,-74.072,99.320,6.907,-85.245,93.093,7.98,224,0.875,bicubic
+regnety_002,+6,0.667,-69.615,99.333,5.533,-84.007,94.467,3.16,224,0.875,bicubic
+tf_mobilenetv3_small_075,+11,0.627,-65.091,99.373,4.173,-81.963,95.827,2.04,224,0.875,bilinear
+resnet26,-23,0.600,-74.692,99.400,6.880,-85.690,93.120,16.00,224,0.875,bicubic
+tv_resnet34,-7,0.600,-72.714,99.400,5.520,-85.900,94.480,21.80,224,0.875,bilinear
+mobilenetv2_100,-5,0.533,-72.445,99.467,6.187,-84.829,93.813,3.50,224,0.875,bicubic
+dla46_c,+8,0.520,-64.358,99.480,4.187,-82.099,95.813,1.31,224,0.875,bilinear
+tf_mobilenetv3_large_minimal_100,-3,0.480,-71.764,99.520,4.880,-85.756,95.120,3.92,224,0.875,bilinear
+dla60x_c,+3,0.467,-67.441,99.533,5.213,-83.221,94.787,1.34,224,0.875,bilinear
+hrnet_w18_small,-6,0.453,-71.889,99.547,4.840,-85.832,95.160,13.19,224,0.875,bilinear
+dla46x_c,+2,0.413,-65.567,99.587,4.440,-82.540,95.560,1.08,224,0.875,bilinear
+gluon_resnet18_v1b,-5,0.387,-70.443,99.613,4.787,-84.969,95.213,11.69,224,0.875,bicubic
+tf_mobilenetv3_small_minimal_100,+3,0.360,-62.538,99.640,2.867,-81.363,97.133,2.04,224,0.875,bilinear
+resnet18,-5,0.293,-69.465,99.707,4.040,-85.038,95.960,11.69,224,0.875,bilinear
+regnetx_002,-5,0.227,-68.527,99.773,3.987,-84.561,96.013,2.68,224,0.875,bicubic
+tv_resnet50,-45,0.000,-76.130,100.000,2.893,-89.969,97.107,25.56,224,0.875,bilinear
--- a/results/results-imagenetv2-matched-frequency.csv
+++ b/results/results-imagenetv2-matched-frequency.csv
@ -1,215 +1,215 @@
-model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation
-tf_efficientnet_l2_ns_475,80.47,19.53,95.73,4.27,480.31,475,0.936,bicubic
-tf_efficientnet_l2_ns,80.25,19.75,95.85,4.15,480.31,800,0.96,bicubic
-tf_efficientnet_b7_ns,78.52,21.48,94.37,5.63,66.35,600,0.949,bicubic
-tf_efficientnet_b6_ns,77.28,22.72,93.89,6.11,43.04,528,0.942,bicubic
-ig_resnext101_32x48d,76.87,23.13,93.32,6.68,828.41,224,0.875,bilinear
-ig_resnext101_32x32d,76.84,23.16,93.19,6.81,468.53,224,0.875,bilinear
-tf_efficientnet_b5_ns,76.82,23.18,93.58,6.42,30.39,456,0.934,bicubic
-tf_efficientnet_b7_ap,76.09,23.91,92.97,7.03,66.35,600,0.949,bicubic
-tf_efficientnet_b8_ap,76.09,23.91,92.73,7.27,87.41,672,0.954,bicubic
-ig_resnext101_32x16d,75.71,24.29,92.9,7.1,194.03,224,0.875,bilinear
-tf_efficientnet_b4_ns,75.69,24.31,93.04,6.96,19.34,380,0.922,bicubic
-swsl_resnext101_32x8d,75.45,24.55,92.75,7.25,88.79,224,0.875,bilinear
-tf_efficientnet_b6_ap,75.38,24.62,92.44,7.56,43.04,528,0.942,bicubic
-tf_efficientnet_b8,74.93,25.07,92.32,7.68,87.41,672,0.954,bicubic
-tf_efficientnet_b7,74.72,25.28,92.22,7.78,66.35,600,0.949,bicubic
-tf_efficientnet_b5_ap,74.59,25.41,91.99,8.01,30.39,456,0.934,bicubic
-swsl_resnext101_32x4d,74.15,25.85,91.99,8.01,44.18,224,0.875,bilinear
-swsl_resnext101_32x16d,74.01,25.99,92.17,7.83,194.03,224,0.875,bilinear
-resnest200e,73.93,26.07,91.58,8.42,70.2,320,0.875,bilinear
-tf_efficientnet_b6,73.9,26.1,91.75,8.25,43.04,528,0.942,bicubic
-tf_efficientnet_b3_ns,73.87,26.13,91.86,8.14,12.23,300,0.904,bicubic
-ig_resnext101_32x8d,73.66,26.34,92.15,7.85,88.79,224,0.875,bilinear
-tf_efficientnet_b5,73.54,26.46,91.46,8.54,30.39,456,0.934,bicubic
-resnest269e,73.46,26.54,91.68,8.32,110.93,416,0.875,bilinear
-tf_efficientnet_b4_ap,72.89,27.11,90.98,9.02,19.34,380,0.922,bicubic
-swsl_resnext50_32x4d,72.58,27.42,90.84,9.16,25.03,224,0.875,bilinear
-resnest101e,72.55,27.45,90.81,9.19,48.28,256,0.875,bilinear
-tresnet_xl_448,72.55,27.45,90.31,9.69,78.44,448,0.875,bilinear
-pnasnet5large,72.37,27.63,90.26,9.74,86.06,331,0.875,bicubic
-nasnetalarge,72.31,27.69,90.51,9.49,88.75,331,0.875,bicubic
-tf_efficientnet_b4,72.28,27.72,90.6,9.4,19.34,380,0.922,bicubic
-tf_efficientnet_b2_ns,72.27,27.73,91.09,8.91,9.11,260,0.89,bicubic
-swsl_resnet50,71.69,28.31,90.51,9.49,25.56,224,0.875,bilinear
-tresnet_xl,71.65,28.35,89.63,10.37,78.44,224,0.875,bilinear
-tresnet_l_448,71.6,28.4,90.06,9.94,55.99,448,0.875,bilinear
-ecaresnet101d,71.5,28.5,90.31,9.69,44.57,224,0.875,bicubic
-ssl_resnext101_32x8d,71.49,28.51,90.47,9.53,88.79,224,0.875,bilinear
-ssl_resnext101_32x16d,71.4,28.6,90.55,9.45,194.03,224,0.875,bilinear
-tresnet_m_448,71.0,29.0,88.68,11.32,31.39,448,0.875,bilinear
-resnest50d_4s2x40d,70.94,29.06,89.71,10.29,30.42,224,0.875,bicubic
-tf_efficientnet_b3_ap,70.92,29.08,89.43,10.57,12.23,300,0.904,bicubic
-efficientnet_b3a,70.87,29.13,89.72,10.28,12.23,320,1.0,bicubic
-tf_efficientnet_b1_ns,70.85,29.15,90.11,9.89,7.79,240,0.882,bicubic
-tresnet_l,70.83,29.17,89.61,10.39,55.99,224,0.875,bilinear
-efficientnet_b3,70.76,29.24,89.84,10.16,12.23,300,0.904,bicubic
-tf_efficientnet_b3,70.62,29.38,89.44,10.56,12.23,300,0.904,bicubic
-gluon_senet154,70.6,29.4,88.92,11.08,115.09,224,0.875,bicubic
-ssl_resnext101_32x4d,70.5,29.5,89.76,10.24,44.18,224,0.875,bilinear
-senet154,70.48,29.52,88.99,11.01,115.09,224,0.875,bilinear
-gluon_seresnext101_64x4d,70.44,29.56,89.35,10.65,88.23,224,0.875,bicubic
-resnest50d_1s4x24d,70.43,29.57,89.24,10.76,25.68,224,0.875,bicubic
-tf_efficientnet_lite4,70.43,29.57,89.12,10.88,13.01,380,0.92,bilinear
-resnest50d,70.42,29.58,88.76,11.24,27.48,224,0.875,bilinear
-gluon_resnet152_v1s,70.32,29.68,88.87,11.13,60.32,224,0.875,bicubic
-ecaresnet101d_pruned,70.12,29.88,89.58,10.42,24.88,224,0.875,bicubic
-inception_resnet_v2,70.12,29.88,88.68,11.32,55.84,299,0.8975,bicubic
-gluon_seresnext101_32x4d,70.01,29.99,88.91,11.09,48.96,224,0.875,bicubic
-gluon_resnet152_v1d,69.95,30.05,88.47,11.53,60.21,224,0.875,bicubic
-ecaresnet50d,69.83,30.17,89.37,10.63,25.58,224,0.875,bicubic
-gluon_resnext101_64x4d,69.69,30.31,88.26,11.74,83.46,224,0.875,bicubic
-ssl_resnext50_32x4d,69.69,30.31,89.42,10.58,25.03,224,0.875,bilinear
-tresnet_m,69.65,30.35,88.0,12.0,31.39,224,0.875,bilinear
-efficientnet_b3_pruned,69.58,30.42,88.97,11.03,9.86,300,0.904,bicubic
-ens_adv_inception_resnet_v2,69.52,30.48,88.5,11.5,55.84,299,0.8975,bicubic
-efficientnet_b2a,69.49,30.51,88.68,11.32,9.11,288,1.0,bicubic
-inception_v4,69.35,30.65,88.78,11.22,42.68,299,0.875,bicubic
-seresnext101_32x4d,69.34,30.66,88.05,11.95,48.96,224,0.875,bilinear
-ecaresnetlight,69.33,30.67,89.22,10.78,30.16,224,0.875,bicubic
-gluon_resnet152_v1c,69.13,30.87,87.89,12.11,60.21,224,0.875,bicubic
-mixnet_xl,69.08,30.92,88.31,11.69,11.9,224,0.875,bicubic
-efficientnet_b2,69.0,31.0,88.62,11.38,9.11,260,0.875,bicubic
-gluon_resnet101_v1d,68.99,31.01,88.08,11.92,44.57,224,0.875,bicubic
-gluon_xception65,68.98,31.02,88.32,11.68,39.92,299,0.875,bicubic
-gluon_resnext101_32x4d,68.96,31.04,88.34,11.66,44.18,224,0.875,bicubic
-tf_efficientnet_b2_ap,68.93,31.07,88.34,11.66,9.11,260,0.89,bicubic
-gluon_resnet152_v1b,68.81,31.19,87.71,12.29,60.19,224,0.875,bicubic
-dpn131,68.76,31.24,87.48,12.52,79.25,224,0.875,bicubic
-resnext50d_32x4d,68.75,31.25,88.31,11.69,25.05,224,0.875,bicubic
-tf_efficientnet_b2,68.75,31.25,87.95,12.05,9.11,260,0.89,bicubic
-gluon_resnet101_v1s,68.72,31.28,87.9,12.1,44.67,224,0.875,bicubic
-dpn107,68.71,31.29,88.13,11.87,86.92,224,0.875,bicubic
-gluon_seresnext50_32x4d,68.67,31.33,88.32,11.68,27.56,224,0.875,bicubic
-hrnet_w64,68.63,31.37,88.07,11.93,128.06,224,0.875,bilinear
-resnext50_32x4d,68.61,31.39,87.57,12.43,25.03,224,0.875,bicubic
-dpn98,68.58,31.42,87.66,12.34,61.57,224,0.875,bicubic
-ssl_resnet50,68.42,31.58,88.58,11.42,25.56,224,0.875,bilinear
-ecaresnet50d_pruned,68.39,31.61,88.37,11.63,19.94,224,0.875,bicubic
-skresnext50_32x4d,68.39,31.61,87.59,12.41,27.48,224,0.875,bicubic
-dla102x2,68.34,31.66,87.87,12.13,41.75,224,0.875,bilinear
-efficientnet_b2_pruned,68.3,31.7,88.1,11.9,8.31,260,0.89,bicubic
-gluon_resnext50_32x4d,68.28,31.72,87.32,12.68,25.03,224,0.875,bicubic
-tf_efficientnet_lite3,68.23,31.77,87.72,12.28,8.2,300,0.904,bilinear
-ese_vovnet39b,68.19,31.81,88.26,11.74,24.57,224,0.875,bicubic
-tf_efficientnet_el,68.18,31.82,88.35,11.65,10.59,300,0.904,bicubic
-dpn92,68.01,31.99,87.59,12.41,37.67,224,0.875,bicubic
-gluon_resnet50_v1d,67.91,32.09,87.12,12.88,25.58,224,0.875,bicubic
-seresnext50_32x4d,67.87,32.13,87.62,12.38,27.56,224,0.875,bilinear
-resnext101_32x8d,67.85,32.15,87.48,12.52,88.79,224,0.875,bilinear
-hrnet_w44,67.77,32.23,87.53,12.47,67.06,224,0.875,bilinear
-hrnet_w48,67.77,32.23,87.42,12.58,77.47,224,0.875,bilinear
-tf_efficientnet_b0_ns,67.72,32.28,88.08,11.92,5.29,224,0.875,bicubic
-xception,67.67,32.33,87.57,12.43,22.86,299,0.8975,bicubic
-dla169,67.61,32.39,87.56,12.44,53.99,224,0.875,bilinear
-gluon_inception_v3,67.59,32.41,87.46,12.54,23.83,299,0.875,bicubic
-hrnet_w40,67.59,32.41,87.13,12.87,57.56,224,0.875,bilinear
-gluon_resnet101_v1c,67.56,32.44,87.16,12.84,44.57,224,0.875,bicubic
-seresnet152,67.55,32.45,87.39,12.61,66.82,224,0.875,bilinear
-res2net50_26w_8s,67.53,32.47,87.27,12.73,48.4,224,0.875,bilinear
-tf_efficientnet_b1_ap,67.52,32.48,87.77,12.23,7.79,240,0.882,bicubic
-tf_efficientnet_cc_b1_8e,67.48,32.52,87.31,12.69,39.72,240,0.882,bicubic
-gluon_resnet101_v1b,67.45,32.55,87.23,12.77,44.55,224,0.875,bicubic
-res2net101_26w_4s,67.45,32.55,87.01,12.99,45.21,224,0.875,bilinear
-resnet50,67.44,32.56,87.42,12.58,25.56,224,0.875,bicubic
-resnetblur50,67.44,32.56,87.43,12.57,25.56,224,0.875,bicubic
-resnest26d,67.21,32.79,87.18,12.82,17.07,224,0.875,bilinear
-efficientnet_b1,67.16,32.84,87.15,12.85,7.79,240,0.875,bicubic
-seresnet101,67.15,32.85,87.05,12.95,49.33,224,0.875,bilinear
-gluon_resnet50_v1s,67.1,32.9,86.86,13.14,25.68,224,0.875,bicubic
-dla60x,67.08,32.92,87.17,12.83,17.65,224,0.875,bilinear
-dla60_res2net,67.03,32.97,87.14,12.86,21.15,224,0.875,bilinear
-resnet152,67.02,32.98,87.57,12.43,60.19,224,0.875,bilinear
-dla102x,67.0,33.0,86.77,13.23,26.77,224,0.875,bilinear
-mixnet_l,66.97,33.03,86.94,13.06,7.33,224,0.875,bicubic
