Awesome

PytorchInsight

This is a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results.

This repository aims to accelarate the advance of Deep Learning Research, make reproducible results and easier for doing researches, and in Pytorch.

Including Papers (to be updated):

Attention Models

• SENet: Squeeze-and-excitation Networks _(paper)
• SKNet: Selective Kernel Networks _(paper)
• CBAM: Convolutional Block Attention Module _(paper)
• GCNet: GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond _(paper)
• BAM: Bottleneck Attention Module _(paper)
• SGENet: Spatial Group-wise Enhance: Enhancing Semantic Feature Learning in Convolutional Networks _(paper)
• SRMNet: SRM: A Style-based Recalibration Module for Convolutional Neural Networks _(paper)

Non-Attention Models

• OctNet: Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution _(paper)
• imagenet_tricks.py: Bag of Tricks for Image Classification with Convolutional Neural Networks _(paper)
• Understanding the Disharmony between Weight Normalization Family and Weight Decay: e-shifted L2 Regularizer <sub>(to appear)
• Generalization Bound Regularizer: A Unified Framework for Understanding Weight Decay <sub>(to appear)
• mixup: Beyond Empirical Risk Minimization <sub>(paper)
• CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features <sub>(paper)

Trained Models and Performance Table

Single crop validation error on ImageNet-1k (center 224x224 crop from resized image with shorter side = 256).

Typical Training & Testing Tips:

Small Models

ShuffleNetV2_1x

python -m torch.distributed.launch --nproc_per_node=8 imagenet_mobile.py --cos -a shufflenetv2_1x --data /path/to/imagenet1k/ \
--epochs 300 --wd 4e-5 --gamma 0.1 -c checkpoints/imagenet/shufflenetv2_1x --train-batch 128 --opt-level O0 --nowd-bn # Triaing

python -m torch.distributed.launch --nproc_per_node=2 imagenet_mobile.py -a shufflenetv2_1x --data /path/to/imagenet1k/ \
-e --resume ../pretrain/shufflenetv2_1x.pth.tar --test-batch 100 --opt-level O0 # Testing, ~69.6% top-1 Acc

Large Models

SGE-ResNet

python -W ignore imagenet.py -a sge_resnet101 --data /path/to/imagenet1k/ --epochs 100 --schedule 30 60 90 \
--gamma 0.1 -c checkpoints/imagenet/sge_resnet101 --gpu-id 0,1,2,3,4,5,6,7 # Training

python -m torch.distributed.launch --nproc_per_node=8 imagenet_fast.py -a sge_resnet101 --data /path/to/imagenet1k/ \ 
--epochs 100 --schedule 30 60 90 --wd 1e-4 --gamma 0.1 -c checkpoints/imagenet/sge_resnet101 --train-batch 32 \ 
--opt-level O0 --wd-all --label-smoothing 0. --warmup 0 # Training (faster) 

python -W ignore imagenet.py -a sge_resnet101 --data /path/to/imagenet1k/ --gpu-id 0,1 -e --resume ../pretrain/sge_resnet101.pth.tar \
# Testing ~78.8% top-1 Acc

python -m torch.distributed.launch --nproc_per_node=2 imagenet_fast.py -a sge_resnet101 --data /path/to/imagenet1k/ -e --resume \
../pretrain/sge_resnet101.pth.tar --test-batch 100 --opt-level O0 # Testing (faster) ~78.8% top-1 Acc

WS-ResNet with e-shifted L2 regularizer, e = 1e-3

python -m torch.distributed.launch --nproc_per_node=8 imagenet_fast.py -a ws_resnet50 --data /share1/public/public/imagenet1k/ \
--epochs 100 --schedule 30 60 90 --wd 1e-4 --gamma 0.1 -c checkpoints/imagenet/es1e-3_ws_resnet50 --train-batch 32 \
--opt-level O0 --label-smoothing 0. --warmup 0 --nowd-conv --mineps 1e-3 --el2

Results of "SGENet: Spatial Group-wise Enhance: Enhancing Semantic Feature Learning in Convolutional Networks"

Note the following results (old) do not set the bias wd = 0 for large models

Classification

Here SK-ResNet* is a modified version (for more fair comparison with ResNet backbone here) of original SKNet. The original SKNets perform stronger, and the pytorch version can be referred in pppLang-SKNet.

Detection

Results of "Understanding the Disharmony between Weight Normalization Family and Weight Decay: e-shifted L2 Regularizer"

Note that the following models are with bias wd = 0.

Classification

Results of "Generalization Bound Regularizer: A Unified Framework for Understanding Weight Decay"

To appear

Citation

If you find our related works useful in your research, please consider citing the paper:

@inproceedings{li2019selective,
  title={Selective Kernel Networks},
  author={Li, Xiang and Wang, Wenhai and Hu, Xiaolin and Yang, Jian},
  journal={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2019}
}

@inproceedings{li2019spatial,
  title={Spatial Group-wise Enhance: Enhancing Semantic Feature Learning in Convolutional Networks},
  author={Li, Xiang and Hu, Xiaolin and Xia, Yan and Yang, Jian},
  journal={arXiv preprint arXiv:1905.09646},
  year={2019}
}

@inproceedings{li2019understanding,
  title={Understanding the Disharmony between Weight Normalization Family and Weight Decay: e-shifted L2 Regularizer},
  author={Li, Xiang and Chen, Shuo and Yang, Jian},
  journal={arXiv preprint arXiv:},
  year={2019}
}

@inproceedings{li2019generalization,
  title={Generalization Bound Regularizer: A Unified Framework for Understanding Weight Decay},
  author={Li, Xiang and Chen, Shuo and Gong, Chen and Xia, Yan and Yang, Jian},
  journal={arXiv preprint arXiv:},
  year={2019}
}