diff --git a/README.md b/README.md index 669520cb4d9f5061a82718539753385fea67507b..4131aa2ddb51375bc6158ae9f224297f01bb7556 100644 --- a/README.md +++ b/README.md @@ -57,6 +57,7 @@ PaddleClas is a toolset for image classification tasks prepared for the industry - [Quick start PaddleClas in 30 minutes](./docs/en/tutorials/quick_start_en.md) - [Model introduction and model zoo](./docs/en/models/models_intro_en.md) - [Model zoo overview](#Model_zoo_overview) + - [SSLD pretrained models](#SSLD_pretrained_series) - [ResNet and Vd series](#ResNet_and_Vd_series) - [Mobile series](#Mobile_series) - [SEResNeXt and Res2Net series](#SEResNeXt_and_Res2Net_series) @@ -114,6 +115,28 @@ Curves of accuracy to the inference time and storage size of common mobile-side ![](./docs/images/models/mobile_arm_top1.png) + +### SSLD pretrained models +Accuracy and inference time of the prtrained models based on SSLD distillation are as follows. More detailed information can be refered to [SSLD distillation tutorial](./docs/en/advanced_tutorials/distillation/distillation_en.md). + +| Model | Top-1 Acc | Top-5 Acc | time(ms)
bs=1 | time(ms)
bs=4 | Flops(G) | Params(M) | Download Address | +|---------------------|-----------|-----------|-----------------------|----------------------|----------|-----------|----------------------------------------------------------------------------------------------| +| ResNet34_vd_ssld | 0.7972 | 0.9490 | 2.43427 | 6.22257 | 7.39 | 21.82 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet34_vd_ssld_pretrained.pdparams) | +| ResNet50_vd_
ssld | 0.8239 | 0.9610 | 3.53131 | 8.09057 | 8.67 | 25.58 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams) | +| ResNet50_vd_
ssld_v2 | 0.8300 | 0.9640 | 3.53131 | 8.09057 | 8.67 | 25.58 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_v2_pretrained.pdparams) | +| ResNet101_vd_
ssld | 0.8373 | 0.9669 | 6.11704 | 13.76222 | 16.1 | 44.57 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet101_vd_ssld_pretrained.pdparams) | +| MobileNetV1_
ssld | 0.7789 | 0.9394 | 32.523048 | 1.11 | 4.19 | 16 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV1_ssld_pretrained.pdparams) | +| MobileNetV2_
ssld | 0.7674 | 0.9339 | 23.317699 | 0.6 | 3.44 | 14 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_ssld_pretrained.pdparams) | +| MobileNetV3_
small_x0_35_ssld | 0.5555 | 0.7771 | 2.6352 | 0.026 | 1.66 | 6.9 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_small_x0_35_ssld_pretrained.pdparams) | +| MobileNetV3_
large_x1_0_ssld | 0.7896 | 0.9448 | 19.30835 | 0.45 | 5.47 | 21 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x1_0_ssld_pretrained.pdparams) | +| MobileNetV3_small_
x1_0_ssld | 0.7129 | 0.9010 | 6.5463 | 0.123 | 2.94 | 12 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_small_x1_0_ssld_pretrained.pdparams) | +| GhostNet_
x1_3_ssld | 0.7938 | 0.9449 | 19.9825 | 0.44 | 7.3 | 29 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x1_3_ssld_pretrained.pdparams) | +| Res2Net50_vd_
26w_4s_ssld | 0.831 | 0.966 | 4.52712 | 9.65722 | 8.37 | 25.06 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_ssld_pretrained.pdparams) | +| Res2Net101_vd_
26w_4s_ssld | 0.839 | 0.971 | 8.08729 | 17.31208 | 16.67 | 45.22 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_ssld_pretrained.pdparams) | +| Res2Net200_vd_
26w_4s_ssld | 0.8513 | 0.9742 | 14.67806 | 32.35032 | 31.49 | 76.21 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_ssld_pretrained.pdparams) | +| HRNet_W18_C_ssld | 0.81162 | 0.95804 | 7.40636 | 13.29752 | 4.14 | 21.29 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W18_C_ssld_pretrained.pdparams) | +| HRNet_W48_C_ssld | 0.8363 | 0.9682 | 13.70761 | 34.43572 | 34.58 | 77.47 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_ssld_pretrained.pdparams) | +| SE_HRNet_W64_C_ssld | 0.8475 | 0.9726 | 31.69770 | 94.99546 | 57.83 | 128.97 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_HRNet_W64_C_ssld_pretrained.pdparams) | diff --git a/README_cn.md b/README_cn.md index 29d0c02bb66f4966c2be9e0e5fb885b1be0b74a0..b8c1581f82231b249045213d63a8a70065213bc2 100644 --- a/README_cn.md +++ b/README_cn.md @@ -59,6 +59,7 @@ - [30分钟玩转PaddleClas](./docs/zh_CN/tutorials/quick_start.md) - [模型库介绍和预训练模型](./docs/zh_CN/models/models_intro.md) - [模型库概览图](#模型库概览图) + - [SSLD知识蒸馏系列](#SSLD知识蒸馏系列) - [ResNet及其Vd系列](#ResNet及其Vd系列) - [移动端系列](#移动端系列) - [SEResNeXt与Res2Net系列](#SEResNeXt与Res2Net系列) @@ -118,6 +119,29 @@ ![](./docs/images/models/mobile_arm_top1.png) + +### SSLD知识蒸馏预训练模型 +基于SSLD知识蒸馏的预训练模型列表如下所示，更多关于SSLD知识蒸馏方案的介绍可以参考：[SSLD知识蒸馏文档](./docs/zh_CN/advanced_tutorials/distillation/distillation.md)。 + +| 模型 | Top-1 Acc | Top-5 Acc | time(ms)