-res2net50_26w_6s,66.91,33.09,86.9,13.1,37.05,224,0.875,bilinear
-efficientnet_es,66.89,33.11,86.73,13.27,5.44,224,0.875,bicubic
-tf_efficientnet_b1,66.89,33.11,87.04,12.96,7.79,240,0.882,bicubic
-tf_efficientnet_em,66.87,33.13,86.98,13.02,6.9,240,0.882,bicubic
-hrnet_w32,66.79,33.21,87.29,12.71,41.23,224,0.875,bilinear
-tf_mixnet_l,66.78,33.22,86.46,13.54,7.33,224,0.875,bicubic
-hrnet_w30,66.76,33.24,86.79,13.21,37.71,224,0.875,bilinear
-selecsls60b,66.72,33.28,86.54,13.46,32.77,224,0.875,bicubic
-wide_resnet101_2,66.68,33.32,87.04,12.96,126.89,224,0.875,bilinear
-wide_resnet50_2,66.65,33.35,86.81,13.19,68.88,224,0.875,bilinear
-dla60_res2next,66.64,33.36,87.02,12.98,17.33,224,0.875,bilinear
-adv_inception_v3,66.6,33.4,86.56,13.44,23.83,299,0.875,bicubic
-dla102,66.55,33.45,86.91,13.09,33.73,224,0.875,bilinear
-gluon_resnet50_v1c,66.54,33.46,86.16,13.84,25.58,224,0.875,bicubic
-tf_inception_v3,66.42,33.58,86.68,13.32,23.83,299,0.875,bicubic
-efficientnet_b0,66.25,33.75,85.95,14.05,5.29,224,0.875,bicubic
-seresnet50,66.24,33.76,86.33,13.67,28.09,224,0.875,bilinear
-selecsls60,66.22,33.78,86.33,13.67,30.67,224,0.875,bicubic
-tf_efficientnet_cc_b0_8e,66.21,33.79,86.22,13.78,24.01,224,0.875,bicubic
-tv_resnext50_32x4d,66.18,33.82,86.04,13.96,25.03,224,0.875,bilinear
-res2net50_26w_4s,66.17,33.83,86.6,13.4,25.7,224,0.875,bilinear
-inception_v3,66.12,33.88,86.34,13.66,23.83,299,0.875,bicubic
-efficientnet_b1_pruned,66.08,33.92,86.58,13.42,6.33,240,0.882,bicubic
-gluon_resnet50_v1b,66.04,33.96,86.27,13.73,25.56,224,0.875,bicubic
-res2net50_14w_8s,66.02,33.98,86.24,13.76,25.06,224,0.875,bilinear
-densenet161,65.85,34.15,86.46,13.54,28.68,224,0.875,bicubic
-res2next50,65.85,34.15,85.83,14.17,24.67,224,0.875,bilinear
-seresnext26tn_32x4d,65.85,34.15,85.68,14.32,16.81,224,0.875,bicubic
-skresnet34,65.77,34.23,85.96,14.04,22.28,224,0.875,bicubic
-resnet101,65.68,34.32,85.98,14.02,44.55,224,0.875,bilinear
-dpn68b,65.6,34.4,85.94,14.06,12.61,224,0.875,bicubic
-seresnext26t_32x4d,65.6,34.4,86.09,13.91,16.82,224,0.875,bicubic
-selecsls42b,65.59,34.41,85.83,14.17,32.46,224,0.875,bicubic
-tf_efficientnet_b0_ap,65.49,34.51,85.55,14.45,5.29,224,0.875,bicubic
-seresnext26d_32x4d,65.42,34.58,85.97,14.03,16.81,224,0.875,bicubic
-tf_efficientnet_lite2,65.39,34.61,86.03,13.97,6.09,260,0.89,bicubic
-res2net50_48w_2s,65.32,34.68,85.96,14.04,25.29,224,0.875,bilinear
-densenetblur121d,65.3,34.7,85.71,14.29,8.0,224,0.875,bicubic
-densenet201,65.28,34.72,85.67,14.33,20.01,224,0.875,bicubic
-tf_efficientnet_es,65.24,34.76,85.54,14.46,5.44,224,0.875,bicubic
-dla60,65.22,34.78,85.75,14.25,22.33,224,0.875,bilinear
-tf_efficientnet_cc_b0_4e,65.13,34.87,85.13,14.87,13.31,224,0.875,bicubic
-mobilenetv2_120d,65.04,34.96,85.99,14.01,5.83,224,0.875,bicubic
-seresnext26_32x4d,65.04,34.96,85.65,14.35,16.79,224,0.875,bicubic
-hrnet_w18,64.91,35.09,85.75,14.25,21.3,224,0.875,bilinear
-densenet169,64.78,35.22,85.25,14.75,14.15,224,0.875,bicubic
-mixnet_m,64.69,35.31,85.47,14.53,5.01,224,0.875,bicubic
-resnet26d,64.63,35.37,85.12,14.88,16.01,224,0.875,bicubic
-tf_efficientnet_lite1,64.37,35.63,85.49,14.51,5.42,240,0.882,bicubic
-tf_efficientnet_b0,64.29,35.71,85.25,14.75,5.29,224,0.875,bicubic
-tf_mixnet_m,64.27,35.73,85.09,14.91,5.01,224,0.875,bicubic
-dpn68,64.22,35.78,85.18,14.82,12.61,224,0.875,bicubic
-mobilenetv2_140,64.05,35.95,85.02,14.98,6.11,224,0.875,bicubic
-densenet121,63.74,36.26,84.63,15.37,7.98,224,0.875,bicubic
-resnest14d,63.6,36.4,84.22,15.78,10.61,224,0.875,bilinear
-tf_mixnet_s,63.59,36.41,84.27,15.73,4.13,224,0.875,bicubic
-resnet26,63.45,36.55,84.27,15.73,16.0,224,0.875,bicubic
-mixnet_s,63.38,36.62,84.71,15.29,4.13,224,0.875,bicubic
-mobilenetv3_large_100,63.36,36.64,84.08,15.92,5.48,224,0.875,bicubic
-tv_resnet50,63.33,36.67,84.65,15.35,25.56,224,0.875,bilinear
-mobilenetv3_rw,63.23,36.77,84.52,15.48,5.48,224,0.875,bicubic
-semnasnet_100,63.12,36.88,84.53,15.47,3.89,224,0.875,bicubic
-tv_densenet121,62.94,37.06,84.26,15.74,7.98,224,0.875,bicubic
-seresnet34,62.89,37.11,84.22,15.78,21.96,224,0.875,bilinear
-hrnet_w18_small_v2,62.83,37.17,83.97,16.03,15.6,224,0.875,bilinear
-mobilenetv2_110d,62.82,37.18,84.48,15.52,4.52,224,0.875,bicubic
-resnet34,62.82,37.18,84.12,15.88,21.8,224,0.875,bilinear
-swsl_resnet18,62.73,37.27,84.3,15.7,11.69,224,0.875,bilinear
-tf_efficientnet_lite0,62.58,37.42,84.25,15.75,4.65,224,0.875,bicubic
-gluon_resnet34_v1b,62.56,37.44,84.0,16.0,21.8,224,0.875,bicubic
-dla34,62.51,37.49,83.92,16.08,15.78,224,0.875,bilinear
-tf_mobilenetv3_large_100,62.47,37.53,83.96,16.04,5.48,224,0.875,bilinear
-fbnetc_100,62.43,37.57,83.39,16.61,5.57,224,0.875,bilinear
-mnasnet_100,61.91,38.09,83.71,16.29,4.38,224,0.875,bicubic
-ssl_resnet18,61.49,38.51,83.33,16.67,11.69,224,0.875,bilinear
-spnasnet_100,61.21,38.79,82.77,17.23,4.42,224,0.875,bilinear
-tv_resnet34,61.2,38.8,82.72,17.28,21.8,224,0.875,bilinear
-skresnet18,60.85,39.15,82.88,17.12,11.96,224,0.875,bicubic
-tf_mobilenetv3_large_075,60.38,39.62,81.96,18.04,3.99,224,0.875,bilinear
-mobilenetv2_100,60.16,39.84,82.24,17.76,3.5,224,0.875,bicubic
-seresnet18,59.81,40.19,81.68,18.32,11.78,224,0.875,bicubic
-tf_mobilenetv3_large_minimal_100,59.07,40.93,81.14,18.86,3.92,224,0.875,bilinear
-hrnet_w18_small,58.97,41.03,81.34,18.66,13.19,224,0.875,bilinear
-gluon_resnet18_v1b,58.32,41.68,80.96,19.04,11.69,224,0.875,bicubic
-resnet18,57.18,42.82,80.19,19.81,11.69,224,0.875,bilinear
-dla60x_c,56.02,43.98,78.96,21.04,1.34,224,0.875,bilinear
-tf_mobilenetv3_small_100,54.51,45.49,77.08,22.92,2.54,224,0.875,bilinear
-dla46x_c,53.08,46.92,76.84,23.16,1.08,224,0.875,bilinear
-dla46_c,52.2,47.8,75.68,24.32,1.31,224,0.875,bilinear
-tf_mobilenetv3_small_075,52.15,47.85,75.46,24.54,2.04,224,0.875,bilinear
-tf_mobilenetv3_small_minimal_100,49.53,50.47,73.05,26.95,2.04,224,0.875,bilinear
+model,rank_diff,top1,top1_diff,top1_err,top5,top5_diff,top5_err,param_count,img_size,cropt_pct,interpolation
+tf_efficientnet_l2_ns_475,+1,80.470,-7.764,19.530,95.730,-2.816,4.270,480.31,475,0.936,bicubic
+tf_efficientnet_l2_ns,-1,80.250,-8.102,19.750,95.850,-2.798,4.150,480.31,800,0.960,bicubic
+tf_efficientnet_b7_ns,=,78.520,-8.318,21.480,94.370,-3.724,5.630,66.35,600,0.949,bicubic
+tf_efficientnet_b6_ns,=,77.280,-9.182,22.720,93.890,-3.994,6.110,43.04,528,0.942,bicubic
+ig_resnext101_32x48d,+1,76.870,-8.572,23.130,93.320,-4.252,6.680,828.41,224,0.875,bilinear
+ig_resnext101_32x32d,+5,76.840,-8.252,23.160,93.190,-4.246,6.810,468.53,224,0.875,bilinear
+tf_efficientnet_b5_ns,-2,76.820,-9.260,23.180,93.580,-4.174,6.420,30.39,456,0.934,bicubic
+tf_efficientnet_b7_ap,+2,76.090,-9.028,23.910,92.970,-4.282,7.030,66.35,600,0.949,bicubic
+tf_efficientnet_b8_ap,-1,76.090,-9.278,23.910,92.730,-4.564,7.270,87.41,672,0.954,bicubic
+ig_resnext101_32x16d,+7,75.710,-8.466,24.290,92.900,-4.296,7.100,194.03,224,0.875,bilinear
+tf_efficientnet_b4_ns,-2,75.690,-9.468,24.310,93.040,-4.428,6.960,19.34,380,0.922,bicubic
+swsl_resnext101_32x8d,+2,75.450,-8.844,24.550,92.750,-4.424,7.250,88.79,224,0.875,bilinear
+tf_efficientnet_b6_ap,=,75.380,-9.406,24.620,92.440,-4.698,7.560,43.04,528,0.942,bicubic
+tf_efficientnet_b8,-7,74.930,-10.440,25.070,92.320,-5.072,7.680,87.41,672,0.954,bicubic
+tf_efficientnet_b7,-3,74.720,-10.212,25.280,92.220,-4.988,7.780,66.35,600,0.949,bicubic
+tf_efficientnet_b5_ap,-1,74.590,-9.664,25.410,91.990,-4.986,8.010,30.39,456,0.934,bicubic
+swsl_resnext101_32x4d,+7,74.150,-9.084,25.850,91.990,-4.766,8.010,44.18,224,0.875,bilinear
+swsl_resnext101_32x16d,+4,74.010,-9.328,25.990,92.170,-4.682,7.830,194.03,224,0.875,bilinear
+resnest200e,+1,73.930,-9.904,26.070,91.580,-5.258,8.420,70.20,320,0.875,bilinear
+tf_efficientnet_b6,-2,73.900,-10.212,26.100,91.750,-5.134,8.250,43.04,528,0.942,bicubic
+tf_efficientnet_b3_ns,-2,73.870,-10.184,26.130,91.860,-5.052,8.140,12.23,300,0.904,bicubic
+ig_resnext101_32x8d,+7,73.660,-9.028,26.340,92.150,-4.482,7.850,88.79,224,0.875,bilinear
+tf_efficientnet_b5,-2,73.540,-10.276,26.460,91.460,-5.290,8.540,30.39,456,0.934,bicubic
+resnest269e,-8,73.460,-10.726,26.540,91.680,-5.242,8.320,110.93,416,0.875,bilinear
+tf_efficientnet_b4_ap,-2,72.890,-10.358,27.110,90.980,-5.408,9.020,19.34,380,0.922,bicubic
+swsl_resnext50_32x4d,+7,72.580,-9.600,27.420,90.840,-5.388,9.160,25.03,224,0.875,bilinear
+resnest101e,=,72.550,-10.340,27.450,90.810,-5.514,9.190,48.28,256,0.875,bilinear
+tresnet_xl_448,-3,72.550,-10.498,27.450,90.310,-5.864,9.690,78.44,448,0.875,bilinear
+pnasnet5large,-1,72.370,-10.370,27.630,90.260,-5.780,9.740,86.06,331,0.875,bicubic
+nasnetalarge,=,72.310,-10.248,27.690,90.510,-5.526,9.490,88.75,331,0.875,bicubic
+tf_efficientnet_b4,-5,72.280,-10.736,27.720,90.600,-5.698,9.400,19.34,380,0.922,bicubic
+tf_efficientnet_b2_ns,-1,72.270,-10.110,27.730,91.090,-5.162,8.910,9.11,260,0.890,bicubic
+swsl_resnet50,+15,71.690,-9.490,28.310,90.510,-5.476,9.490,25.56,224,0.875,bilinear
+tresnet_xl,+1,71.650,-10.420,28.350,89.630,-6.298,10.370,78.44,224,0.875,bilinear
+tresnet_l_448,-3,71.600,-10.668,28.400,90.060,-5.918,9.940,55.99,448,0.875,bilinear
+ecaresnet101d,-2,71.500,-10.666,28.500,90.310,-5.742,9.690,44.57,224,0.875,bicubic
+ssl_resnext101_32x8d,+4,71.490,-10.136,28.510,90.470,-5.568,9.530,88.79,224,0.875,bilinear
+ssl_resnext101_32x16d,-1,71.400,-10.436,28.600,90.550,-5.544,9.450,194.03,224,0.875,bilinear
+tresnet_m_448,=,71.000,-10.712,29.000,88.680,-6.890,11.320,31.39,448,0.875,bilinear
+resnest50d_4s2x40d,+9,70.940,-10.174,29.060,89.710,-5.858,10.290,30.42,224,0.875,bicubic
+tf_efficientnet_b3_ap,-3,70.920,-10.908,29.080,89.430,-6.194,10.570,12.23,300,0.904,bicubic
