diff --git a/README.md b/README.md index c984ebee2ee53619e23113720f25c9221cbecf5f..e6bdfcf22f94ffdcc574689b443ac3b9c6e3bb8a 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,7 @@ PaddleClas is a toolset for image classification tasks prepared for the industry and academia. It helps users train better computer vision models and apply them in real scenarios. **Recent update** +- 2020.12.06 Add `SE_HRNet_W64_C_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 84.75%. - 2020.11.23 Add `GhostNet_x1_3_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 79.38%. - 2020.11.09 Add `InceptionV3` architecture and pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 79.1%. - 2020.09.17 Add `Res2Net50_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 83.1%. Add `Res2Net101_vd_26w_4s_ssld` pretrained model, whose Top-1 Acc on ImageNet-1k dataset reaches 83.9%. @@ -256,6 +257,7 @@ Accuracy and inference time metrics of HRNet series models are shown as follows. | HRNet_W48_C | 0.7895 | 0.9442 | 13.70761 | 34.43572 | 34.58 | 77.47 | [Download link](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 | [Download link](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_pretrained.pdparams) | | HRNet_W64_C | 0.7930 | 0.9461 | 17.57527 | 47.9533 | 57.83 | 128.06 | [Download link](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) | diff --git a/README_cn.md b/README_cn.md index e6e50262702684fd753527dc5f8659bdddb3cdbc..80c888d1edb35fed6598f44e479224e8094999a2 100644 --- a/README_cn.md +++ b/README_cn.md @@ -8,6 +8,7 @@ **近期更新** +- 2020.12.06 添加`SE_HRNet_W64_C_ssld`模型，在ImageNet-1k上Top-1 Acc可达84.75%。 - 2020.11.23 添加`GhostNet_x1_3_ssld `模型，在ImageNet-1k上Top-1 Acc可达79.38%。 - 2020.11.18 添加图像分类[常见问题2020第一季第三期](./docs/zh_CN/faq_series/faq_2020_s1.md) 5个新问题，并且计划以后每周会更新，欢迎大家持续关注。 - 2020.11.09 添加`InceptionV3 `结构和模型，在ImageNet-1k上Top-1 Acc可达79.14%。 @@ -260,6 +261,7 @@ 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_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_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) | diff --git a/docs/en/models/HRNet_en.md b/docs/en/models/HRNet_en.md index 22935b8f39ef49970ceeba6098852d5711e35c1e..971aa6778e9cf47cbc95cf5008359c130e0cff04 100644 --- a/docs/en/models/HRNet_en.md +++ b/docs/en/models/HRNet_en.md @@ -30,6 +30,7 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC | HRNet_W48_C | 0.790 | 0.944 | 0.793 | 0.945 | 34.580 | 77.470 | | HRNet_W48_C_ssld | 0.836 | 0.968 | 0.793 | 0.945 | 34.580 | 77.470 | | HRNet_W64_C | 0.793 | 0.946 | 0.795 | 0.946 | 57.830 | 128.060 | +| SE_HRNet_W64_C_ssld | 0.847 | 0.973 | | | 57.830 | 128.970 | ## Inference speed based on V100 GPU @@ -62,3 +63,5 @@ At present, there are 7 pretrained models of such models open-sourced by PaddleC | HRNet_W48_C | 224 | 256 | 12.65015 | 23.12886 | 33.37859 | 13.70761 | 34.43572 | 63.01219 | | HRNet_W48_C_ssld | 224 | 256 | 12.65015 | 23.12886 | 33.37859 | 13.70761 | 34.43572 | 63.01219 | | HRNet_W64_C | 224 | 256 | 15.10428 | 27.68901 | 40.4198 | 17.57527 | 47.9533 | 97.11228 | +| SE_HRNet_W64_C_ssld | 224 | 256 | 32.33651 | 69.31189 | 116.07245 | 31.69770 | 94.99546 | 174.45766 | + diff --git a/docs/en/models/Mobile_en.md b/docs/en/models/Mobile_en.md index b1c7f476dc150a8f0abe9c85d97340eef6d0294d..6bd7c94ced2f9ea6c9d94825b1cf23e11e41da93 100644 --- a/docs/en/models/Mobile_en.md +++ b/docs/en/models/Mobile_en.md @@ -144,3 +144,6 @@ Currently there are 32 pretrained models of the mobile series open source by Pad | ShuffleNetV2_x1_5 | 1.51054 | 2.4565 | 3.41738 | 1.45389 | 2.5203 | 3.99872 | | ShuffleNetV2_x2_0 | 1.95616 | 2.44751 | 4.19173 | 2.15654 | 3.18247 | 5.46893 | | ShuffleNetV2_swish | 2.50213 | 2.92881 | 3.474 | 2.5129 | 2.97422 | 3.69357 | +| GhostNet_x0_5 | 2.64492 | 3.48473 | 4.48844 | 2.36115 | 3.52802 | 3.89444 | +| GhostNet_x1_0 | 2.63120 | 3.92065 | 4.48296 | 2.57042 | 3.56296 | 4.85524 | +| GhostNet_x1_3 | 2.89715 | 3.80329 | 4.81661 | 2.81810 | 3.72071 | 5.92269 | diff --git a/docs/en/models/models_intro_en.md b/docs/en/models/models_intro_en.md index 22a34a04e423a2ee72dd7e57ef802ee6699d503c..ed8936dc760b5e23f38be76779241c993d4a0bba 100644 --- a/docs/en/models/models_intro_en.md +++ b/docs/en/models/models_intro_en.md @@ -163,6 +163,7 @@ python tools/infer/predict.py \ - [HRNet_W48_C](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_pretrained.pdparams) - [HRNet_W48_C_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_ssld_pretrained.pdparams) - [HRNet_W64_C](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W64_C_pretrained.pdparams) + - [SE_HRNet_W64_C_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_HRNet_W64_C_ssld_pretrained.pdparams) - DPN and DenseNet series diff --git a/docs/en/update_history_en.md b/docs/en/update_history_en.md index 0d7dce531ddef8818d14436025f5bfd91d567202..82efc29097d6f92cd312d463bb4fc1891fedd94c 100644 --- a/docs/en/update_history_en.md +++ b/docs/en/update_history_en.md @@ -1,5 +1,8 @@ # Release Notes +- 2020.12.06 + * Add `SE_HRNet_W64_C_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 84.75%. + - 2020.11.23 * Add `GhostNet_x1_3_ssld` pretrained model, whose Top-1 Acc on ImageNet1k dataset reaches 79.38%. diff --git a/docs/zh_CN/models/HRNet.md b/docs/zh_CN/models/HRNet.md index 3c50a802412296ca763b39414b2c447c6d5edca2..6417f318647aa1366970539e26b776fa724b83f8 100644 --- a/docs/zh_CN/models/HRNet.md +++ b/docs/zh_CN/models/HRNet.md @@ -29,6 +29,7 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络， | HRNet_W48_C | 0.790 | 0.944 | 0.793 | 0.945 | 34.580 | 77.470 | | HRNet_W48_C_ssld | 0.836 | 0.968 | 0.793 | 0.945 | 34.580 | 77.470 | | HRNet_W64_C | 0.793 | 0.946 | 0.795 | 0.946 | 57.830 | 128.060 | +| SE_HRNet_W64_C_ssld | 0.847 | 0.973 | | | 57.830 | 128.970 | ## 基于V100 GPU的预测速度 @@ -47,7 +48,6 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络， - ## 基于T4 GPU的预测速度 | Models | Crop Size | Resize Short Size | FP16
Batch Size=1
(ms) | FP16
Batch Size=4
(ms) | FP16
Batch Size=8
(ms) | FP32
Batch Size=1
(ms) | FP32
Batch Size=4
(ms) | FP32
Batch Size=8
(ms) | @@ -61,3 +61,4 @@ HRNet是2019年由微软亚洲研究院提出的一种全新的神经网络， | HRNet_W48_C | 224 | 256 | 12.65015 | 23.12886 | 33.37859 | 13.70761 | 34.43572 | 63.01219 | | HRNet_W48_C_ssld | 224 | 256 | 12.65015 | 23.12886 | 33.37859 | 13.70761 | 34.43572 | 63.01219 | | HRNet_W64_C | 224 | 256 | 15.10428 | 27.68901 | 40.4198 | 17.57527 | 47.9533 | 97.11228 | +| SE_HRNet_W64_C_ssld | 224 | 256 | 32.33651 | 69.31189 | 116.07245 | 31.69770 | 94.99546 | 174.45766 | diff --git a/docs/zh_CN/models/Mobile.md b/docs/zh_CN/models/Mobile.md index 5fcc9efb6120154d59b3de2de7119d5bf8ed5b97..1df0005e78561db6fc7ac7bc76d60ff4a1cb5a0a 100644 --- a/docs/zh_CN/models/Mobile.md +++ b/docs/zh_CN/models/Mobile.md @@ -145,3 +145,6 @@ GhostNet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 | 1.51054 | 2.4565 | 3.41738 | 1.45389 | 2.5203 | 3.99872 | | ShuffleNetV2_x2_0 | 1.95616 | 2.44751 | 4.19173 | 2.15654 | 3.18247 | 5.46893 | | ShuffleNetV2_swish | 2.50213 | 2.92881 | 3.474 | 2.5129 | 2.97422 | 3.69357 | +| GhostNet_x0_5 | 2.64492 | 3.48473 | 4.48844 | 2.36115 | 3.52802 | 3.89444 | +| GhostNet_x1_0 | 2.63120 | 3.92065 | 4.48296 | 2.57042 | 3.56296 | 4.85524 | +| GhostNet_x1_3 | 2.89715 | 3.80329 | 4.81661 | 2.81810 | 3.72071 | 5.92269 | diff --git a/docs/zh_CN/models/models_intro.md b/docs/zh_CN/models/models_intro.md index 7b922333758dcabc8de864f08124fff8aed2fe9c..b8c238a04803ecefb791c330694aad366a2a2949 100644 --- a/docs/zh_CN/models/models_intro.md +++ b/docs/zh_CN/models/models_intro.md @@ -163,7 +163,7 @@ python tools/infer/predict.py \ - [HRNet_W48_C](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_pretrained.pdparams) - [HRNet_W48_C_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W48_C_ssld_pretrained.pdparams) - [HRNet_W64_C](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/HRNet_W64_C_pretrained.pdparams) - + - [SE_HRNet_W64_C_ssld](https://paddle-imagenet-models-name.bj.bcebos.com/dygraph/SE_HRNet_W64_C_ssld_pretrained.pdparams) - DPN与DenseNet系列 - DPN系列[[14](#ref14)]([论文地址](https://arxiv.org/abs/1707.01629)) diff --git a/docs/zh_CN/update_history.md b/docs/zh_CN/update_history.md index 3d50fe1f5aa9a1da571223ae53b52c63a0c8a1ad..bf4de3571766f45076de48e78afafdb6b0cf8f72 100644 --- a/docs/zh_CN/update_history.md +++ b/docs/zh_CN/update_history.md @@ -1,5 +1,8 @@ # 更新日志 +- 2020.12.06 + * 添加SE_HRNet_W64_C_ssld模型，在ImageNet上Top-1 Acc可达0.8475。 + - 2020.11.23 * 添加GhostNet_x1_3_ssld模型，在ImageNet上Top-1 Acc可达0.7938。