diff --git a/configs/ResNeSt/ResNeSt50_fast_1s1x64d.yaml b/configs/ResNeSt/ResNeSt50_fast_1s1x64d.yaml new file mode 100644 index 000000000..99cb1137e --- /dev/null +++ b/configs/ResNeSt/ResNeSt50_fast_1s1x64d.yaml @@ -0,0 +1,78 @@ +mode: 'train' +ARCHITECTURE: + name: 'ResNeSt50_fast_1s1x64d' + +pretrained_model: "" +model_save_dir: "./output/" +classes_num: 1000 +total_images: 1281167 +save_interval: 1 +validate: True +valid_interval: 1 +epochs: 300 +topk: 5 +image_shape: [3, 224, 224] + +use_mix: True +ls_epsilon: 0.1 + +LEARNING_RATE: + function: 'CosineWarmup' + params: + lr: 0.1 + +OPTIMIZER: + function: 'Momentum' + params: + momentum: 0.9 + regularizer: + function: 'L2' + factor: 0.000070 + +TRAIN: + batch_size: 256 + num_workers: 4 + file_list: "./dataset/ILSVRC2012/train_list.txt" + data_dir: "./dataset/ILSVRC2012/" + shuffle_seed: 0 + transforms: + - DecodeImage: + to_rgb: True + to_np: False + channel_first: False + - RandCropImage: + size: 224 + - RandFlipImage: + flip_code: 1 + - AutoAugment: + - NormalizeImage: + scale: 1./255. + mean: [0.485, 0.456, 0.406] + std: [0.229, 0.224, 0.225] + order: '' + - ToCHWImage: + mix: + - CutmixOperator: + alpha: 0.2 + +VALID: + batch_size: 64 + num_workers: 4 + file_list: "./dataset/ILSVRC2012/val_list.txt" + data_dir: "./dataset/ILSVRC2012/" + shuffle_seed: 0 + transforms: + - DecodeImage: + to_rgb: True + to_np: False + channel_first: False + - ResizeImage: + resize_short: 256 + - CropImage: + size: 224 + - NormalizeImage: + scale: 1.0/255.0 + mean: [0.485, 0.456, 0.406] + std: [0.229, 0.224, 0.225] + order: '' + - ToCHWImage: diff --git a/docs/en/models/Mobile_en.md b/docs/en/models/Mobile_en.md index 739f653d7..c3ebd8f73 100644 --- a/docs/en/models/Mobile_en.md +++ b/docs/en/models/Mobile_en.md @@ -58,9 +58,9 @@ Currently there are 32 pretrained models of the mobile series open source by Pad | ShuffleNetV2_x1_5 | 0.716 | 0.902 | 0.726 | | 0.580 | 3.470 | | ShuffleNetV2_x2_0 | 0.732 | 0.912 | 0.749 | | 1.120 | 7.320 | | ShuffleNetV2_swish | 0.700 | 0.892 | | | 0.290 | 2.260 | -| GhostNet_x0_5 | 0.668 | 0.869 | 0.662 | 0.866 | 0.041 | 2.600 | -| GhostNet_x1_0 | 0.740 | 0.916 | 0.739 | 0.914 | 0.147 | 5.200 | -| GhostNet_x1_3 | 0.757 | 0.925 | 0.757 | 0.927 | 0.220 | 7.300 | +| GhostNet_x0_5 | 0.668 | 0.869 | 0.662 | 0.866 | 0.082 | 2.600 | +| GhostNet_x1_0 | 0.740 | 0.916 | 0.739 | 0.914 | 0.294 | 5.200 | +| GhostNet_x1_3 | 0.757 | 0.925 | 0.757 | 0.927 | 0.440 | 7.300 | ## Inference speed and storage size based on SD855 diff --git a/docs/en/models/ResNeSt_RegNet_en.md b/docs/en/models/ResNeSt_RegNet_en.md index 3952b1155..ad1dad176 100644 --- a/docs/en/models/ResNeSt_RegNet_en.md +++ b/docs/en/models/ResNeSt_RegNet_en.md @@ -6,4 +6,5 @@ The ResNeSt series was proposed in 2020. The original resnet network structure h | Models | Top1 | Top5 | Reference
top1 | Reference
top5 | FLOPS
(G) | Parameters
(M) | |:--:|:--:|:--:|:--:|:--:|:--:|:--:| -| ResNeSt50 | 0.8102 | 0.9542| 0.8113 | -|5.39 | 27.5 | +| ResNeSt50_fast_1s1x64d | 0.8035 | 0.9528| 0.8035 | -| 8.68 | 26.3 | +| ResNeSt50 | 0.8102 | 0.9542| 0.8113 | -| 10.78 | 27.5 | diff --git a/docs/en/models/models_intro_en.md b/docs/en/models/models_intro_en.md index 5fa4358fe..72cecd805 100644 --- a/docs/en/models/models_intro_en.md +++ b/docs/en/models/models_intro_en.md @@ -191,6 +191,13 @@ python tools/infer/predict.py \ - [Fix_ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/Fix_ResNeXt101_32x48d_wsl_pretrained.tar) + +- ResNeSt and RegNet series + - ResNeSt series[[24](#ref24)]([paper link](https://arxiv.org/abs/2004.08955)) + - [ResNeSt50_fast_1s1x64d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeSt50_fast_1s1x64d_pretrained.pdparams) + - [ResNeSt50](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeSt50_pretrained.pdparams) + + - Other models - AlexNet series[[18](#ref18)]([paper link](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)) - [AlexNet](https://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar) @@ -261,3 +268,5 @@ python tools/infer/predict.py \ [22] Ding X, Guo Y, Ding G, et al. Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks[C]//Proceedings of the IEEE International Conference on Computer Vision. 2019: 1911-1920. [23] Han K, Wang Y, Tian Q, et al. GhostNet: More features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1580-1589. + +[24] Zhang H, Wu C, Zhang Z, et al. Resnest: Split-attention networks[J]. arXiv preprint arXiv:2004.08955, 2020. diff --git a/docs/zh_CN/models/Mobile.md b/docs/zh_CN/models/Mobile.md index f8c39952c..386b3848e 100644 --- a/docs/zh_CN/models/Mobile.md +++ b/docs/zh_CN/models/Mobile.md @@ -59,9 +59,9 @@ GhosttNet是华为于2020年提出的一种全新的轻量化网络结构，通 | ShuffleNetV2_x1_5 | 0.716 | 0.902 | 0.726 | | 0.580 | 3.470 | | ShuffleNetV2_x2_0 | 0.732 | 0.912 | 0.749 | | 1.120 | 7.320 | | ShuffleNetV2_swish | 0.700 | 0.892 | | | 0.290 | 2.260 | -| GhostNet_x0_5 | 0.668 | 0.869 | 0.662 | 0.866 | 0.041 | 2.600 | -| GhostNet_x1_0 | 0.740 | 0.916 | 0.739 | 0.914 | 0.147 | 5.200 | -| GhostNet_x1_3 | 0.757 | 0.925 | 0.757 | 0.927 | 0.220 | 7.300 | +| GhostNet_x0_5 | 0.668 | 0.869 | 0.662 | 0.866 | 0.082 | 2.600 | +| GhostNet_x1_0 | 0.740 | 0.916 | 0.739 | 0.914 | 0.294 | 5.200 | +| GhostNet_x1_3 | 0.757 | 0.925 | 0.757 | 0.927 | 0.440 | 7.300 | ## 基于SD855的预测速度和存储大小 diff --git a/docs/zh_CN/models/ResNeSt_RegNet.md b/docs/zh_CN/models/ResNeSt_RegNet.md index 2b12d7394..10b1e5896 100644 --- a/docs/zh_CN/models/ResNeSt_RegNet.md +++ b/docs/zh_CN/models/ResNeSt_RegNet.md @@ -9,6 +9,5 @@ ResNeSt系列模型是在2020年提出的，在原有的resnet网络结构上做 | Models | Top1 | Top5 | Reference
top1 | Reference
top5 | FLOPS
(G) | Parameters
(M) | |:--:|:--:|:--:|:--:|:--:|:--:|:--:| -| ResNeSt50 | 0.8102 | 0.9542| 0.8113 | -|5.39 | 27.5 | - - +| ResNeSt50_fast_1s1x64d | 0.8035 | 0.9528| 0.8035 | -| 8.68 | 26.3 | +| ResNeSt50 | 0.8102 | 0.9542| 0.8113 | -| 10.78 | 27.5 | diff --git a/docs/zh_CN/models/models_intro.md b/docs/zh_CN/models/models_intro.md index 6064a45b6..7faa7c0f0 100644 --- a/docs/zh_CN/models/models_intro.md +++ b/docs/zh_CN/models/models_intro.md @@ -190,6 +190,11 @@ python tools/infer/predict.py \ - [ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x48d_wsl_pretrained.tar) - [Fix_ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/Fix_ResNeXt101_32x48d_wsl_pretrained.tar) +- ResNeSt与RegNet系列 + - ResNeSt系列[[24](#ref24)]([论文地址](https://arxiv.org/abs/2004.08955)) + - [ResNeSt50_fast_1s1x64d)(https://paddle-imagenet-models-name.bj.bcebos.com/ResNeSt50_fast_1s1x64d_pretrained.pdparams) + - [ResNeSt50)(https://paddle-imagenet-models-name.bj.bcebos.com/ResNeSt50_pretrained.pdparams) + - 其他模型 - AlexNet系列[[18](#ref18)]([论文地址](https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf)) @@ -261,3 +266,5 @@ python tools/infer/predict.py \ [22] Ding X, Guo Y, Ding G, et al. Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks[C]//Proceedings of the IEEE International Conference on Computer Vision. 2019: 1911-1920. [23] Han K, Wang Y, Tian Q, et al. GhostNet: More features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2020: 1580-1589. + +[24] Zhang H, Wu C, Zhang Z, et al. Resnest: Split-attention networks[J]. arXiv preprint arXiv:2004.08955, 2020.