+efficientnet_b3a,-6,70.870,-11.004,29.130,89.720,-6.120,10.280,12.23,320,1.000,bicubic
+tf_efficientnet_b1_ns,+2,70.850,-10.536,29.150,90.110,-5.628,9.890,7.79,240,0.882,bicubic
+tresnet_l,=,70.830,-10.658,29.170,89.610,-6.018,10.390,55.99,224,0.875,bilinear
+efficientnet_b3,-2,70.760,-10.738,29.240,89.840,-5.878,10.160,12.23,300,0.904,bicubic
+tf_efficientnet_b3,-6,70.620,-11.020,29.380,89.440,-6.282,10.560,12.23,300,0.904,bicubic
+gluon_senet154,=,70.600,-10.624,29.400,88.920,-6.436,11.080,115.09,224,0.875,bicubic
+ssl_resnext101_32x4d,+5,70.500,-10.428,29.500,89.760,-5.968,10.240,44.18,224,0.875,bilinear
+senet154,-3,70.480,-10.824,29.520,88.990,-6.508,11.010,115.09,224,0.875,bilinear
+gluon_seresnext101_64x4d,+5,70.440,-10.450,29.560,89.350,-5.954,10.650,88.23,224,0.875,bicubic
+resnest50d_1s4x24d,=,70.430,-10.560,29.570,89.240,-6.082,10.760,25.68,224,0.875,bicubic
+tf_efficientnet_lite4,-10,70.430,-11.098,29.570,89.120,-6.548,10.880,13.01,380,0.920,bilinear
+resnest50d,-1,70.420,-10.538,29.580,88.760,-6.622,11.240,27.48,224,0.875,bilinear
+gluon_resnet152_v1s,-4,70.320,-10.692,29.680,88.870,-6.546,11.130,60.32,224,0.875,bicubic
+ecaresnet101d_pruned,+3,70.120,-10.688,29.880,89.580,-6.048,10.420,24.88,224,0.875,bicubic
+inception_resnet_v2,+9,70.120,-10.340,29.880,88.680,-6.630,11.320,55.84,299,0.897,bicubic
+gluon_seresnext101_32x4d,-3,70.010,-10.892,29.990,88.910,-6.384,11.090,48.96,224,0.875,bicubic
+gluon_resnet152_v1d,+6,69.950,-10.520,30.050,88.470,-6.736,11.530,60.21,224,0.875,bicubic
+ecaresnet50d,+2,69.830,-10.774,30.170,89.370,-5.952,10.630,25.58,224,0.875,bicubic
+gluon_resnext101_64x4d,+2,69.690,-10.912,30.310,88.260,-6.734,11.740,83.46,224,0.875,bicubic
+ssl_resnext50_32x4d,+11,69.690,-10.638,30.310,89.420,-5.984,10.580,25.03,224,0.875,bilinear
+tresnet_m,-3,69.650,-11.146,30.350,88.000,-6.856,12.000,31.39,224,0.875,bilinear
+efficientnet_b3_pruned,-7,69.580,-11.276,30.420,88.970,-6.270,11.030,9.86,300,0.904,bicubic
+ens_adv_inception_resnet_v2,+19,69.520,-10.456,30.480,88.500,-6.446,11.500,55.84,299,0.897,bicubic
+efficientnet_b2a,-5,69.490,-11.118,30.510,88.680,-6.630,11.320,9.11,288,1.000,bicubic
+inception_v4,+13,69.350,-10.806,30.650,88.780,-6.194,11.220,42.68,299,0.875,bicubic
+seresnext101_32x4d,+10,69.340,-10.896,30.660,88.050,-6.978,11.950,48.96,224,0.875,bilinear
+ecaresnetlight,-2,69.330,-11.124,30.670,89.220,-6.036,10.780,30.16,224,0.875,bicubic
+gluon_resnet152_v1c,+16,69.130,-10.786,30.870,87.890,-6.952,12.110,60.21,224,0.875,bicubic
+mixnet_xl,-7,69.080,-11.398,30.920,88.310,-6.622,11.690,11.90,224,0.875,bicubic
+efficientnet_b2,-2,69.000,-11.402,31.000,88.620,-6.456,11.380,9.11,260,0.875,bicubic
+gluon_resnet101_v1d,-4,68.990,-11.434,31.010,88.080,-6.940,11.920,44.57,224,0.875,bicubic
+gluon_xception65,+24,68.980,-10.624,31.020,88.320,-6.428,11.680,39.92,299,0.875,bicubic
+gluon_resnext101_32x4d,-3,68.960,-11.374,31.040,88.340,-6.586,11.660,44.18,224,0.875,bicubic
+tf_efficientnet_b2_ap,-2,68.930,-11.376,31.070,88.340,-6.688,11.660,9.11,260,0.890,bicubic
+gluon_resnet152_v1b,+18,68.810,-10.882,31.190,87.710,-7.028,12.290,60.19,224,0.875,bicubic
+dpn131,+12,68.760,-11.068,31.240,87.480,-7.224,12.520,79.25,224,0.875,bicubic
+resnext50d_32x4d,+17,68.750,-10.924,31.250,88.310,-6.558,11.690,25.05,224,0.875,bicubic
+tf_efficientnet_b2,+2,68.750,-11.340,31.250,87.950,-6.956,12.050,9.11,260,0.890,bicubic
+gluon_resnet101_v1s,-6,68.720,-11.580,31.280,87.900,-7.250,12.100,44.67,224,0.875,bicubic
+dpn107,-3,68.710,-11.454,31.290,88.130,-6.782,11.870,86.92,224,0.875,bicubic
+gluon_seresnext50_32x4d,+4,68.670,-11.242,31.330,88.320,-6.498,11.680,27.56,224,0.875,bicubic
+hrnet_w64,+17,68.630,-10.842,31.370,88.070,-6.580,11.930,128.06,224,0.875,bilinear
+resnext50_32x4d,+7,68.610,-11.152,31.390,87.570,-7.030,12.430,25.03,224,0.875,bicubic
+dpn98,+11,68.580,-11.056,31.420,87.660,-6.934,12.340,61.57,224,0.875,bicubic
+ssl_resnet50,+24,68.420,-10.808,31.580,88.580,-6.252,11.420,25.56,224,0.875,bilinear
+ecaresnet50d_pruned,+5,68.390,-11.328,31.610,88.370,-6.520,11.630,19.94,224,0.875,bicubic
+skresnext50_32x4d,-8,68.390,-11.760,31.610,87.590,-7.054,12.410,27.48,224,0.875,bicubic
+dla102x2,+12,68.340,-11.112,31.660,87.870,-6.774,12.130,41.75,224,0.875,bilinear
+efficientnet_b2_pruned,-6,68.300,-11.618,31.700,88.100,-6.748,11.900,8.31,260,0.890,bicubic
+gluon_resnext50_32x4d,+11,68.280,-11.076,31.720,87.320,-7.104,12.680,25.03,224,0.875,bicubic
+tf_efficientnet_lite3,-2,68.230,-11.582,31.770,87.720,-7.194,12.280,8.20,300,0.904,bilinear
+ese_vovnet39b,+10,68.190,-11.130,31.810,88.260,-6.450,11.740,24.57,224,0.875,bicubic
+tf_efficientnet_el,-27,68.180,-12.268,31.820,88.350,-6.810,11.650,10.59,300,0.904,bicubic
+dpn92,-13,68.010,-12.006,31.990,87.590,-7.248,12.410,37.67,224,0.875,bicubic
+gluon_resnet50_v1d,+20,67.910,-11.164,32.090,87.120,-7.356,12.880,25.58,224,0.875,bicubic
+seresnext50_32x4d,+18,67.870,-11.206,32.130,87.620,-6.814,12.380,27.56,224,0.875,bilinear
+resnext101_32x8d,+6,67.850,-11.462,32.150,87.480,-7.046,12.520,88.79,224,0.875,bilinear
+hrnet_w44,+23,67.770,-11.124,32.230,87.530,-6.840,12.470,67.06,224,0.875,bilinear
+hrnet_w48,+5,67.770,-11.540,32.230,87.420,-7.098,12.580,77.47,224,0.875,bilinear
+tf_efficientnet_b0_ns,+32,67.720,-10.932,32.280,88.080,-6.288,11.920,5.29,224,0.875,bicubic
+xception,+16,67.670,-11.378,32.330,87.570,-6.822,12.430,22.86,299,0.897,bicubic
+dla169,+26,67.610,-11.100,32.390,87.560,-6.778,12.440,53.99,224,0.875,bilinear
+gluon_inception_v3,+22,67.590,-11.214,32.410,87.460,-6.920,12.540,23.83,299,0.875,bicubic
+hrnet_w40,+16,67.590,-11.344,32.410,87.130,-7.336,12.870,57.56,224,0.875,bilinear
+gluon_resnet101_v1c,-7,67.560,-11.984,32.440,87.160,-7.426,12.840,44.57,224,0.875,bicubic
+seresnet152,+25,67.550,-11.108,32.450,87.390,-6.984,12.610,66.82,224,0.875,bilinear
+res2net50_26w_8s,+4,67.530,-11.680,32.470,87.270,-7.092,12.730,48.40,224,0.875,bilinear
+tf_efficientnet_b1_ap,=,67.520,-11.758,32.480,87.770,-6.538,12.230,7.79,240,0.882,bicubic
+tf_efficientnet_cc_b1_8e,-3,67.480,-11.818,32.520,87.310,-7.054,12.690,39.72,240,0.882,bicubic
+gluon_resnet101_v1b,-5,67.450,-11.854,32.550,87.230,-7.294,12.770,44.55,224,0.875,bicubic
+res2net101_26w_4s,+2,67.450,-11.746,32.550,87.010,-7.430,12.990,45.21,224,0.875,bilinear
+resnet50,+6,67.440,-11.592,32.560,87.420,-6.964,12.580,25.56,224,0.875,bicubic
+resnetblur50,-6,67.440,-11.850,32.560,87.430,-7.202,12.570,25.56,224,0.875,bicubic
+resnest26d,+22,67.210,-11.272,32.790,87.180,-7.110,12.820,17.07,224,0.875,bilinear
+efficientnet_b1,+14,67.160,-11.538,32.840,87.150,-7.002,12.850,7.79,240,0.875,bicubic
+seresnet101,+26,67.150,-11.246,32.850,87.050,-7.208,12.950,49.33,224,0.875,bilinear
+gluon_resnet50_v1s,+10,67.100,-11.612,32.900,86.860,-7.382,13.140,25.68,224,0.875,bicubic
+dla60x,+26,67.080,-11.162,32.920,87.170,-6.852,12.830,17.65,224,0.875,bilinear
+dla60_res2net,+18,67.030,-11.442,32.970,87.140,-7.064,12.860,21.15,224,0.875,bilinear
+resnet152,+23,67.020,-11.292,32.980,87.570,-6.476,12.430,60.19,224,0.875,bilinear
+dla102x,+13,67.000,-11.508,33.000,86.770,-7.464,13.230,26.77,224,0.875,bilinear
+mixnet_l,-3,66.970,-12.006,33.030,86.940,-7.244,13.060,7.33,224,0.875,bicubic
+res2net50_26w_6s,+10,66.910,-11.664,33.090,86.900,-7.226,13.100,37.05,224,0.875,bilinear
+efficientnet_es,+26,66.890,-11.164,33.110,86.730,-7.200,13.270,5.44,224,0.875,bicubic
+tf_efficientnet_b1,-1,66.890,-11.942,33.110,87.040,-7.156,12.960,7.79,240,0.882,bicubic
+tf_efficientnet_em,+4,66.870,-11.828,33.130,86.980,-7.340,13.020,6.90,240,0.882,bicubic
+hrnet_w32,+13,66.790,-11.658,33.210,87.290,-6.898,12.710,41.23,224,0.875,bilinear
+tf_mixnet_l,-2,66.780,-11.990,33.220,86.460,-7.544,13.540,7.33,224,0.875,bicubic
+hrnet_w30,+18,66.760,-11.436,33.240,86.790,-7.430,13.210,37.71,224,0.875,bilinear
+selecsls60b,+11,66.720,-11.698,33.280,86.540,-7.626,13.460,32.77,224,0.875,bicubic
+wide_resnet101_2,-8,66.680,-12.166,33.320,87.040,-7.244,12.960,126.89,224,0.875,bilinear
+wide_resnet50_2,+6,66.650,-11.818,33.350,86.810,-7.276,13.190,68.88,224,0.875,bilinear
+dla60_res2next,+6,66.640,-11.808,33.360,87.020,-7.124,12.980,17.33,224,0.875,bilinear
+adv_inception_v3,+30,66.600,-10.980,33.400,86.560,-7.164,13.440,23.83,299,0.875,bicubic
+dla102,+16,66.550,-11.476,33.450,86.910,-7.040,13.090,33.73,224,0.875,bilinear
+gluon_resnet50_v1c,+16,66.540,-11.470,33.460,86.160,-7.828,13.840,25.58,224,0.875,bicubic
+tf_inception_v3,+21,66.420,-11.436,33.580,86.680,-6.964,13.320,23.83,299,0.875,bicubic
+efficientnet_b0,+22,66.250,-11.442,33.750,85.950,-7.582,14.050,5.29,224,0.875,bicubic
+seresnet50,+22,66.240,-11.396,33.760,86.330,-7.422,13.670,28.09,224,0.875,bilinear
+selecsls60,+15,66.220,-11.762,33.780,86.330,-7.502,13.670,30.67,224,0.875,bicubic
+tf_efficientnet_cc_b0_8e,+16,66.210,-11.698,33.790,86.220,-7.436,13.780,24.01,224,0.875,bicubic
+tv_resnext50_32x4d,+20,66.180,-11.438,33.820,86.040,-7.658,13.960,25.03,224,0.875,bilinear
+res2net50_26w_4s,+13,66.170,-11.776,33.830,86.600,-7.252,13.400,25.70,224,0.875,bilinear
+inception_v3,+25,66.120,-11.316,33.880,86.340,-7.136,13.660,23.83,299,0.875,bicubic
+efficientnet_b1_pruned,=,66.080,-12.162,33.920,86.580,-7.252,13.420,6.33,240,0.882,bicubic
+gluon_resnet50_v1b,+19,66.040,-11.538,33.960,86.270,-7.448,13.730,25.56,224,0.875,bicubic
+res2net50_14w_8s,+2,66.020,-12.132,33.980,86.240,-7.602,13.760,25.06,224,0.875,bilinear
+densenet161,+23,65.850,-11.498,34.150,86.460,-7.188,13.540,28.68,224,0.875,bicubic
+res2next50,-3,65.850,-12.392,34.150,85.830,-8.062,14.170,24.67,224,0.875,bilinear
+seresnext26tn_32x4d,+3,65.850,-12.140,34.150,85.680,-8.068,14.320,16.81,224,0.875,bicubic