bs=1 | time(ms)
bs=4 | Flops(G) | Params(M) | 下载地址 | +|---------------------|-----------|-----------|-----------------------|----------------------|----------|-----------|----------------------------------------------------------------------------------------------| +| ResNet34_vd_ssld | 0.7972 | 0.9490 | 2.43427 | 6.22257 | 7.39 | 21.82 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet34_vd_ssld_pretrained.pdparams) | +| ResNet50_vd_
ssld | 0.8239 | 0.9610 | 3.53131 | 8.09057 | 8.67 | 25.58 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_pretrained.pdparams) | +| ResNet50_vd_
ssld_v2 | 0.8300 | 0.9640 | 3.53131 | 8.09057 | 8.67 | 25.58 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet50_vd_ssld_v2_pretrained.pdparams) | +| ResNet101_vd_
ssld | 0.8373 | 0.9669 | 6.11704 | 13.76222 | 16.1 | 44.57 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/ResNet101_vd_ssld_pretrained.pdparams) | +| MobileNetV1_
ssld | 0.7789 | 0.9394 | 32.523048 | 1.11 | 4.19 | 16 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV1_ssld_pretrained.pdparams) | +| MobileNetV2_
ssld | 0.7674 | 0.9339 | 23.317699 | 0.6 | 3.44 | 14 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV2_ssld_pretrained.pdparams) | +| MobileNetV3_
small_x0_35_ssld | 0.5555 | 0.7771 | 2.6352 | 0.026 | 1.66 | 6.9 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_small_x0_35_ssld_pretrained.pdparams) | +| MobileNetV3_
large_x1_0_ssld | 0.7896 | 0.9448 | 19.30835 | 0.45 | 5.47 | 21 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_large_x1_0_ssld_pretrained.pdparams) | +| MobileNetV3_small_
x1_0_ssld | 0.7129 | 0.9010 | 6.5463 | 0.123 | 2.94 | 12 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/MobileNetV3_small_x1_0_ssld_pretrained.pdparams) | +| GhostNet_
x1_3_ssld | 0.7938 | 0.9449 | 19.9825 | 0.44 | 7.3 | 29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/GhostNet_x1_3_ssld_pretrained.pdparams) | +| Res2Net50_vd_
26w_4s_ssld | 0.831 | 0.966 | 4.52712 | 9.65722 | 8.37 | 25.06 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_ssld_pretrained.pdparams) | +| Res2Net101_vd_
26w_4s_ssld | 0.839 | 0.971 | 8.08729 | 17.31208 | 16.67 | 45.22 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_ssld_pretrained.pdparams) | +| Res2Net200_vd_
26w_4s_ssld | 0.8513 | 0.9742 | 14.67806 | 32.35032 | 31.49 | 76.21 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/Res2Net200_vd_26w_4s_ssld_pretrained.pdparams) | +| HRNet_W18_C_ssld | 0.81162 | 0.95804 | 7.40636 | 13.29752 | 4.14 | 21.29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W18_C_ssld_pretrained.pdparams) | +| HRNet_W48_C_ssld | 0.8363 | 0.9682 | 13.70761 | 34.43572 | 34.58 | 77.47 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_ssld_pretrained.pdparams) | +| SE_HRNet_W64_C_ssld | 0.8475 | 0.9726 | 31.69770 | 94.99546 | 57.83 | 128.97 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_HRNet_W64_C_ssld_pretrained.pdparams) | + ### ResNet及其Vd系列 @@ -260,7 +284,7 @@ HRNet系列模型的精度、速度指标如下表所示，更多关于该系列 | HRNet_W40_C | 0.7877 | 0.9447 | 12.12202 | 25.68184 | 25.41 | 57.55 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W40_C_pretrained.pdparams) | | HRNet_W44_C | 0.7900 | 0.9451 | 13.19858 | 32.25202 | 29.79 | 67.06 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W44_C_pretrained.pdparams) | | HRNet_W48_C | 0.7895 | 0.9442 | 13.70761 | 34.43572 | 34.58 | 77.47 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_pretrained.pdparams) | -| HRNet_W48_C_ssld | 0.8363 | 0.9682 | 13.70761 | 34.43572 | 34.58 | 77.47 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_pretrained.pdparams) | +| HRNet_W48_C_ssld | 0.8363 | 0.9682 | 13.70761 | 34.43572 | 34.58 | 77.47 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_ssld_pretrained.pdparams) | | HRNet_W64_C | 0.7930 | 0.9461 | 17.57527 | 47.9533 | 57.83 | 128.06 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W64_C_pretrained.pdparams) | | SE_HRNet_W64_C_ssld | 0.8475 | 0.9726 | 31.69770 | 94.99546 | 57.83 | 128.97 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_HRNet_W64_C_ssld_pretrained.pdparams) |