Migrations
/
pytorch-image-models
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md and docs in prep for 0.3.0 PyPi release.

Browse Source
pull/268/head
Ross Wightman 4 years ago
parent af3299ba4a
commit 46f15443be
6 changed files with 76 additions and 151 deletions
Show Stats Download Patch File Download Diff File

9
README.md
Unescape View File

@ -2,6 +2,13 @@
## What's New ## What's New
### Oct 30, 2020
* Test with PyTorch 1.7 and fix a small top-n metric view vs reshape issue.
* Convert newly added 224x224 Vision Transformer weights from official JAX repo. 81.8 top-1 for B/16, 83.1 L/16.
* Support PyTorch 1.7 optimized, native SiLU (aka Swish) activation. Add mapping to 'silu' name, custom swish will eventually be deprecated.
* Fix regression for loading pretrained classifier via direct model entrypoint functions. Didn't impact create_model() factory usage.
* PyPi release @ 0.3.0 version!
### Oct 26, 2020 ### Oct 26, 2020
* Update Vision Transformer models to be compatible with official code release at https://github.com/google-research/vision_transformer * Update Vision Transformer models to be compatible with official code release at https://github.com/google-research/vision_transformer
* Add Vision Transformer weights (ImageNet-21k pretrain) for 384x384 base and large models converted from official jax impl * Add Vision Transformer weights (ImageNet-21k pretrain) for 384x384 base and large models converted from official jax impl
@ -141,7 +148,7 @@ A full version of the list below with source links can be found in the [document
* SelecSLS - https://arxiv.org/abs/1907.00837 * SelecSLS - https://arxiv.org/abs/1907.00837
* Selective Kernel Networks - https://arxiv.org/abs/1903.06586 * Selective Kernel Networks - https://arxiv.org/abs/1903.06586
* TResNet - https://arxiv.org/abs/2003.13630 * TResNet - https://arxiv.org/abs/2003.13630
* Vision Transformer - https://openreview.net/forum?id=YicbFdNTTy * Vision Transformer - https://arxiv.org/abs/2010.11929
* VovNet V2 and V1 - https://arxiv.org/abs/1911.06667 * VovNet V2 and V1 - https://arxiv.org/abs/1911.06667
* Xception - https://arxiv.org/abs/1610.02357 * Xception - https://arxiv.org/abs/1610.02357
* Xception (Modified Aligned, Gluon) - https://arxiv.org/abs/1802.02611 * Xception (Modified Aligned, Gluon) - https://arxiv.org/abs/1802.02611

11
docs/archived_changes.md
Unescape View File

@ -1,5 +1,16 @@
# Archived Changes # Archived Changes
### 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 ### Feb 29, 2020
* New MobileNet-V3 Large weights trained from stratch with this code to 75.77% top-1 * 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 * IMPORTANT CHANGE - default weight init changed for all MobilenetV3 / EfficientNet / related models

46
docs/changes.md
Unescape View File

@ -1,5 +1,40 @@
# Recent Changes # Recent Changes
### Oct 30, 2020
* Test with PyTorch 1.7 and fix a small top-n metric view vs reshape issue.
* Convert newly added 224x224 Vision Transformer weights from official JAX repo. 81.8 top-1 for B/16, 83.1 L/16.
* Support PyTorch 1.7 optimized, native SiLU (aka Swish) activation. Add mapping to 'silu' name, custom swish will eventually be deprecated.
* Fix regression for loading pretrained classifier via direct model entrypoint functions. Didn't impact create_model() factory usage.
* PyPi release @ 0.3.0 version!
### Oct 26, 2020
* Update Vision Transformer models to be compatible with official code release at https://github.com/google-research/vision_transformer
* Add Vision Transformer weights (ImageNet-21k pretrain) for 384x384 base and large models converted from official jax impl
* ViT-B/16 - 84.2
* ViT-B/32 - 81.7
* ViT-L/16 - 85.2
* ViT-L/32 - 81.5
### Oct 21, 2020
* Weights added for Vision Transformer (ViT) models. 77.86 top-1 for 'small' and 79.35 for 'base'. Thanks to [Christof](https://www.kaggle.com/christofhenkel) for training the base model w/ lots of GPUs.
### Oct 13, 2020
* Initial impl of Vision Transformer models. Both patch and hybrid (CNN backbone) variants. Currently trying to train...
* Adafactor and AdaHessian (FP32 only, no AMP) optimizers
* EdgeTPU-M (`efficientnet_em`) model trained in PyTorch, 79.3 top-1
* Pip release, doc updates pending a few more changes...
### Sept 18, 2020
* New ResNet 'D' weights. 72.7 (top-1) ResNet-18-D, 77.1 ResNet-34-D, 80.5 ResNet-50-D
* Added a few untrained defs for other ResNet models (66D, 101D, 152D, 200/200D)
### Sept 3, 2020
* New weights
* Wide-ResNet50 - 81.5 top-1 (vs 78.5 torchvision)
* SEResNeXt50-32x4d - 81.3 top-1 (vs 79.1 cadene)
* Support for native Torch AMP and channels_last memory format added to train/validate scripts (`--channels-last`, `--native-amp` vs `--apex-amp`)
* Models tested with channels_last on latest NGC 20.08 container. AdaptiveAvgPool in attn layers changed to mean((2,3)) to work around bug with NHWC kernel.
### Aug 12, 2020 ### Aug 12, 2020
* New/updated weights from training experiments * New/updated weights from training experiments
* EfficientNet-B3 - 82.1 top-1 (vs 81.6 for official with AA and 81.9 for AdvProp) * EfficientNet-B3 - 82.1 top-1 (vs 81.6 for official with AA and 81.9 for AdvProp)
@ -54,14 +89,3 @@ Bunch of changes:
* TResNet models and SpaceToDepth, AntiAliasDownsampleLayer layers by [mrT23](https://github.com/mrT23) * 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) * 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 * 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)