+skresnet34,+32,65.770,-11.140,34.230,85.960,-7.356,14.040,22.28,224,0.875,bicubic
+resnet101,+18,65.680,-11.694,34.320,85.980,-7.566,14.020,44.55,224,0.875,bilinear
+dpn68b,+13,65.600,-11.914,34.400,85.940,-7.882,14.060,12.61,224,0.875,bicubic
+seresnext26t_32x4d,=,65.600,-12.388,34.400,86.090,-7.616,13.910,16.82,224,0.875,bicubic
+selecsls42b,+22,65.590,-11.586,34.410,85.830,-7.562,14.170,32.46,224,0.875,bicubic
+tf_efficientnet_b0_ap,+23,65.490,-11.594,34.510,85.550,-7.704,14.450,5.29,224,0.875,bicubic
+seresnext26d_32x4d,+6,65.420,-12.184,34.580,85.970,-7.642,14.030,16.81,224,0.875,bicubic
+tf_efficientnet_lite2,+10,65.390,-12.070,34.610,86.030,-7.716,13.970,6.09,260,0.890,bicubic
+res2net50_48w_2s,+8,65.320,-12.194,34.680,85.960,-7.588,14.040,25.29,224,0.875,bilinear
+densenetblur121d,+28,65.300,-11.276,34.700,85.710,-7.480,14.290,8.00,224,0.875,bicubic
+densenet201,+13,65.280,-12.010,34.720,85.670,-7.808,14.330,20.01,224,0.875,bicubic
+tf_efficientnet_es,+13,65.240,-12.024,34.760,85.540,-8.060,14.460,5.44,224,0.875,bicubic
+dla60,+17,65.220,-11.804,34.780,85.750,-7.558,14.250,22.33,224,0.875,bilinear
+tf_efficientnet_cc_b0_4e,+8,65.130,-12.174,34.870,85.130,-8.202,14.870,13.31,224,0.875,bicubic
+mobilenetv2_120d,+8,65.040,-12.254,34.960,85.990,-7.512,14.010,5.83,224,0.875,bicubic
+seresnext26_32x4d,+12,65.040,-12.060,34.960,85.650,-7.660,14.350,16.79,224,0.875,bicubic
+hrnet_w18,+18,64.910,-11.846,35.090,85.750,-7.692,14.250,21.30,224,0.875,bilinear
+densenet169,+26,64.780,-11.132,35.220,85.250,-7.774,14.750,14.15,224,0.875,bicubic
+mixnet_m,+7,64.690,-12.566,35.310,85.470,-7.948,14.530,5.01,224,0.875,bicubic
+resnet26d,+16,64.630,-12.050,35.370,85.120,-8.046,14.880,16.01,224,0.875,bicubic
+tf_efficientnet_lite1,+16,64.370,-12.268,35.630,85.490,-7.742,14.510,5.42,240,0.882,bicubic
+tf_efficientnet_b0,+12,64.290,-12.550,35.710,85.250,-7.976,14.750,5.29,224,0.875,bicubic
+tf_mixnet_m,+8,64.270,-12.680,35.730,85.090,-8.066,14.910,5.01,224,0.875,bicubic
+dpn68,+17,64.220,-12.086,35.780,85.180,-7.790,14.820,12.61,224,0.875,bicubic
+mobilenetv2_140,+14,64.050,-12.474,35.950,85.020,-7.970,14.980,6.11,224,0.875,bicubic
+densenet121,+22,63.740,-11.834,36.260,84.630,-8.026,15.370,7.98,224,0.875,bicubic
+resnest14d,+23,63.600,-11.904,36.400,84.220,-8.294,15.780,10.61,224,0.875,bilinear
+tf_mixnet_s,+18,63.590,-12.058,36.410,84.270,-8.366,15.730,4.13,224,0.875,bicubic
+resnet26,+23,63.450,-11.842,36.550,84.270,-8.300,15.730,16.00,224,0.875,bicubic
+mixnet_s,+13,63.380,-12.608,36.620,84.710,-8.084,15.290,4.13,224,0.875,bicubic
+mobilenetv3_large_100,+14,63.360,-12.408,36.640,84.080,-8.460,15.920,5.48,224,0.875,bicubic
+tv_resnet50,+10,63.330,-12.800,36.670,84.650,-8.212,15.350,25.56,224,0.875,bilinear
+mobilenetv3_rw,+14,63.230,-12.398,36.770,84.520,-8.190,15.480,5.48,224,0.875,bicubic
+semnasnet_100,+17,63.120,-12.336,36.880,84.530,-8.062,15.470,3.89,224,0.875,bicubic
+tv_densenet121,+26,62.940,-11.812,37.060,84.260,-7.892,15.740,7.98,224,0.875,bicubic
+seresnet34,+24,62.890,-11.918,37.110,84.220,-7.906,15.780,21.96,224,0.875,bilinear
+hrnet_w18_small_v2,+17,62.830,-12.296,37.170,83.970,-8.446,16.030,15.60,224,0.875,bilinear
+mobilenetv2_110d,+19,62.820,-12.232,37.180,84.480,-7.700,15.520,4.52,224,0.875,bicubic
+resnet34,+17,62.820,-12.292,37.180,84.120,-8.168,15.880,21.80,224,0.875,bilinear
+swsl_resnet18,+30,62.730,-10.556,37.270,84.300,-7.432,15.700,11.69,224,0.875,bilinear
+tf_efficientnet_lite0,+18,62.580,-12.262,37.420,84.250,-7.920,15.750,4.65,224,0.875,bicubic
+gluon_resnet34_v1b,+22,62.560,-12.020,37.440,84.000,-7.988,16.000,21.80,224,0.875,bicubic
+dla34,+20,62.510,-12.126,37.490,83.920,-8.144,16.080,15.78,224,0.875,bilinear
+tf_mobilenetv3_large_100,+5,62.470,-13.046,37.530,83.960,-8.640,16.040,5.48,224,0.875,bilinear
+fbnetc_100,+10,62.430,-12.690,37.570,83.390,-8.996,16.610,5.57,224,0.875,bilinear
+mnasnet_100,+16,61.910,-12.746,38.090,83.710,-8.416,16.290,4.38,224,0.875,bicubic
+ssl_resnet18,+26,61.490,-11.110,38.510,83.330,-8.086,16.670,11.69,224,0.875,bilinear
+spnasnet_100,+17,61.210,-12.870,38.790,82.770,-9.062,17.230,4.42,224,0.875,bilinear
+tv_resnet34,+20,61.200,-12.114,38.800,82.720,-8.700,17.280,21.80,224,0.875,bilinear
+skresnet18,+21,60.850,-12.194,39.150,82.880,-8.298,17.120,11.96,224,0.875,bicubic
+tf_mobilenetv3_large_075,+17,60.380,-13.062,39.620,81.960,-9.392,18.040,3.99,224,0.875,bilinear
+mobilenetv2_100,+20,60.160,-12.818,39.840,82.240,-8.776,17.760,3.50,224,0.875,bicubic
+seresnet18,+24,59.810,-11.948,40.190,81.680,-8.654,18.320,11.78,224,0.875,bicubic
+tf_mobilenetv3_large_minimal_100,+22,59.070,-13.174,40.930,81.140,-9.496,18.860,3.92,224,0.875,bilinear
+hrnet_w18_small,+20,58.970,-13.372,41.030,81.340,-9.332,18.660,13.19,224,0.875,bilinear
+gluon_resnet18_v1b,+22,58.320,-12.510,41.680,80.960,-8.796,19.040,11.69,224,0.875,bicubic
+resnet18,+23,57.180,-12.578,42.820,80.190,-8.888,19.810,11.69,224,0.875,bilinear
+dla60x_c,+25,56.020,-11.888,43.980,78.960,-9.474,21.040,1.34,224,0.875,bilinear
+tf_mobilenetv3_small_100,+23,54.510,-13.408,45.490,77.080,-10.582,22.920,2.54,224,0.875,bilinear
+dla46x_c,+24,53.080,-12.900,46.920,76.840,-10.140,23.160,1.08,224,0.875,bilinear
+dla46_c,+25,52.200,-12.678,47.800,75.680,-10.606,24.320,1.31,224,0.875,bilinear
+tf_mobilenetv3_small_075,+23,52.150,-13.568,47.850,75.460,-10.676,24.540,2.04,224,0.875,bilinear
+tf_mobilenetv3_small_minimal_100,+24,49.530,-13.368,50.470,73.050,-11.180,26.950,2.04,224,0.875,bilinear
--- a/results/results-sketch.csv
+++ b/results/results-sketch.csv
@ -1,239 +1,239 @@
-model,top1,top1_err,top5,top5_err,param_count,img_size,cropt_pct,interpolation
-ig_resnext101_32x48d,58.8143,41.1857,81.0863,18.9137,828.41,224,0.875,bilinear
-ig_resnext101_32x32d,58.38,41.62,80.3789,19.6211,468.53,224,0.875,bilinear
-ig_resnext101_32x16d,57.7001,42.2999,79.9131,20.0869,194.03,224,0.875,bilinear
-swsl_resnext101_32x16d,57.4663,42.5337,80.3808,19.6192,194.03,224,0.875,bilinear
-swsl_resnext101_32x8d,56.4346,43.5654,78.9345,21.0655,88.79,224,0.875,bilinear
-ig_resnext101_32x8d,54.9176,45.0824,77.5452,22.4548,88.79,224,0.875,bilinear
-swsl_resnext101_32x4d,53.5911,46.4089,76.3387,23.6613,44.18,224,0.875,bilinear
-tf_efficientnet_l2_ns_475,51.4866,48.5134,73.9295,26.0705,480.31,475,0.936,bicubic
-swsl_resnext50_32x4d,50.449,49.551,73.3577,26.6423,25.03,224,0.875,bilinear
-swsl_resnet50,49.551,50.449,72.3319,27.6681,25.56,224,0.875,bilinear
-tf_efficientnet_b7_ns,47.8001,52.1999,69.6378,30.3622,66.35,600,0.949,bicubic
-tf_efficientnet_b6_ns,47.751,52.249,69.9621,30.0379,43.04,528,0.942,bicubic
-tf_efficientnet_l2_ns,47.5702,52.4298,70.0171,29.9829,480.31,800,0.96,bicubic
-tf_efficientnet_b8_ap,45.7781,54.2219,67.9047,32.0953,87.41,672,0.954,bicubic
-tf_efficientnet_b5_ns,45.6071,54.3929,67.8516,32.1484,30.39,456,0.934,bicubic
-tf_efficientnet_b4_ns,43.4554,56.5446,65.5132,34.4868,19.34,380,0.922,bicubic
-tf_efficientnet_b8,42.5023,57.4977,64.8745,35.1255,87.41,672,0.954,bicubic
-tf_efficientnet_b7,41.4372,58.5628,63.0274,36.9726,66.35,600,0.949,bicubic
-tf_efficientnet_b7_ap,41.4333,58.5667,62.8761,37.1239,66.35,600,0.949,bicubic
-tf_efficientnet_b5_ap,41.4196,58.5804,62.0822,37.9178,30.39,456,0.934,bicubic
-tf_efficientnet_b6_ap,41.0914,58.9086,62.3593,37.6407,43.04,528,0.942,bicubic
-tf_efficientnet_b4_ap,40.4763,59.5237,61.7127,38.2873,19.34,380,0.922,bicubic
-tf_efficientnet_b3_ns,39.5822,60.4178,61.4632,38.5368,12.23,300,0.904,bicubic
-tf_efficientnet_b5,38.3285,61.6715,59.9285,40.0715,30.39,456,0.934,bicubic
-tf_efficientnet_b3_ap,37.0611,62.9389,57.2363,42.7637,12.23,300,0.904,bicubic
-resnest269e,36.67,63.33,56.8099,43.1901,110.93,416,0.875,bilinear
-tf_efficientnet_b2_ns,36.1768,63.8232,57.5547,42.4453,9.11,260,0.89,bicubic
-ecaresnet101d,36.0058,63.9942,56.1536,43.8464,44.57,224,0.875,bicubic
-swsl_resnet18,35.8604,64.1396,58.437,41.563,11.69,224,0.875,bilinear
-resnest200e,35.8466,64.1534,55.8903,44.1097,70.2,320,0.875,bilinear
-resnest101e,35.3652,64.6348,55.7861,44.2139,48.28,256,0.875,bilinear
-ssl_resnext101_32x16d,34.6087,65.3913,55.9139,44.0861,194.03,224,0.875,bilinear
-resnest50d_4s2x40d,34.3611,65.6389,54.7112,45.2888,30.42,224,0.875,bicubic
-tf_efficientnet_b1_ns,34.1528,65.8472,55.4894,44.5106,7.79,240,0.882,bicubic
-tf_efficientnet_b4,34.0624,65.9376,54.216,45.784,19.34,380,0.922,bicubic
-ssl_resnext101_32x8d,34.0211,65.9789,55.5935,44.4065,88.79,224,0.875,bilinear
-tf_efficientnet_b6,34.0054,65.9946,54.5403,45.4597,43.04,528,0.942,bicubic
-efficientnet_b3_pruned,33.9956,66.0044,54.1099,45.8901,9.86,300,0.904,bicubic
-tresnet_xl,33.2587,66.7413,52.2962,47.7038,78.44,224,0.875,bilinear
-resnest50d_1s4x24d,33.1388,66.8612,52.8307,47.1693,25.68,224,0.875,bicubic
-resnest50d,32.9678,67.0322,52.701,47.299,27.48,224,0.875,bilinear
-tf_efficientnet_b3,32.8637,67.1363,52.9623,47.0377,12.23,300,0.904,bicubic
-inception_resnet_v2,32.736,67.264,50.6396,49.3604,55.84,299,0.8975,bicubic
-gluon_resnet152_v1d,32.7301,67.2699,51.0837,48.9163,60.21,224,0.875,bicubic
-tf_efficientnet_b2_ap,32.679,67.321,52.2333,47.7667,9.11,260,0.89,bicubic
-nasnetalarge,32.5827,67.4173,49.7868,50.2132,88.75,331,0.875,bicubic
-tresnet_l,32.567,67.433,51.1407,48.8593,55.99,224,0.875,bilinear
-pnasnet5large,32.5316,67.4684,50.1877,49.8123,86.06,331,0.875,bicubic
-ens_adv_inception_resnet_v2,32.3705,67.6295,50.4274,49.5726,55.84,299,0.8975,bicubic
-gluon_resnet152_v1s,32.3312,67.6688,50.5394,49.4606,60.32,224,0.875,bicubic
-gluon_seresnext101_64x4d,32.1936,67.8064,50.3272,49.6728,88.23,224,0.875,bicubic
-gluon_seresnext101_32x4d,32.115,67.885,51.2409,48.7591,48.96,224,0.875,bicubic
