From 57510fd5b23f3ab8777a625d43c50c7dd819551c Mon Sep 17 00:00:00 2001 From: Ross Wightman Date: Wed, 5 Aug 2020 17:26:55 -0700 Subject: [PATCH] Fix some documentation rendering issues --- docs/changes.md | 5 ++++- docs/models.md | 52 +++++++++++++++++++++++-------------------- mkdocs.yml | 1 + requirements-docs.txt | 3 ++- 4 files changed, 35 insertions(+), 26 deletions(-) diff --git a/docs/changes.md b/docs/changes.md index 2e63fe23..0b5c3752 100644 --- a/docs/changes.md +++ b/docs/changes.md @@ -1,7 +1,8 @@ # Recent Changes -### Aug 1, 2020 +### Aug 5, 2020 Universal feature extraction, new models, new weights, new test sets. + * All models support the `features_only=True` argument for `create_model` call to return a network that extracts features from the deepest layer at each stride. * New models * CSPResNet, CSPResNeXt, CSPDarkNet, DarkNet @@ -14,6 +15,8 @@ Universal feature extraction, new models, new weights, new test sets. * DPN68b - 79.2 top-1 * EfficientNet-Lite0 (non-TF ver) - 75.5 (submitted by @hal-314) * Add 'real' labels for ImageNet and ImageNet-Renditions test set, see [`results/README.md`](results/README.md) +* Train script and loader/transform tweaks to punch through more aug arguments +* README and documentation overhaul. See initial (WIP) documentation at https://rwightman.github.io/pytorch-image-models/ ### June 11, 2020 Bunch of changes: diff --git a/docs/models.md b/docs/models.md index a0268138..000d1c18 100644 --- a/docs/models.md +++ b/docs/models.md @@ -3,6 +3,7 @@ The model architectures included come from a wide variety of sources. Sources, including papers, original impl ("reference code") that I rewrote / adapted, and PyTorch impl that I leveraged directly ("code") are listed below. Most included models have pretrained weights. The weights are either: + 1. from their original sources 2. ported by myself from their original impl in a different framework (e.g. Tensorflow models) 3. trained from scratch using the included training script @@ -55,16 +56,17 @@ The validation results for the pretrained weights can be found [here](results.md * Reference code: https://github.com/tensorflow/models/tree/master/research/slim/nets/nasnet ## EfficientNet [[efficientnet.py](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/efficientnet.py)] -* Papers - * 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 + +* Papers: + * 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 * My PyTorch code: https://github.com/rwightman/gen-efficientnet-pytorch * Reference code: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet @@ -77,27 +79,28 @@ The validation results for the pretrained weights can be found [here](results.md * Reference code: https://github.com/facebookresearch/pycls/blob/master/pycls/models/regnet.py ## ResNet, ResNeXt [[resnet.py](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/resnet.py)] + * ResNet (V1B) - * Paper: `Deep Residual Learning for Image Recognition` - https://arxiv.org/abs/1512.03385 - * Code: https://github.com/pytorch/vision/tree/master/torchvision/models + * Paper: `Deep Residual Learning for Image Recognition` - https://arxiv.org/abs/1512.03385 + * Code: https://github.com/pytorch/vision/tree/master/torchvision/models * ResNeXt - * Paper: `Aggregated Residual Transformations for Deep Neural Networks` - https://arxiv.org/abs/1611.05431 - * Code: https://github.com/pytorch/vision/tree/master/torchvision/models + * Paper: `Aggregated Residual Transformations for Deep Neural Networks` - https://arxiv.org/abs/1611.05431 + * Code: https://github.com/pytorch/vision/tree/master/torchvision/models * 'Bag of Tricks' / Gluon C, D, E, S ResNet variants - * Paper: `Bag of Tricks for Image Classification with CNNs` - https://arxiv.org/abs/1812.01187 - * Code: https://github.com/dmlc/gluon-cv/blob/master/gluoncv/model_zoo/resnetv1b.py + * Paper: `Bag of Tricks for Image Classification with CNNs` - https://arxiv.org/abs/1812.01187 + * Code: https://github.com/dmlc/gluon-cv/blob/master/gluoncv/model_zoo/resnetv1b.py * Instagram pretrained / ImageNet tuned ResNeXt101 - * Paper: `Exploring the Limits of Weakly Supervised Pretraining` - https://arxiv.org/abs/1805.00932 - * Weights: https://pytorch.org/hub/facebookresearch_WSL-Images_resnext (NOTE: CC BY-NC 4.0 License, NOT commercial friendly) + * Paper: `Exploring the Limits of Weakly Supervised Pretraining` - https://arxiv.org/abs/1805.00932 + * Weights: https://pytorch.org/hub/facebookresearch_WSL-Images_resnext (NOTE: CC BY-NC 4.0 License, NOT commercial friendly) * Semi-supervised (SSL) / Semi-weakly Supervised (SWSL) ResNet and ResNeXts - * Paper: `Billion-scale semi-supervised learning for image classification` - https://arxiv.org/abs/1905.00546 - * Weights: https://github.com/facebookresearch/semi-supervised-ImageNet1K-models (NOTE: CC BY-NC 4.0 License, NOT commercial friendly) + * Paper: `Billion-scale semi-supervised learning for image classification` - https://arxiv.org/abs/1905.00546 + * Weights: https://github.com/facebookresearch/semi-supervised-ImageNet1K-models (NOTE: CC BY-NC 4.0 License, NOT commercial friendly) * Squeeze-and-Excitation Networks - * Paper: `Squeeze-and-Excitation Networks` - https://arxiv.org/abs/1709.01507 - * Code: Added to ResNet base, this is current version going forward, old `senet.py` is being deprecated + * Paper: `Squeeze-and-Excitation Networks` - https://arxiv.org/abs/1709.01507 + * Code: Added to ResNet base, this is current version going forward, old `senet.py` is being deprecated * ECAResNet (ECA-Net) - * Paper: `ECA-Net: Efficient Channel Attention for Deep CNN` - https://arxiv.org/abs/1910.03151v4 - * Code: Added to ResNet base, ECA module contributed by @VRandme, reference https://github.com/BangguWu/ECANet + * Paper: `ECA-Net: Efficient Channel Attention for Deep CNN` - https://arxiv.org/abs/1910.03151v4 + * Code: Added to ResNet base, ECA module contributed by @VRandme, reference https://github.com/BangguWu/ECANet ## Res2Net [[res2net.py](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/res2net.py)] * Paper: `Res2Net: A New Multi-scale Backbone Architecture` - https://arxiv.org/abs/1904.01169 @@ -121,6 +124,7 @@ The validation results for the pretrained weights can be found [here](results.md ## Squeeze-and-Excitation Networks [[senet.py](https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/senet.py)] NOTE: I am deprecating this version of the networks, the new ones are part of `resnet.py` + * Paper: `Squeeze-and-Excitation Networks` - https://arxiv.org/abs/1709.01507 * Code: https://github.com/Cadene/pretrained-models.pytorch diff --git a/mkdocs.yml b/mkdocs.yml index f6473342..86a9b679 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -39,3 +39,4 @@ markdown_extensions: - pymdownx.tasklist: custom_checkbox: true - pymdownx.tilde + - mdx_truly_sane_lists diff --git a/requirements-docs.txt b/requirements-docs.txt index fbac998b..40d3e9bd 100644 --- a/requirements-docs.txt +++ b/requirements-docs.txt @@ -1,2 +1,3 @@ mkdocs==1.1.2 -mkdocs-material==5.4.0 \ No newline at end of file +mkdocs-material==5.4.0 +mdx_truly_sane_lists \ No newline at end of file