4
docs/index.md
Unescape View File

@ -13,13 +13,13 @@ pip install timm
Little to no care has been taken to be Python 2.x friendly and will not support it. If you run into any challenges running on Windows, or other OS, I'm definitely open to looking into those issues so long as it's in a reproducible (read Conda) environment. Little to no care has been taken to be Python 2.x friendly and will not support it. If you run into any challenges running on Windows, or other OS, I'm definitely open to looking into those issues so long as it's in a reproducible (read Conda) environment.
PyTorch versions 1.4, 1.5.x, and 1.6 have been tested with this code. PyTorch versions 1.4, 1.5.x, 1.6, and 1.7 have been tested with this code.
I've tried to keep the dependencies minimal, the setup is as per the PyTorch default install instructions for Conda: I've tried to keep the dependencies minimal, the setup is as per the PyTorch default install instructions for Conda:
``` ```
conda create -n torch-env conda create -n torch-env
conda activate torch-env conda activate torch-env
conda install -c pytorch pytorch torchvision cudatoolkit=10.2 conda install -c pytorch pytorch torchvision cudatoolkit=11
conda install pyyaml conda install pyyaml
``` ```

4
docs/models.md
Unescape View File

@ -132,6 +132,10 @@ NOTE: I am deprecating this version of the networks, the new ones are part of `r
* Paper: `TResNet: High Performance GPU-Dedicated Architecture` - https://arxiv.org/abs/2003.13630 * Paper: `TResNet: High Performance GPU-Dedicated Architecture` - https://arxiv.org/abs/2003.13630
* Code: https://github.com/mrT23/TResNet * Code: https://github.com/mrT23/TResNet
## Vision Transformer [[vision_transformer.py](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py)]
* Paper: `An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale` - https://arxiv.org/abs/2010.11929
* Reference code and pretrained weights: https://github.com/google-research/vision_transformer
## VovNet V2 and V1 [[vovnet.py](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vovnet.py)] ## VovNet V2 and V1 [[vovnet.py](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vovnet.py)]
* Paper: `CenterMask : Real-Time Anchor-Free Instance Segmentation` - https://arxiv.org/abs/1911.06667 * Paper: `CenterMask : Real-Time Anchor-Free Instance Segmentation` - https://arxiv.org/abs/1911.06667
* Reference code: https://github.com/youngwanLEE/vovnet-detectron2 * Reference code: https://github.com/youngwanLEE/vovnet-detectron2