-efficientnet_b3a,31.7279,68.2721,51.3215,48.6785,12.23,320,1.0,bicubic
-efficientnet_b3,31.5648,68.4352,51.2724,48.7276,12.23,300,0.904,bicubic
-resnet50,31.5451,68.4549,50.1719,49.8281,25.56,224,0.875,bicubic
-ssl_resnext101_32x4d,31.4331,68.5669,52.1154,47.8846,44.18,224,0.875,bilinear
-inception_v4,31.382,68.618,49.2366,50.7634,42.68,299,0.875,bicubic
-ecaresnetlight,31.1325,68.8675,50.2525,49.7475,30.16,224,0.875,bicubic
-gluon_resnet101_v1s,31.1128,68.8872,49.7907,50.2093,44.67,224,0.875,bicubic
-tf_efficientnet_cc_b0_8e,31.0814,68.9186,50.7733,49.2267,24.01,224,0.875,bicubic
-ecaresnet50d,31.0637,68.9363,50.846,49.154,25.58,224,0.875,bicubic
-gluon_resnet152_v1c,31.0067,68.9933,48.9359,51.0641,60.21,224,0.875,bicubic
-tresnet_m,30.9929,69.0071,48.6903,51.3097,31.39,224,0.875,bilinear
-gluon_resnext101_64x4d,30.9812,69.0188,48.5527,51.4473,83.46,224,0.875,bicubic
-tf_efficientnet_cc_b1_8e,30.9006,69.0994,50.0737,49.9263,39.72,240,0.882,bicubic
-ecaresnet101d_pruned,30.8947,69.1053,50.001,49.999,24.88,224,0.875,bicubic
-gluon_resnext101_32x4d,30.8809,69.1191,48.537,51.463,44.18,224,0.875,bicubic
-tf_efficientnet_lite4,30.8397,69.1603,50.3979,49.6021,13.01,380,0.92,bilinear
-dpn107,30.6805,69.3195,48.8062,51.1938,86.92,224,0.875,bicubic
-ese_vovnet39b,30.6766,69.3234,49.8929,50.1071,24.57,224,0.875,bicubic
-tresnet_xl_448,30.6196,69.3804,49.0715,50.9285,78.44,448,0.875,bilinear
-gluon_resnet152_v1b,30.6176,69.3824,48.5292,51.4708,60.19,224,0.875,bicubic
-ssl_resnext50_32x4d,30.594,69.406,50.6534,49.3466,25.03,224,0.875,bilinear
-gluon_resnet101_v1d,30.5095,69.4905,47.975,52.025,44.57,224,0.875,bicubic
-resnest26d,30.4997,69.5003,50.677,49.323,17.07,224,0.875,bilinear
-efficientnet_b2a,30.4231,69.5769,49.6748,50.3252,9.11,288,1.0,bicubic
-tf_efficientnet_b1_ap,30.4191,69.5809,49.5529,50.4471,7.79,240,0.882,bicubic
-dpn98,30.0576,69.9424,48.2403,51.7597,61.57,224,0.875,bicubic
-tf_efficientnet_b2,30.0202,69.9798,49.5903,50.4097,9.11,260,0.89,bicubic
-dpn131,30.0143,69.9857,48.144,51.856,79.25,224,0.875,bicubic
-senet154,30.0006,69.9994,48.032,51.968,115.09,224,0.875,bilinear
-dpn92,29.9691,70.0309,49.1599,50.8401,37.67,224,0.875,bicubic
-gluon_senet154,29.8866,70.1134,47.8728,52.1272,115.09,224,0.875,bicubic
-xception,29.8493,70.1507,48.6903,51.3097,22.86,299,0.8975,bicubic
-adv_inception_v3,29.8237,70.1763,47.8669,52.1331,23.83,299,0.875,bicubic
-resnetblur50,29.6233,70.3767,48.2501,51.7499,25.56,224,0.875,bicubic
-efficientnet_b2,29.6174,70.3826,48.7728,51.2272,9.11,260,0.875,bicubic
-gluon_xception65,29.5545,70.4455,47.523,52.477,39.92,299,0.875,bicubic
-resnext101_32x8d,29.4347,70.5653,48.482,51.518,88.79,224,0.875,bilinear
-ssl_resnet50,29.4229,70.5771,49.773,50.227,25.56,224,0.875,bilinear
-resnext50_32x4d,29.3285,70.6715,47.3953,52.6047,25.03,224,0.875,bicubic
-ecaresnet50d_pruned,29.2165,70.7835,48.4584,51.5416,19.94,224,0.875,bicubic
-tresnet_l_448,29.1674,70.8326,47.2342,52.7658,55.99,448,0.875,bilinear
-gluon_inception_v3,29.1143,70.8857,46.9433,53.0567,23.83,299,0.875,bicubic
-hrnet_w64,28.9866,71.0134,47.1399,52.8601,128.06,224,0.875,bilinear
-tf_efficientnet_b0_ns,28.9139,71.0861,49.0106,50.9894,5.29,224,0.875,bicubic
-tf_efficientnet_b1,28.8923,71.1077,47.5112,52.4888,7.79,240,0.882,bicubic
-gluon_resnet101_v1b,28.8569,71.1431,46.3715,53.6285,44.55,224,0.875,bicubic
-skresnext50_32x4d,28.8176,71.1824,46.5032,53.4968,27.48,224,0.875,bicubic
-tf_efficientnet_lite3,28.6545,71.3455,47.358,52.642,8.2,300,0.904,bilinear
-hrnet_w40,28.6447,71.3553,47.4425,52.5575,57.56,224,0.875,bilinear
-gluon_seresnext50_32x4d,28.6408,71.3592,46.4501,53.5499,27.56,224,0.875,bicubic
-skresnet34,28.629,71.371,47.9573,52.0427,22.28,224,0.875,bicubic
-resnet152,28.5347,71.4653,47.1143,52.8857,60.19,224,0.875,bilinear
-hrnet_w48,28.4069,71.5931,47.5741,52.4259,77.47,224,0.875,bilinear
-gluon_resnext50_32x4d,28.3833,71.6167,45.3261,54.6739,25.03,224,0.875,bicubic
-efficientnet_b2_pruned,28.3657,71.6343,47.0593,52.9407,8.31,260,0.89,bicubic
-tf_efficientnet_b0_ap,28.3499,71.6501,47.5309,52.4691,5.29,224,0.875,bicubic
-dla102x2,28.3185,71.6815,46.7567,53.2433,41.75,224,0.875,bilinear
-dla169,28.3106,71.6894,47.3992,52.6008,53.99,224,0.875,bilinear
-tf_efficientnet_cc_b0_4e,28.3106,71.6894,47.3639,52.6361,13.31,224,0.875,bicubic
-mixnet_xl,28.293,71.707,46.7174,53.2826,11.9,224,0.875,bicubic
-gluon_resnet50_v1d,28.236,71.764,45.8763,54.1237,25.58,224,0.875,bicubic
-wide_resnet101_2,28.1063,71.8937,46.4246,53.5754,126.89,224,0.875,bilinear
-gluon_resnet101_v1c,28.1023,71.8977,45.953,54.047,44.57,224,0.875,bicubic
-densenet161,28.1004,71.8996,46.6506,53.3494,28.68,224,0.875,bicubic
-regnetx_320,28.0788,71.9212,45.1198,54.8802,107.81,224,0.875,bicubic
-regnety_320,28.0709,71.9291,45.4597,54.5403,145.05,224,0.875,bicubic
-dpn68b,27.8842,72.1158,47.4602,52.5398,12.61,224,0.875,bicubic
-regnetx_160,27.8253,72.1747,45.6307,54.3693,54.28,224,0.875,bicubic
-tf_inception_v3,27.786,72.214,45.7113,54.2887,23.83,299,0.875,bicubic
-res2net101_26w_4s,27.7742,72.2258,45.1709,54.8291,45.21,224,0.875,bilinear
-regnety_160,27.6386,72.3614,45.5344,54.4656,83.59,224,0.875,bicubic
-hrnet_w44,27.6248,72.3752,45.8311,54.1689,67.06,224,0.875,bilinear
-inception_v3,27.5698,72.4302,45.2613,54.7387,23.83,299,0.875,bicubic
-regnetx_080,27.4106,72.5894,45.0215,54.9785,39.57,224,0.875,bicubic
-hrnet_w30,27.3851,72.6149,46.5425,53.4575,37.71,224,0.875,bilinear
-hrnet_w32,27.3772,72.6228,45.9903,54.0097,41.23,224,0.875,bilinear
-gluon_resnet50_v1s,27.3261,72.6739,45.2141,54.7859,25.68,224,0.875,bicubic
-densenet201,27.2613,72.7387,46.2241,53.7759,20.01,224,0.875,bicubic
-regnety_064,27.2279,72.7721,44.8506,55.1494,30.58,224,0.875,bicubic
-densenetblur121d,27.224,72.776,46.3067,53.6933,8.0,224,0.875,bicubic
-efficientnet_b1_pruned,27.1945,72.8055,45.8724,54.1276,6.33,240,0.882,bicubic
-res2net50_26w_8s,27.0726,72.9274,44.432,55.568,48.4,224,0.875,bilinear
-dla102x,27.0235,72.9765,45.4951,54.5049,26.77,224,0.875,bilinear
-resnet101,26.9685,73.0315,45.2357,54.7643,44.55,224,0.875,bilinear
-resnext50d_32x4d,26.8742,73.1258,44.43,55.57,25.05,224,0.875,bicubic
-regnetx_120,26.8644,73.1356,44.6816,55.3184,46.11,224,0.875,bicubic
-seresnext101_32x4d,26.8192,73.1808,43.5084,56.4916,48.96,224,0.875,bilinear
-densenet169,26.8113,73.1887,45.3752,54.6248,14.15,224,0.875,bicubic
-regnetx_064,26.8015,73.1985,44.9036,55.0964,26.21,224,0.875,bicubic
-regnety_120,26.7818,73.2182,44.4399,55.5601,51.82,224,0.875,bicubic
-regnetx_032,26.7071,73.2929,45.2259,54.7741,15.3,224,0.875,bicubic
-densenet121,26.6757,73.3243,45.8999,54.1001,7.98,224,0.875,bicubic
-seresnet152,26.6718,73.3282,43.9447,56.0553,66.82,224,0.875,bilinear
-tf_efficientnet_el,26.6226,73.3774,44.6364,55.3636,10.59,300,0.904,bicubic
-efficientnet_es,26.6168,73.3832,45.106,54.894,5.44,224,0.875,bicubic
-res2net50_26w_6s,26.5873,73.4127,43.9781,56.0219,37.05,224,0.875,bilinear
-dla60x,26.5637,73.4363,45.0392,54.9608,17.65,224,0.875,bilinear
-regnety_080,26.5146,73.4854,44.3554,55.6446,39.18,224,0.875,bicubic
-tf_efficientnet_b0,26.491,73.509,45.6562,54.3438,5.29,224,0.875,bicubic
-res2net50_14w_8s,26.4713,73.5287,44.3691,55.6309,25.06,224,0.875,bilinear
-gluon_resnet50_v1b,26.432,73.568,44.0331,55.9669,25.56,224,0.875,bicubic
-regnetx_040,26.2395,73.7605,44.4241,55.5759,22.12,224,0.875,bicubic
-dpn68,26.1216,73.8784,44.2335,55.7665,12.61,224,0.875,bicubic
-hrnet_w18,25.9761,74.0239,44.8093,55.1907,21.3,224,0.875,bilinear
-regnety_040,25.9133,74.0867,43.8543,56.1457,20.65,224,0.875,bicubic
-resnet34,25.8838,74.1162,43.9899,56.0101,21.8,224,0.875,bilinear
-res2net50_26w_4s,25.87,74.13,43.1606,56.8394,25.7,224,0.875,bilinear
-tresnet_m_448,25.8504,74.1496,42.8678,57.1322,31.39,448,0.875,bilinear
-gluon_resnet50_v1c,25.7954,74.2046,43.0172,56.9828,25.58,224,0.875,bicubic
-selecsls60,25.7285,74.2715,44.0685,55.9315,30.67,224,0.875,bicubic
-dla60_res2net,25.6421,74.3579,43.589,56.411,21.15,224,0.875,bilinear
-dla60_res2next,25.6382,74.3618,43.6696,56.3304,17.33,224,0.875,bilinear
-tf_efficientnet_lite1,25.5065,74.4935,43.5831,56.4169,5.42,240,0.882,bicubic
-mixnet_l,25.4986,74.5014,43.4632,56.5368,7.33,224,0.875,bicubic
-efficientnet_b1,25.4829,74.5171,43.2864,56.7136,7.79,240,0.875,bicubic
-tv_resnext50_32x4d,25.4692,74.5308,42.7912,57.2088,25.03,224,0.875,bilinear
-tf_mixnet_l,25.42,74.58,42.5436,57.4564,7.33,224,0.875,bicubic
-res2next50,25.3945,74.6055,42.4925,57.5075,24.67,224,0.875,bilinear
-selecsls60b,25.3277,74.6723,43.5536,56.4464,32.77,224,0.875,bicubic
-seresnet101,25.3277,74.6723,42.8285,57.1715,49.33,224,0.875,bilinear
-regnety_032,25.3237,74.6763,42.9071,57.0929,19.44,224,0.875,bicubic
-dla102,25.3139,74.6861,43.8366,56.1634,33.73,224,0.875,bilinear
-wide_resnet50_2,25.31,74.69,42.1781,57.8219,68.88,224,0.875,bilinear
-resnest14d,25.2825,74.7175,44.1215,55.8785,10.61,224,0.875,bilinear
-seresnext50_32x4d,25.2176,74.7824,41.9383,58.0617,27.56,224,0.875,bilinear
-res2net50_48w_2s,25.0231,74.9769,42.2017,57.7983,25.29,224,0.875,bilinear
-efficientnet_b0,25.0152,74.9848,42.7853,57.2147,5.29,224,0.875,bicubic
-gluon_resnet34_v1b,24.9484,75.0516,42.237,57.763,21.8,224,0.875,bicubic
-mobilenetv2_120d,24.9327,75.0673,43.0643,56.9357,5.83,224,0.875,bicubic
-dla60,24.9268,75.0732,43.3021,56.6979,22.33,224,0.875,bilinear
-regnety_016,24.8187,75.1813,42.6261,57.3739,11.2,224,0.875,bicubic
-tf_efficientnet_em,24.5338,75.4662,42.41,57.59,6.9,240,0.882,bicubic
-tf_efficientnet_lite2,24.5299,75.4701,42.292,57.708,6.09,260,0.89,bicubic
-skresnet18,24.4945,75.5055,42.5377,57.4623,11.96,224,0.875,bicubic