153
docs/results.md
Unescape View File

@ -1,23 +1,31 @@
# Results # Results
CSV files containing an ImageNet-1K validation and OOD test set validation results for all included models with pretrained weights and default configurations is located [here](https://github.com/rwightman/pytorch-image-models/tree/master/results). CSV files containing an ImageNet-1K validation and out-of-distribution (OOD) test set validation results for all included models with pretrained weights and default configurations is located [here](https://github.com/rwightman/pytorch-image-models/tree/master/results).
## Self-trained Weights ## Self-trained Weights
I've leveraged the training scripts in this repository to train a few of the models with to good levels of performance. I've leveraged the training scripts in this repository to train a few of the models with to good levels of performance.
|Model | Acc@1 (Err) | Acc@5 (Err) | Param # (M) | Interpolation | Image Size | |Model | Acc@1 (Err) | Acc@5 (Err) | Param # (M) | Interpolation | Image Size |
|---|---|---|---|---|---| |---|---|---|---|---|---|
| efficientnet_b3a | 81.874 (18.126) | 95.840 (4.160) | 12.23 | bicubic | 320 (1.0 crop) | | efficientnet_b3a | 82.242 (17.758) | 96.114 (3.886) | 12.23 | bicubic | 320 (1.0 crop) |
| efficientnet_b3 | 81.498 (18.502) | 95.718 (4.282) | 12.23 | bicubic | 300 | | efficientnet_b3 | 82.076 (17.924) | 96.020 (3.980) | 12.23 | bicubic | 300 |
| regnet_32 | 82.002 (17.998) | 95.906 (4.094) | 19.44 | bicubic | 224 |
| skresnext50d_32x4d | 81.278 (18.722) | 95.366 (4.634) | 27.5 | bicubic | 288 (1.0 crop) | | skresnext50d_32x4d | 81.278 (18.722) | 95.366 (4.634) | 27.5 | bicubic | 288 (1.0 crop) |
| seresnext50d_32x4d | 81.266 (18.734) | 95.620 (4.380) | 27.6 | bicubic | 224 |
| efficientnet_b2a | 80.608 (19.392) | 95.310 (4.690) | 9.11 | bicubic | 288 (1.0 crop) | | efficientnet_b2a | 80.608 (19.392) | 95.310 (4.690) | 9.11 | bicubic | 288 (1.0 crop) |
| resnet50d | 80.530 (19.470) | 95.160 (4.840) | 25.6 | bicubic | 224 |
| mixnet_xl | 80.478 (19.522) | 94.932 (5.068) | 11.90 | bicubic | 224 | | mixnet_xl | 80.478 (19.522) | 94.932 (5.068) | 11.90 | bicubic | 224 |
| efficientnet_b2 | 80.402 (19.598) | 95.076 (4.924) | 9.11 | bicubic | 260 | | efficientnet_b2 | 80.402 (19.598) | 95.076 (4.924) | 9.11 | bicubic | 260 |
| seresnet50 | 80.274 (19.726) | 95.070 (4.930) | 28.1 | bicubic | 224 |
| skresnext50d_32x4d | 80.156 (19.844) | 94.642 (5.358) | 27.5 | bicubic | 224 | | skresnext50d_32x4d | 80.156 (19.844) | 94.642 (5.358) | 27.5 | bicubic | 224 |
| cspdarknet53 | 80.058 (19.942) | 95.084 (4.916) | 27.6 | bicubic | 256 |
| cspresnext50 | 80.040 (19.960) | 94.944 (5.056) | 20.6 | bicubic | 224 |
| resnext50_32x4d | 79.762 (20.238) | 94.600 (5.400) | 25 | bicubic | 224 | | resnext50_32x4d | 79.762 (20.238) | 94.600 (5.400) | 25 | bicubic | 224 |
| resnext50d_32x4d | 79.674 (20.326) | 94.868 (5.132) | 25.1 | bicubic | 224 | | resnext50d_32x4d | 79.674 (20.326) | 94.868 (5.132) | 25.1 | bicubic | 224 |
| cspresnet50 | 79.574 (20.426) | 94.712 (5.288) | 21.6 | bicubic | 256 |
| ese_vovnet39b | 79.320 (20.680) | 94.710 (5.290) | 24.6 | bicubic | 224 | | ese_vovnet39b | 79.320 (20.680) | 94.710 (5.290) | 24.6 | bicubic | 224 |
| resnetblur50 | 79.290 (20.710) | 94.632 (5.368) | 25.6 | bicubic | 224 | | resnetblur50 | 79.290 (20.710) | 94.632 (5.368) | 25.6 | bicubic | 224 |
| dpn68b | 79.216 (20.784) | 94.414 (5.586) | 12.6 | bicubic | 224 |
| resnet50 | 79.038 (20.962) | 94.390 (5.610) | 25.6 | bicubic | 224 | | resnet50 | 79.038 (20.962) | 94.390 (5.610) | 25.6 | bicubic | 224 |
| mixnet_l | 78.976 (21.024 | 94.184 (5.816) | 7.33 | bicubic | 224 | | mixnet_l | 78.976 (21.024 | 94.184 (5.816) | 7.33 | bicubic | 224 |
| efficientnet_b1 | 78.692 (21.308) | 94.086 (5.914) | 7.79 | bicubic | 240 | | efficientnet_b1 | 78.692 (21.308) | 94.086 (5.914) | 7.79 | bicubic | 240 |
@ -28,6 +36,7 @@ I've leveraged the training scripts in this repository to train a few of the mod
| seresnext26d_32x4d | 77.602 (22.398) | 93.608 (6.392) | 16.8 | bicubic | 224 | | seresnext26d_32x4d | 77.602 (22.398) | 93.608 (6.392) | 16.8 | bicubic | 224 |
| mobilenetv2_120d | 77.294 (22.706 | 93.502 (6.498) | 5.8 | bicubic | 224 | | mobilenetv2_120d | 77.294 (22.706 | 93.502 (6.498) | 5.8 | bicubic | 224 |
| mixnet_m | 77.256 (22.744) | 93.418 (6.582) | 5.01 | bicubic | 224 | | mixnet_m | 77.256 (22.744) | 93.418 (6.582) | 5.01 | bicubic | 224 |
| resnet34d | 77.116 (22.884) | 93.382 (6.618) | 21.8 | bicubic | 224 |
| seresnext26_32x4d | 77.104 (22.896) | 93.316 (6.684) | 16.8 | bicubic | 224 | | seresnext26_32x4d | 77.104 (22.896) | 93.316 (6.684) | 16.8 | bicubic | 224 |
| skresnet34 | 76.912 (23.088) | 93.322 (6.678) | 22.2 | bicubic | 224 | | skresnet34 | 76.912 (23.088) | 93.322 (6.678) | 22.2 | bicubic | 224 |
| ese_vovnet19b_dw | 76.798 (23.202) | 93.268 (6.732) | 6.5 | bicubic | 224 | | ese_vovnet19b_dw | 76.798 (23.202) | 93.268 (6.732) | 6.5 | bicubic | 224 |
@ -47,141 +56,11 @@ I've leveraged the training scripts in this repository to train a few of the mod
| spnasnet_100 | 74.084 (25.916) | 91.818 (8.182) | 4.42 | bilinear | 224 | | spnasnet_100 | 74.084 (25.916) | 91.818 (8.182) | 4.42 | bilinear | 224 |
| skresnet18 | 73.038 (26.962) | 91.168 (8.832) | 11.9 | bicubic | 224 | | skresnet18 | 73.038 (26.962) | 91.168 (8.832) | 11.9 | bicubic | 224 |
| mobilenetv2_100 | 72.978 (27.022) | 91.016 (8.984) | 3.5 | bicubic | 224 | | mobilenetv2_100 | 72.978 (27.022) | 91.016 (8.984) | 3.5 | bicubic | 224 |
| resnet18d | 72.260 (27.740) | 90.696 (9.304) | 11.7 | bicubic | 224 |
| seresnet18 | 71.742 (28.258) | 90.334 (9.666) | 11.8 | bicubic | 224 | | seresnet18 | 71.742 (28.258) | 90.334 (9.666) | 11.8 | bicubic | 224 |
## Ported Weights ## Ported and Other 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 | Acc@1 (Err) | Acc@5 (Err) | Param # (M) | Interpolation | Image Size | For weights ported from other deep learning frameworks (Tensorflow, MXNet GluonCV) or copied from other PyTorch sources, please see the full results tables for ImageNet and various OOD test sets at in the [results tables](https://github.com/rwightman/pytorch-image-models/tree/master/results).
|---|---|---|---|---|---|
| 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 |
Models with `*tfp` next to them were scored with `--tf-preprocessing` flag.
The `tf_efficientnet`, `tf_mixnet` models require an equivalent for 'SAME' padding as their arch results in asymmetric padding. I've added this in the model creation wrapper, but it does come with a performance penalty.
Sources for original weights: Model code .py files contain links to original sources of models and weights.
* `tf_efficientnet*`: [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet)
* `tf_efficientnet_e*`: [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/edgetpu)
* `tf_mixnet*`: [Tensorflow TPU](https://github.com/tensorflow/tpu/tree/master/models/official/mnasnet/mixnet)
* `tf_inception*`: [Tensorflow Slim](https://github.com/tensorflow/models/tree/master/research/slim)
* `gluon_*`: [MxNet Gluon](https://gluon-cv.mxnet.io/model_zoo/classification.html)

Write Preview
Loading…
Cancel
Save