-regnetx_016,24.4768,75.5232,42.5023,57.4977,9.19,224,0.875,bicubic
-tf_efficientnet_lite0,24.3707,75.6293,42.5102,57.4898,4.65,224,0.875,bicubic
-tv_resnet50,24.0917,75.9083,41.3095,58.6905,25.56,224,0.875,bilinear
-seresnet34,24.0366,75.9634,41.8951,58.1049,21.96,224,0.875,bilinear
-tv_densenet121,23.846,76.154,41.9207,58.0793,7.98,224,0.875,bicubic
-tf_efficientnet_es,23.8244,76.1756,41.3193,58.6807,5.44,224,0.875,bicubic
-mobilenetv2_140,23.7104,76.2896,41.4687,58.5313,6.11,224,0.875,bicubic
-mixnet_m,23.7085,76.2915,41.1386,58.8614,5.01,224,0.875,bicubic
-dla34,23.677,76.323,41.5434,58.4566,15.78,224,0.875,bilinear
-seresnet50,23.6436,76.3564,40.0814,59.9186,28.09,224,0.875,bilinear
-tf_mixnet_m,23.4786,76.5214,41.0049,58.9951,5.01,224,0.875,bicubic
-tv_resnet34,23.4727,76.5273,41.3665,58.6335,21.8,224,0.875,bilinear
-selecsls42b,23.3665,76.6335,40.6768,59.3232,32.46,224,0.875,bicubic
-mobilenetv2_110d,23.0698,76.9302,40.7436,59.2564,4.52,224,0.875,bicubic
-mobilenetv3_large_100,22.665,77.335,40.7848,59.2152,5.48,224,0.875,bicubic
-mobilenetv3_rw,22.6257,77.3743,40.3702,59.6298,5.48,224,0.875,bicubic
-tf_mobilenetv3_large_100,22.5707,77.4293,39.7591,60.2409,5.48,224,0.875,bilinear
-hrnet_w18_small_v2,22.3408,77.6592,39.8475,60.1525,15.6,224,0.875,bilinear
-regnety_008,22.1128,77.8872,38.8964,61.1036,6.26,224,0.875,bicubic
-seresnext26tn_32x4d,22.0028,77.9972,38.4916,61.5084,16.81,224,0.875,bicubic
-seresnext26t_32x4d,21.9871,78.0129,38.5663,61.4337,16.82,224,0.875,bicubic
-regnety_006,21.9733,78.0267,38.9534,61.0466,6.06,224,0.875,bicubic
-regnetx_008,21.9517,78.0483,38.9298,61.0702,7.26,224,0.875,bicubic
-resnet26d,21.9144,78.0856,38.6174,61.3826,16.01,224,0.875,bicubic
-semnasnet_100,21.8967,78.1033,38.6036,61.3964,3.89,224,0.875,bicubic
-regnetx_006,21.7434,78.2566,38.9043,61.0957,6.2,224,0.875,bicubic
-gluon_resnet18_v1b,21.5449,78.4551,38.8728,61.1272,11.69,224,0.875,bicubic
-fbnetc_100,21.4919,78.5081,38.1654,61.8346,5.57,224,0.875,bilinear
-mnasnet_100,21.3504,78.6496,37.7154,62.2846,4.38,224,0.875,bicubic
-resnet26,21.2954,78.7046,38.0161,61.9839,16.0,224,0.875,bicubic
-ssl_resnet18,21.2777,78.7223,39.1145,60.8855,11.69,224,0.875,bilinear
-mixnet_s,21.258,78.742,38.1929,61.8071,4.13,224,0.875,bicubic
-seresnext26d_32x4d,21.2541,78.7459,37.2851,62.7149,16.81,224,0.875,bicubic
-seresnext26_32x4d,21.093,78.907,37.6388,62.3612,16.79,224,0.875,bicubic
-regnetx_004,20.8866,79.1134,37.5484,62.4516,5.16,224,0.875,bicubic
-spnasnet_100,20.867,79.133,37.8923,62.1077,4.42,224,0.875,bilinear
-seresnet18,20.8395,79.1605,37.6447,62.3553,11.78,224,0.875,bicubic
-mobilenetv2_100,20.7609,79.2391,37.7508,62.2492,3.5,224,0.875,bicubic
-tf_mixnet_s,20.4779,79.5221,36.6268,63.3732,4.13,224,0.875,bicubic
-regnety_004,20.417,79.583,37.0296,62.9704,4.34,224,0.875,bicubic
-tf_mobilenetv3_large_075,20.3718,79.6282,36.7702,63.2298,3.99,224,0.875,bilinear
-hrnet_w18_small,20.3659,79.6341,37.0945,62.9055,13.19,224,0.875,bilinear
-resnet18,20.2283,79.7717,37.2595,62.7405,11.69,224,0.875,bilinear
-tf_mobilenetv3_large_minimal_100,20.1163,79.8837,36.9038,63.0962,3.92,224,0.875,bilinear
-regnety_002,17.4596,82.5404,32.4432,67.5568,3.16,224,0.875,bicubic
-regnetx_002,16.9506,83.0494,32.2349,67.7651,2.68,224,0.875,bicubic
-dla60x_c,16.3257,83.6743,31.775,68.225,1.34,224,0.875,bilinear
-tf_mobilenetv3_small_100,16.2334,83.7666,31.2229,68.7771,2.54,224,0.875,bilinear
-tf_mobilenetv3_small_075,14.9404,85.0596,29.5722,70.4278,2.04,224,0.875,bilinear
-dla46_c,14.6613,85.3387,29.3737,70.6263,1.31,224,0.875,bilinear
-dla46x_c,14.3803,85.6197,29.1772,70.8228,1.08,224,0.875,bilinear
-tf_mobilenetv3_small_minimal_100,13.9677,86.0323,27.9805,72.0195,2.04,224,0.875,bilinear
+model,rank_diff,top1,top1_diff,top1_err,top5,top5_diff,top5_err,param_count,img_size,cropt_pct,interpolation
+ig_resnext101_32x48d,+5,58.814,-26.628,41.186,81.086,-16.486,18.914,828.41,224,0.875,bilinear
+ig_resnext101_32x32d,+9,58.380,-26.712,41.620,80.379,-17.057,19.621,468.53,224,0.875,bilinear
+ig_resnext101_32x16d,+14,57.700,-26.476,42.300,79.913,-17.283,20.087,194.03,224,0.875,bilinear
+swsl_resnext101_32x16d,+18,57.466,-25.872,42.534,80.381,-16.471,19.619,194.03,224,0.875,bilinear
+swsl_resnext101_32x8d,+9,56.435,-27.859,43.565,78.934,-18.240,21.066,88.79,224,0.875,bilinear
+ig_resnext101_32x8d,+23,54.918,-27.770,45.082,77.545,-19.087,22.455,88.79,224,0.875,bilinear
+swsl_resnext101_32x4d,+17,53.591,-29.643,46.409,76.339,-20.417,23.661,44.18,224,0.875,bilinear
+tf_efficientnet_l2_ns_475,-6,51.487,-36.747,48.513,73.930,-24.616,26.070,480.31,475,0.936,bicubic
+swsl_resnext50_32x4d,+24,50.449,-31.731,49.551,73.358,-22.870,26.642,25.03,224,0.875,bilinear
+swsl_resnet50,+38,49.551,-31.629,50.449,72.332,-23.654,27.668,25.56,224,0.875,bilinear
+tf_efficientnet_b7_ns,-8,47.800,-39.038,52.200,69.638,-28.456,30.362,66.35,600,0.949,bicubic
+tf_efficientnet_b6_ns,-8,47.751,-38.711,52.249,69.962,-27.922,30.038,43.04,528,0.942,bicubic
+tf_efficientnet_l2_ns,-12,47.570,-40.782,52.430,70.017,-28.631,29.983,480.31,800,0.960,bicubic
+tf_efficientnet_b8_ap,-6,45.778,-39.590,54.222,67.905,-29.389,32.095,87.41,672,0.954,bicubic
+tf_efficientnet_b5_ns,-10,45.607,-40.473,54.393,67.852,-29.902,32.148,30.39,456,0.934,bicubic
+tf_efficientnet_b4_ns,-7,43.455,-41.703,56.545,65.513,-31.955,34.487,19.34,380,0.922,bicubic
+tf_efficientnet_b8,-10,42.502,-42.868,57.498,64.874,-32.518,35.126,87.41,672,0.954,bicubic
+tf_efficientnet_b7,-6,41.437,-43.495,58.563,63.027,-34.181,36.973,66.35,600,0.949,bicubic
+tf_efficientnet_b7_ap,-9,41.433,-43.685,58.567,62.876,-34.376,37.124,66.35,600,0.949,bicubic
+tf_efficientnet_b5_ap,-5,41.420,-42.834,58.580,62.082,-34.894,37.918,30.39,456,0.934,bicubic
+tf_efficientnet_b6_ap,-8,41.091,-43.695,58.909,62.359,-34.779,37.641,43.04,528,0.942,bicubic
+tf_efficientnet_b4_ap,+1,40.476,-42.772,59.524,61.713,-34.675,38.287,19.34,380,0.922,bicubic
+tf_efficientnet_b3_ns,-4,39.582,-44.472,60.418,61.463,-35.449,38.537,12.23,300,0.904,bicubic
+tf_efficientnet_b5,-3,38.328,-45.488,61.672,59.928,-36.822,40.072,30.39,456,0.934,bicubic
+tf_efficientnet_b3_ap,+13,37.061,-44.767,62.939,57.236,-38.388,42.764,12.23,300,0.904,bicubic
+resnest269e,-10,36.670,-47.516,63.330,56.810,-40.112,43.190,110.93,416,0.875,bilinear
+tf_efficientnet_b2_ns,+4,36.177,-46.203,63.823,57.555,-38.697,42.445,9.11,260,0.890,bicubic
+ecaresnet101d,+6,36.006,-46.160,63.994,56.154,-39.898,43.846,44.57,224,0.875,bicubic
+swsl_resnet18,+192,35.860,-37.426,64.140,58.437,-33.295,41.563,11.69,224,0.875,bilinear
+resnest200e,-10,35.847,-47.987,64.153,55.890,-40.948,44.110,70.20,320,0.875,bilinear
+resnest101e,-4,35.365,-47.525,64.635,55.786,-40.538,44.214,48.28,256,0.875,bilinear
+ssl_resnext101_32x16d,+5,34.609,-47.227,65.391,55.914,-40.180,44.086,194.03,224,0.875,bilinear
+resnest50d_4s2x40d,+16,34.361,-46.753,65.639,54.711,-40.857,45.289,30.42,224,0.875,bicubic
+tf_efficientnet_b1_ns,+11,34.153,-47.233,65.847,55.489,-40.249,44.511,7.79,240,0.882,bicubic
+tf_efficientnet_b4,-9,34.062,-48.954,65.938,54.216,-42.082,45.784,19.34,380,0.922,bicubic
+ssl_resnext101_32x8d,+5,34.021,-47.605,65.979,55.593,-40.445,44.407,88.79,224,0.875,bilinear
+tf_efficientnet_b6,-19,34.005,-50.107,65.995,54.540,-42.344,45.460,43.04,528,0.942,bicubic
+efficientnet_b3_pruned,+18,33.996,-46.860,66.004,54.110,-41.130,45.890,9.86,300,0.904,bicubic
+tresnet_xl,-4,33.259,-48.811,66.741,52.296,-43.632,47.704,78.44,224,0.875,bilinear
+resnest50d_1s4x24d,+11,33.139,-47.851,66.861,52.831,-42.491,47.169,25.68,224,0.875,bicubic
+resnest50d,+11,32.968,-47.990,67.032,52.701,-42.681,47.299,27.48,224,0.875,bilinear
+tf_efficientnet_b3,-2,32.864,-48.776,67.136,52.962,-42.760,47.038,12.23,300,0.904,bicubic
+inception_resnet_v2,+22,32.736,-47.724,67.264,50.640,-44.670,49.360,55.84,299,0.897,bicubic
+gluon_resnet152_v1d,+20,32.730,-47.740,67.270,51.084,-44.122,48.916,60.21,224,0.875,bicubic
+tf_efficientnet_b2_ap,+28,32.679,-47.627,67.321,52.233,-42.795,47.767,9.11,260,0.890,bicubic
+nasnetalarge,-16,32.583,-49.975,67.417,49.787,-46.249,50.213,88.75,331,0.875,bicubic
+tresnet_l,-3,32.567,-48.921,67.433,51.141,-44.487,48.859,55.99,224,0.875,bilinear
+pnasnet5large,-20,32.532,-50.208,67.468,50.188,-45.852,49.812,86.06,331,0.875,bicubic
+ens_adv_inception_resnet_v2,+34,32.370,-47.606,67.629,50.427,-44.519,49.573,55.84,299,0.897,bicubic
+gluon_resnet152_v1s,=,32.331,-48.681,67.669,50.539,-44.877,49.461,60.32,224,0.875,bicubic
+gluon_seresnext101_64x4d,+4,32.194,-48.696,67.806,50.327,-44.977,49.673,88.23,224,0.875,bicubic
+gluon_seresnext101_32x4d,+2,32.115,-48.787,67.885,51.241,-44.053,48.759,48.96,224,0.875,bicubic
+efficientnet_b3a,-17,31.728,-50.146,68.272,51.322,-44.518,48.678,12.23,320,1.000,bicubic
+efficientnet_b3,-11,31.565,-49.933,68.435,51.272,-44.446,48.728,12.23,300,0.904,bicubic
+resnet50,+64,31.545,-47.487,68.455,50.172,-44.212,49.828,25.56,224,0.875,bicubic
+ssl_resnext101_32x4d,-3,31.433,-49.495,68.567,52.115,-43.613,47.885,44.18,224,0.875,bilinear
+inception_v4,+22,31.382,-48.774,68.618,49.237,-45.737,50.763,42.68,299,0.875,bicubic
+ecaresnetlight,+8,31.133,-49.321,68.868,50.252,-45.004,49.748,30.16,224,0.875,bicubic
+gluon_resnet101_v1s,+15,31.113,-49.187,68.887,49.791,-45.359,50.209,44.67,224,0.875,bicubic
+tf_efficientnet_cc_b0_8e,+98,31.081,-46.827,68.919,50.773,-42.883,49.227,24.01,224,0.875,bicubic
+ecaresnet50d,=,31.064,-49.540,68.936,50.846,-44.476,49.154,25.58,224,0.875,bicubic
+gluon_resnet152_v1c,+23,31.007,-48.909,68.993,48.936,-45.906,51.064,60.21,224,0.875,bicubic
+tresnet_m,-4,30.993,-49.803,69.007,48.690,-46.166,51.310,31.39,224,0.875,bilinear
+gluon_resnext101_64x4d,-2,30.981,-49.621,69.019,48.553,-46.441,51.447,83.46,224,0.875,bicubic
+tf_efficientnet_cc_b1_8e,+42,30.901,-48.397,69.099,50.074,-44.290,49.926,39.72,240,0.882,bicubic
+ecaresnet101d_pruned,-8,30.895,-49.913,69.105,50.001,-45.627,49.999,24.88,224,0.875,bicubic
+gluon_resnext101_32x4d,+4,30.881,-49.453,69.119,48.537,-46.389,51.463,44.18,224,0.875,bicubic
+tf_efficientnet_lite4,-26,30.840,-50.688,69.160,50.398,-45.270,49.602,13.01,380,0.920,bilinear
+dpn107,+9,30.680,-49.484,69.320,48.806,-46.106,51.194,86.92,224,0.875,bicubic
+ese_vovnet39b,+33,30.677,-48.643,69.323,49.893,-44.817,50.107,24.57,224,0.875,bicubic
+tresnet_xl_448,-46,30.620,-52.428,69.380,49.072,-47.102,50.928,78.44,448,0.875,bilinear
+gluon_resnet152_v1b,+22,30.618,-49.074,69.382,48.529,-46.209,51.471,60.19,224,0.875,bicubic
+ssl_resnext50_32x4d,-1,30.594,-49.734,69.406,50.653,-44.751,49.347,25.03,224,0.875,bilinear
+gluon_resnet101_v1d,-6,30.509,-49.915,69.490,47.975,-47.045,52.025,44.57,224,0.875,bicubic
+resnest26d,+62,30.500,-47.982,69.500,50.677,-43.613,49.323,17.07,224,0.875,bilinear
+efficientnet_b2a,-16,30.423,-50.185,69.577,49.675,-45.635,50.325,9.11,288,1.000,bicubic
+tf_efficientnet_b1_ap,+32,30.419,-48.859,69.581,49.553,-44.755,50.447,7.79,240,0.882,bicubic
+dpn98,+18,30.058,-49.578,69.942,48.240,-46.354,51.760,61.57,224,0.875,bicubic
+tf_efficientnet_b2,+2,30.020,-50.070,69.980,49.590,-45.316,50.410,9.11,260,0.890,bicubic
+dpn131,+9,30.014,-49.814,69.986,48.144,-46.560,51.856,79.25,224,0.875,bicubic
+senet154,-35,30.001,-51.303,69.999,48.032,-47.466,51.968,115.09,224,0.875,bilinear
+dpn92,=,29.969,-50.047,70.031,49.160,-45.678,50.840,37.67,224,0.875,bicubic
+gluon_senet154,-36,29.887,-51.337,70.113,47.873,-47.483,52.127,115.09,224,0.875,bicubic
+xception,+34,29.849,-49.199,70.151,48.690,-45.702,51.310,22.86,299,0.897,bicubic
+adv_inception_v3,+80,29.824,-47.756,70.176,47.867,-45.857,52.133,23.83,299,0.875,bicubic
+resnetblur50,+22,29.623,-49.667,70.377,48.250,-46.382,51.750,25.56,224,0.875,bicubic
+efficientnet_b2,-18,29.617,-50.785,70.383,48.773,-46.303,51.227,9.11,260,0.875,bicubic
+gluon_xception65,+9,29.555,-50.049,70.445,47.523,-47.225,52.477,39.92,299,0.875,bicubic
+resnext101_32x8d,+15,29.435,-49.877,70.565,48.482,-46.044,51.518,88.79,224,0.875,bilinear
+ssl_resnet50,+20,29.423,-49.805,70.577,49.773,-45.059,50.227,25.56,224,0.875,bilinear
+resnext50_32x4d,=,29.328,-50.434,70.671,47.395,-47.205,52.605,25.03,224,0.875,bicubic
+ecaresnet50d_pruned,=,29.216,-50.502,70.784,48.458,-46.432,51.542,19.94,224,0.875,bicubic
+tresnet_l_448,-61,29.167,-53.101,70.833,47.234,-48.744,52.766,55.99,448,0.875,bilinear
+gluon_inception_v3,+32,29.114,-49.690,70.886,46.943,-47.437,53.057,23.83,299,0.875,bicubic
+hrnet_w64,+5,28.987,-50.485,71.013,47.140,-47.510,52.860,128.06,224,0.875,bilinear
+tf_efficientnet_b0_ns,+37,28.914,-49.738,71.086,49.011,-45.357,50.989,5.29,224,0.875,bicubic
+tf_efficientnet_b1,+28,28.892,-49.940,71.108,47.511,-46.685,52.489,7.79,240,0.882,bicubic
+gluon_resnet101_v1b,+8,28.857,-50.447,71.143,46.371,-48.153,53.629,44.55,224,0.875,bicubic
+skresnext50_32x4d,-19,28.818,-51.332,71.182,46.503,-48.141,53.497,27.48,224,0.875,bicubic
+tf_efficientnet_lite3,-10,28.654,-51.158,71.346,47.358,-47.556,52.642,8.20,300,0.904,bilinear
+hrnet_w40,+20,28.645,-50.289,71.355,47.443,-47.023,52.557,57.56,224,0.875,bilinear
+gluon_seresnext50_32x4d,-16,28.641,-51.271,71.359,46.450,-48.368,53.550,27.56,224,0.875,bicubic
+skresnet34,+81,28.629,-48.281,71.371,47.957,-45.359,52.043,22.28,224,0.875,bicubic
+resnet152,+40,28.535,-49.777,71.465,47.114,-46.932,52.886,60.19,224,0.875,bilinear
+hrnet_w48,=,28.407,-50.903,71.593,47.574,-46.944,52.426,77.47,224,0.875,bilinear
+gluon_resnext50_32x4d,-4,28.383,-50.973,71.617,45.326,-49.098,54.674,25.03,224,0.875,bicubic
+efficientnet_b2_pruned,-23,28.366,-51.552,71.634,47.059,-47.789,52.941,8.31,260,0.890,bicubic
+tf_efficientnet_b0_ap,+72,28.350,-48.734,71.650,47.531,-45.723,52.469,5.29,224,0.875,bicubic
+dla102x2,-8,28.319,-51.133,71.681,46.757,-47.887,53.243,41.75,224,0.875,bilinear
+dla169,+19,28.311,-50.399,71.689,47.399,-46.939,52.601,53.99,224,0.875,bilinear
+tf_efficientnet_cc_b0_4e,+62,28.311,-48.993,71.689,47.364,-45.968,52.636,13.31,224,0.875,bicubic
+mixnet_xl,-49,28.293,-52.185,71.707,46.717,-48.215,53.283,11.90,224,0.875,bicubic
+gluon_resnet50_v1d,+3,28.236,-50.838,71.764,45.876,-48.600,54.124,25.58,224,0.875,bicubic
+wide_resnet101_2,+10,28.106,-50.740,71.894,46.425,-47.859,53.575,126.89,224,0.875,bilinear
+gluon_resnet101_v1c,-16,28.102,-51.442,71.898,45.953,-48.633,54.047,44.57,224,0.875,bicubic
+densenet161,+56,28.100,-49.248,71.900,46.651,-46.997,53.349,28.68,224,0.875,bicubic
+regnetx_320,-41,28.079,-52.167,71.921,45.120,-49.902,54.880,107.81,224,0.875,bicubic
+regnety_320,-61,28.071,-52.743,71.929,45.460,-49.780,54.540,145.05,224,0.875,bicubic
+dpn68b,+48,27.884,-49.630,72.116,47.460,-46.362,52.540,12.61,224,0.875,bicubic
+regnetx_160,-32,27.825,-52.041,72.175,45.631,-49.197,54.369,54.28,224,0.875,bicubic
+tf_inception_v3,+38,27.786,-50.070,72.214,45.711,-47.933,54.289,23.83,299,0.875,bicubic
+res2net101_26w_4s,-8,27.774,-51.422,72.226,45.171,-49.269,54.829,45.21,224,0.875,bilinear
+regnety_160,-48,27.639,-52.661,72.361,45.534,-49.428,54.466,83.59,224,0.875,bicubic
+hrnet_w44,-2,27.625,-51.269,72.375,45.831,-48.539,54.169,67.06,224,0.875,bilinear
+inception_v3,+45,27.570,-49.866,72.430,45.261,-48.215,54.739,23.83,299,0.875,bicubic
+regnetx_080,-13,27.411,-51.787,72.589,45.022,-49.536,54.978,39.57,224,0.875,bicubic
+hrnet_w30,+21,27.385,-50.811,72.615,46.542,-47.678,53.458,37.71,224,0.875,bilinear
+hrnet_w32,+13,27.377,-51.071,72.623,45.990,-48.198,54.010,41.23,224,0.875,bilinear
+gluon_resnet50_v1s,-1,27.326,-51.386,72.674,45.214,-49.028,54.786,25.68,224,0.875,bicubic
+densenet201,+45,27.261,-50.029,72.739,46.224,-47.254,53.776,20.01,224,0.875,bicubic
+regnety_064,-38,27.228,-52.484,72.772,44.851,-49.923,55.149,30.58,224,0.875,bicubic
+densenetblur121d,+57,27.224,-49.352,72.776,46.307,-46.883,53.693,8.00,224,0.875,bicubic
+efficientnet_b1_pruned,+13,27.195,-51.047,72.805,45.872,-47.960,54.128,6.33,240,0.882,bicubic
+res2net50_26w_8s,-22,27.073,-52.137,72.927,44.432,-49.930,55.568,48.40,224,0.875,bilinear
+dla102x,=,27.023,-51.485,72.977,45.495,-48.739,54.505,26.77,224,0.875,bilinear
+resnet101,+35,26.968,-50.406,73.031,45.236,-48.310,54.764,44.55,224,0.875,bilinear
+resnext50d_32x4d,-42,26.874,-52.800,73.126,44.430,-50.438,55.570,25.05,224,0.875,bicubic
+regnetx_120,-40,26.864,-52.726,73.136,44.682,-50.058,55.318,46.11,224,0.875,bicubic
+seresnext101_32x4d,-62,26.819,-53.417,73.181,43.508,-51.520,56.492,48.96,224,0.875,bilinear
+densenet169,+55,26.811,-49.101,73.189,45.375,-47.649,54.625,14.15,224,0.875,bicubic
+regnetx_064,-24,26.802,-52.264,73.198,44.904,-49.552,55.096,26.21,224,0.875,bicubic
+regnety_120,-72,26.782,-53.600,73.218,44.440,-50.688,55.560,51.82,224,0.875,bicubic
+regnetx_032,+6,26.707,-51.459,73.293,45.226,-48.854,54.774,15.30,224,0.875,bicubic
+densenet121,+55,26.676,-48.898,73.324,45.900,-46.756,54.100,7.98,224,0.875,bicubic
+seresnet152,-13,26.672,-51.986,73.328,43.945,-50.429,56.055,66.82,224,0.875,bilinear
+tf_efficientnet_el,-79,26.623,-53.825,73.377,44.636,-50.524,55.364,10.59,300,0.904,bicubic
+efficientnet_es,+4,26.617,-51.437,73.383,45.106,-48.824,54.894,5.44,224,0.875,bicubic
+res2net50_26w_6s,-14,26.587,-51.987,73.413,43.978,-50.148,56.022,37.05,224,0.875,bilinear
+dla60x,-4,26.564,-51.678,73.436,45.039,-48.983,54.961,17.65,224,0.875,bilinear
+regnety_080,-63,26.515,-53.353,73.485,44.355,-50.477,55.645,39.18,224,0.875,bicubic
+tf_efficientnet_b0,+34,26.491,-50.349,73.509,45.656,-47.570,54.344,5.29,224,0.875,bicubic
+res2net50_14w_8s,-2,26.471,-51.681,73.529,44.369,-49.473,55.631,25.06,224,0.875,bilinear
+gluon_resnet50_v1b,+13,26.432,-51.146,73.568,44.033,-49.685,55.967,25.56,224,0.875,bicubic
+regnetx_040,-18,26.239,-52.247,73.760,44.424,-49.818,55.576,22.12,224,0.875,bicubic
+dpn68,+37,26.122,-50.184,73.878,44.233,-48.737,55.767,12.61,224,0.875,bicubic
+hrnet_w18,+30,25.976,-50.780,74.024,44.809,-48.633,55.191,21.30,224,0.875,bilinear
+regnety_040,-46,25.913,-53.309,74.087,43.854,-50.802,56.146,20.65,224,0.875,bicubic
+resnet34,+49,25.884,-49.228,74.116,43.990,-48.298,56.010,21.80,224,0.875,bilinear
+res2net50_26w_4s,-2,25.870,-52.076,74.130,43.161,-50.691,56.839,25.70,224,0.875,bilinear
+tresnet_m_448,-121,25.850,-55.862,74.150,42.868,-52.702,57.132,31.39,448,0.875,bilinear
+gluon_resnet50_v1c,-8,25.795,-52.215,74.205,43.017,-50.971,56.983,25.58,224,0.875,bicubic
+selecsls60,-6,25.729,-52.253,74.272,44.069,-49.763,55.931,30.67,224,0.875,bicubic
+dla60_res2net,-25,25.642,-52.830,74.358,43.589,-50.615,56.411,21.15,224,0.875,bilinear
+dla60_res2next,-24,25.638,-52.810,74.362,43.670,-50.474,56.330,17.33,224,0.875,bilinear
+tf_efficientnet_lite1,+23,25.506,-51.132,74.493,43.583,-49.649,56.417,5.42,240,0.882,bicubic
+mixnet_l,-46,25.499,-53.477,74.501,43.463,-50.721,56.537,7.33,224,0.875,bicubic
+efficientnet_b1,-37,25.483,-53.215,74.517,43.286,-50.866,56.714,7.79,240,0.875,bicubic
+tv_resnext50_32x4d,-5,25.469,-52.149,74.531,42.791,-50.907,57.209,25.03,224,0.875,bilinear
+tf_mixnet_l,-42,25.420,-53.350,74.580,42.544,-51.460,57.456,7.33,224,0.875,bicubic
+res2next50,-23,25.395,-52.847,74.606,42.492,-51.400,57.508,24.67,224,0.875,bilinear
+selecsls60b,-29,25.328,-53.090,74.672,43.554,-50.612,56.446,32.77,224,0.875,bicubic
+seresnet101,-29,25.328,-53.068,74.672,42.828,-51.430,57.172,49.33,224,0.875,bilinear
+regnety_032,-50,25.324,-53.546,74.676,42.907,-51.495,57.093,19.44,224,0.875,bicubic
+dla102,-22,25.314,-52.712,74.686,43.837,-50.113,56.163,33.73,224,0.875,bilinear
+wide_resnet50_2,-36,25.310,-53.158,74.690,42.178,-51.908,57.822,68.88,224,0.875,bilinear
+resnest14d,+25,25.282,-50.222,74.718,44.121,-48.393,55.879,10.61,224,0.875,bilinear
+seresnext50_32x4d,-62,25.218,-53.858,74.782,41.938,-52.496,58.062,27.56,224,0.875,bilinear
+res2net50_48w_2s,-10,25.023,-52.491,74.977,42.202,-51.346,57.798,25.29,224,0.875,bilinear
+efficientnet_b0,-18,25.015,-52.677,74.985,42.785,-50.747,57.215,5.29,224,0.875,bicubic
+gluon_resnet34_v1b,+35,24.948,-49.632,75.052,42.237,-49.751,57.763,21.80,224,0.875,bicubic
+mobilenetv2_120d,-7,24.933,-52.361,75.067,43.064,-50.438,56.936,5.83,224,0.875,bicubic
+dla60,-1,24.927,-52.097,75.073,43.302,-50.006,56.698,22.33,224,0.875,bilinear
+regnety_016,-23,24.819,-53.033,75.181,42.626,-51.090,57.374,11.20,224,0.875,bicubic
+tf_efficientnet_em,-53,24.534,-54.164,75.466,42.410,-51.910,57.590,6.90,240,0.882,bicubic
+tf_efficientnet_lite2,-16,24.530,-52.930,75.470,42.292,-51.454,57.708,6.09,260,0.890,bicubic
+skresnet18,+36,24.494,-48.550,75.505,42.538,-48.640,57.462,11.96,224,0.875,bicubic
+regnetx_016,-4,24.477,-52.453,75.523,42.502,-50.916,57.498,9.19,224,0.875,bicubic
+tf_efficientnet_lite0,+22,24.371,-50.471,75.629,42.510,-49.660,57.490,4.65,224,0.875,bicubic
+tv_resnet50,+4,24.092,-52.038,75.908,41.309,-51.553,58.691,25.56,224,0.875,bilinear
+seresnet34,+21,24.037,-50.771,75.963,41.895,-50.231,58.105,21.96,224,0.875,bilinear
+tv_densenet121,+21,23.846,-50.906,76.154,41.921,-50.231,58.079,7.98,224,0.875,bicubic
+tf_efficientnet_es,-16,23.824,-53.440,76.176,41.319,-52.281,58.681,5.44,224,0.875,bicubic
+mobilenetv2_140,-3,23.710,-52.814,76.290,41.469,-51.521,58.531,6.11,224,0.875,bicubic
+mixnet_m,-17,23.709,-53.547,76.291,41.139,-52.279,58.861,5.01,224,0.875,bicubic
+dla34,+19,23.677,-50.959,76.323,41.543,-50.521,58.457,15.78,224,0.875,bilinear
+seresnet50,-34,23.644,-53.992,76.356,40.081,-53.671,59.919,28.09,224,0.875,bilinear
+tf_mixnet_m,-15,23.479,-53.471,76.521,41.005,-52.151,58.995,5.01,224,0.875,bicubic
+tv_resnet34,+22,23.473,-49.841,76.527,41.367,-50.053,58.633,21.80,224,0.875,bilinear
+selecsls42b,-21,23.366,-53.810,76.633,40.677,-52.715,59.323,32.46,224,0.875,bicubic
+mobilenetv2_110d,+8,23.070,-51.982,76.930,40.744,-51.436,59.256,4.52,224,0.875,bicubic
+mobilenetv3_large_100,-5,22.665,-53.103,77.335,40.785,-51.755,59.215,5.48,224,0.875,bicubic
+mobilenetv3_rw,-4,22.626,-53.002,77.374,40.370,-52.340,59.630,5.48,224,0.875,bicubic
+tf_mobilenetv3_large_100,-3,22.571,-52.945,77.429,39.759,-52.841,60.241,5.48,224,0.875,bilinear
+hrnet_w18_small_v2,+1,22.341,-52.785,77.659,39.847,-52.569,60.153,15.60,224,0.875,bilinear
+regnety_008,-14,22.113,-54.201,77.887,38.896,-54.166,61.104,6.26,224,0.875,bicubic
+seresnext26tn_32x4d,-52,22.003,-55.987,77.997,38.492,-55.256,61.508,16.81,224,0.875,bicubic
+seresnext26t_32x4d,-52,21.987,-56.001,78.013,38.566,-55.140,61.434,16.82,224,0.875,bicubic
+regnety_006,-4,21.973,-53.287,78.027,38.953,-53.575,61.047,6.06,224,0.875,bicubic
+regnetx_008,=,21.952,-53.070,78.048,38.930,-53.414,61.070,7.26,224,0.875,bicubic
+resnet26d,-23,21.914,-54.766,78.086,38.617,-54.549,61.383,16.01,224,0.875,bicubic
+semnasnet_100,-9,21.897,-53.559,78.103,38.604,-53.988,61.396,3.89,224,0.875,bicubic
+regnetx_006,+6,21.743,-52.119,78.257,38.904,-52.776,61.096,6.20,224,0.875,bicubic
+gluon_resnet18_v1b,+16,21.545,-49.285,78.455,38.873,-50.883,61.127,11.69,224,0.875,bicubic
+fbnetc_100,-8,21.492,-53.628,78.508,38.165,-54.221,61.835,5.57,224,0.875,bilinear
+mnasnet_100,-2,21.350,-53.306,78.650,37.715,-54.411,62.285,4.38,224,0.875,bicubic
+resnet26,-13,21.295,-53.997,78.705,38.016,-54.554,61.984,16.00,224,0.875,bicubic
+ssl_resnet18,+7,21.278,-51.322,78.722,39.114,-52.302,60.886,11.69,224,0.875,bilinear
+mixnet_s,-24,21.258,-54.730,78.742,38.193,-54.601,61.807,4.13,224,0.875,bicubic
+seresnext26d_32x4d,-55,21.254,-56.350,78.746,37.285,-56.327,62.715,16.81,224,0.875,bicubic
+seresnext26_32x4d,-41,21.093,-56.007,78.907,37.639,-55.671,62.361,16.79,224,0.875,bicubic
+regnetx_004,+4,20.887,-51.519,79.113,37.548,-53.282,62.452,5.16,224,0.875,bicubic
+spnasnet_100,-6,20.867,-53.213,79.133,37.892,-53.940,62.108,4.42,224,0.875,bilinear
+seresnet18,+5,20.840,-50.918,79.160,37.645,-52.689,62.355,11.78,224,0.875,bicubic
+mobilenetv2_100,-1,20.761,-52.217,79.239,37.751,-53.265,62.249,3.50,224,0.875,bicubic
+tf_mixnet_s,-28,20.478,-55.170,79.522,36.627,-56.009,63.373,4.13,224,0.875,bicubic
+regnety_004,-9,20.417,-53.609,79.583,37.030,-54.718,62.970,4.34,224,0.875,bicubic
+tf_mobilenetv3_large_075,-8,20.372,-53.070,79.628,36.770,-54.582,63.230,3.99,224,0.875,bilinear
+hrnet_w18_small,-2,20.366,-51.976,79.634,37.094,-53.578,62.906,13.19,224,0.875,bilinear
+resnet18,+2,20.228,-49.530,79.772,37.260,-51.818,62.740,11.69,224,0.875,bilinear
+tf_mobilenetv3_large_minimal_100,-3,20.116,-52.128,79.884,36.904,-53.732,63.096,3.92,224,0.875,bilinear
+regnety_002,-1,17.460,-52.822,82.540,32.443,-57.097,67.557,3.16,224,0.875,bicubic
+regnetx_002,=,16.951,-51.803,83.049,32.235,-56.313,67.765,2.68,224,0.875,bicubic
+dla60x_c,+1,16.326,-51.582,83.674,31.775,-56.659,68.225,1.34,224,0.875,bilinear
+tf_mobilenetv3_small_100,-1,16.233,-51.685,83.767,31.223,-56.439,68.777,2.54,224,0.875,bilinear
+tf_mobilenetv3_small_075,+1,14.940,-50.778,85.060,29.572,-56.564,70.428,2.04,224,0.875,bilinear
+dla46_c,+1,14.661,-50.217,85.339,29.374,-56.912,70.626,1.31,224,0.875,bilinear
+dla46x_c,-2,14.380,-51.600,85.620,29.177,-57.803,70.823,1.08,224,0.875,bilinear
+tf_mobilenetv3_small_minimal_100,=,13.968,-48.930,86.032,27.980,-56.250,72.019,2.04,224,0.875,bilinear
--- a/setup.py
+++ b/setup.py
@ -40,7 +40,7 @@ setup(

    # Note that this is a string of words separated by whitespace, not a list.
    keywords='pytorch pretrained models efficientnet mobilenetv3 mnasnet',
-    packages=find_packages(exclude=['convert', 'tests']),
+    packages=find_packages(exclude=['convert', 'tests', 'results']),
    include_package_data=True,
    install_requires=['torch >= 1.0', 'torchvision'],
    python_requires='>=3.6',
--- a/timm/models/resnest.py
+++ b/timm/models/resnest.py
@ -32,21 +32,21 @@ default_cfgs = {
    'resnest26d': _cfg(
        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/gluon_resnest26-50eb607c.pth'),
    'resnest50d': _cfg(
-        url='https://hangzh.s3.amazonaws.com/encoding/models/resnest50-528c19ca.pth'),
+        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-resnest/resnest50-528c19ca.pth'),
    'resnest101e': _cfg(
-        url='https://hangzh.s3.amazonaws.com/encoding/models/resnest101-22405ba7.pth',
+        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-resnest/resnest101-22405ba7.pth',
        input_size=(3, 256, 256), pool_size=(8, 8)),
    'resnest200e': _cfg(
-        url='https://hangzh.s3.amazonaws.com/encoding/models/resnest200-75117900.pth',
+        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-resnest/resnest200-75117900.pth',
        input_size=(3, 320, 320), pool_size=(10, 10), crop_pct=0.909, interpolation='bicubic'),
    'resnest269e': _cfg(
-        url='https://hangzh.s3.amazonaws.com/encoding/models/resnest269-0cc87c48.pth',
+        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-resnest/resnest269-0cc87c48.pth',
        input_size=(3, 416, 416), pool_size=(13, 13), crop_pct=0.928, interpolation='bicubic'),
    'resnest50d_4s2x40d': _cfg(
-        url='https://hangzh.s3.amazonaws.com/encoding/models/resnest50_fast_4s2x40d-41d14ed0.pth',
+        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-resnest/resnest50_fast_4s2x40d-41d14ed0.pth',
        interpolation='bicubic'),
    'resnest50d_1s4x24d': _cfg(
-        url='https://hangzh.s3.amazonaws.com/encoding/models/resnest50_fast_1s4x24d-d4a4f76f.pth',
+        url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-resnest/resnest50_fast_1s4x24d-d4a4f76f.pth',
        interpolation='bicubic')
 }

--- a/timm/scheduler/cosine_lr.py
+++ b/timm/scheduler/cosine_lr.py
@ -103,7 +103,7 @@ class CosineLRScheduler(Scheduler):
    def get_cycle_length(self, cycles=0):
        if not cycles:
            cycles = self.cycle_limit
-        assert cycles > 0
+        cycles = max(1, cycles)
        if self.t_mul == 1.0:
            return self.t_initial * cycles
        else:
--- a/timm/scheduler/scheduler_factory.py
+++ b/timm/scheduler/scheduler_factory.py
@ -28,7 +28,7 @@ def create_scheduler(args, optimizer):
            decay_rate=args.decay_rate,
            warmup_lr_init=args.warmup_lr,
            warmup_t=args.warmup_epochs,
-            cycle_limit=getattr(args, 'lr_cycle_limit', 0),
+            cycle_limit=getattr(args, 'lr_cycle_limit', 1),
            t_in_epochs=True,
            noise_range_t=noise_range,
            noise_pct=getattr(args, 'lr_noise_pct', 0.67),
@ -44,7 +44,7 @@ def create_scheduler(args, optimizer):
            lr_min=args.min_lr,
            warmup_lr_init=args.warmup_lr,
            warmup_t=args.warmup_epochs,
-            cycle_limit=getattr(args, 'lr_cycle_limit', 0),
+            cycle_limit=getattr(args, 'lr_cycle_limit', 1),
            t_in_epochs=True,
            noise_range_t=noise_range,
            noise_pct=getattr(args, 'lr_noise_pct', 0.67),
--- a/timm/scheduler/tanh_lr.py
+++ b/timm/scheduler/tanh_lr.py
@ -107,7 +107,7 @@ class TanhLRScheduler(Scheduler):
    def get_cycle_length(self, cycles=0):
        if not cycles:
            cycles = self.cycle_limit
-        assert cycles > 0
+        cycles = max(1, cycles)
        if self.t_mul == 1.0:
            return self.t_initial * cycles
        else: