Skip to content

M
models

PaddlePaddle / models
大约 1 年 前同步成功

通知 222
Star 6828
Fork 2962
M
models
提交 b430a921 编写于 作者: C cuicheng
浏览文件
操作

update TensorRT 1.5.2 inference time

上级 89d4f259
隐藏空白更改
内联 并排
Showing with 142 addition and 142 deletion
PaddleCV/image_classification/README.md
浏览文件 @ b430a921
......@@ -236,128 +236,128 @@ PaddlePaddle/Models ImageClassification 支持自定义数据
### AlexNet
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[AlexNet](http://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar) | 56.72% | 79.17% | 3.083 | 2.728 |
|[AlexNet](http://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar) | 56.72% | 79.17% | 3.083 | 2.566 |
### SqueezeNet
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[SqueezeNet1_0](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_0_pretrained.tar) | 59.60% | 81.66% | 2.740 | 1.688 |
|[SqueezeNet1_1](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_1_pretrained.tar) | 60.08% | 81.85% | 2.751 | 1.270 |
|[SqueezeNet1_0](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_0_pretrained.tar) | 59.60% | 81.66% | 2.740 | 1.719 |
|[SqueezeNet1_1](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_1_pretrained.tar) | 60.08% | 81.85% | 2.751 | 1.282 |
### VGG Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[VGG11](https://paddle-imagenet-models-name.bj.bcebos.com/VGG11_pretrained.tar) | 69.28% | 89.09% | 8.223 | 6.821 |
|[VGG13](https://paddle-imagenet-models-name.bj.bcebos.com/VGG13_pretrained.tar) | 70.02% | 89.42% | 9.512 | 7.783 |
|[VGG16](https://paddle-imagenet-models-name.bj.bcebos.com/VGG16_pretrained.tar) | 72.00% | 90.69% | 11.315 | 9.067 |
|[VGG19](https://paddle-imagenet-models-name.bj.bcebos.com/VGG19_pretrained.tar) | 72.56% | 90.93% | 13.096 | 10.388 |
|[VGG11](https://paddle-imagenet-models-name.bj.bcebos.com/VGG11_pretrained.tar) | 69.28% | 89.09% | 8.223 | 6.619 |
|[VGG13](https://paddle-imagenet-models-name.bj.bcebos.com/VGG13_pretrained.tar) | 70.02% | 89.42% | 9.512 | 7.566 |
|[VGG16](https://paddle-imagenet-models-name.bj.bcebos.com/VGG16_pretrained.tar) | 72.00% | 90.69% | 11.315 | 8.985 |
|[VGG19](https://paddle-imagenet-models-name.bj.bcebos.com/VGG19_pretrained.tar) | 72.56% | 90.93% | 13.096 | 9.997 |
### MobileNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[MobileNetV1_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_25_pretrained.tar) | 51.43% | 75.46% | 2.283 | 0.866 |
|[MobileNetV1_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_5_pretrained.tar) | 63.52% | 84.73% | 2.378 | 1.058 |
|[MobileNetV1_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_75_pretrained.tar) | 68.81% | 88.23% | 2.540 | 1.386 |
|[MobileNetV1_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_25_pretrained.tar) | 51.43% | 75.46% | 2.283 | 0.838 |
|[MobileNetV1_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_5_pretrained.tar) | 63.52% | 84.73% | 2.378 | 1.052 |
|[MobileNetV1_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_75_pretrained.tar) | 68.81% | 88.23% | 2.540 | 1.376 |
|[MobileNetV1](http://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar) | 70.99% | 89.68% | 2.609 |1.615 |
|[MobileNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | 53.21% | 76.52% | 4.267 | 3.777 |
|[MobileNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | 65.03% | 85.72% | 4.514 | 4.150 |
|[MobileNetV2_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_75_pretrained.tar) | 69.83% | 89.01% | 4.313 | 3.720 |
|[MobileNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15% | 90.65% | 4.546 | 5.278 |
|[MobileNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | 74.12% | 91.67% | 5.235 | 6.909 |
|[MobileNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | 75.23% | 92.58% | 6.680 | 7.658 |
|[MobileNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | 53.21% | 76.52% | 4.267 | 2.791 |
|[MobileNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | 65.03% | 85.72% | 4.514 | 3.008 |
|[MobileNetV2_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_75_pretrained.tar) | 69.83% | 89.01% | 4.313 | 3.504 |
|[MobileNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15% | 90.65% | 4.546 | 3.874 |
|[MobileNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | 74.12% | 91.67% | 5.235 | 4.771 |
|[MobileNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | 75.23% | 92.58% | 6.680 | 5.649 |
|[MobileNetV3_small_x1_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_pretrained.tar) | 67.46% | 87.12% | 6.809 | |
### ShuffleNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ShuffleNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_pretrained.tar) | 68.80% | 88.45% | 6.101 | 3.616 |
|[ShuffleNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_25_pretrained.tar) | 49.90% | 73.79% | 5.956 | 2.961 |
|[ShuffleNetV2_x0_33](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_33_pretrained.tar) | 53.73% | 77.05% | 5.896 | 2.941 |
|[ShuffleNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_5_pretrained.tar) | 60.32% | 82.26% | 6.048 | 3.088 |
|[ShuffleNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x1_5_pretrained.tar) | 71.63% | 90.15% | 6.113 | 3.699 |
|[ShuffleNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x2_0_pretrained.tar) | 73.15% | 91.20% | 6.430 | 4.553 |
|[ShuffleNetV2_swish](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_swish_pretrained.tar) | 70.03% | 89.17% | 6.078 | 6.282 |
|[ShuffleNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_25_pretrained.tar) | 49.90% | 73.79% | 5.956 | 2.505 |
|[ShuffleNetV2_x0_33](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_33_pretrained.tar) | 53.73% | 77.05% | 5.896 | 2.519 |
|[ShuffleNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_5_pretrained.tar) | 60.32% | 82.26% | 6.048 | 2.642 |
|[ShuffleNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x1_5_pretrained.tar) | 71.63% | 90.15% | 6.113 | 3.164 |
|[ShuffleNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x2_0_pretrained.tar) | 73.15% | 91.20% | 6.430 | 3.954 |
|[ShuffleNetV2_swish](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_swish_pretrained.tar) | 70.03% | 89.17% | 6.078 | 4.976 |
### ResNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ResNet18](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_pretrained.tar) | 70.98% | 89.92% | 3.456 | 2.484 |
|[ResNet18_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_vd_pretrained.tar) | 72.26% | 90.80% | 3.847 | 2.473 |
|[ResNet34](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar) | 74.57% | 92.14% | 5.668 | 3.767 |
|[ResNet34_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_vd_pretrained.tar) | 75.98% | 92.98% | 6.089 | 3.531 |
|[ResNet50](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar) | 76.50% | 93.00% | 8.787 | 5.434 |
|[ResNet50_vc](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vc_pretrained.tar) |78.35% | 94.03% | 9.013 | 5.463 |
|[ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar) | 79.12% | 94.44% | 9.058 | 5.510 |
|[ResNet50_vd_v2](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_v2_pretrained.tar) | 79.84% | 94.93% | 9.058 | 5.510 |
|[ResNet101](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar) | 77.56% | 93.64% | 15.447 | 8.779 |
|[ResNet101_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar) | 80.17% | 94.97% | 15.685 | 8.878 |
|[ResNet152](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_pretrained.tar) | 78.26% | 93.96% | 21.816 | 12.148 |
|[ResNet152_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_vd_pretrained.tar) | 80.59% | 95.30% | 22.041 | 12.259 |
|[ResNet200_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet200_vd_pretrained.tar) | 80.93% | 95.33% | 28.015 | 15.278 |
|[ResNet18](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_pretrained.tar) | 70.98% | 89.92% | 3.456 | 2.261 |
|[ResNet18_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_vd_pretrained.tar) | 72.26% | 90.80% | 3.847 | 2.404 |
|[ResNet34](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar) | 74.57% | 92.14% | 5.668 | 3.424 |
|[ResNet34_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_vd_pretrained.tar) | 75.98% | 92.98% | 6.089 | 3.544 |
|[ResNet50](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar) | 76.50% | 93.00% | 8.787 | 5.137 |
|[ResNet50_vc](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vc_pretrained.tar) |78.35% | 94.03% | 9.013 | 5.285 |
|[ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar) | 79.12% | 94.44% | 9.058 | 5.259 |
|[ResNet50_vd_v2](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_v2_pretrained.tar) | 79.84% | 94.93% | 9.058 | 5.259 |
|[ResNet101](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar) | 77.56% | 93.64% | 15.447 | 8.473 |
|[ResNet101_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar) | 80.17% | 94.97% | 15.685 | 8.574 |
|[ResNet152](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_pretrained.tar) | 78.26% | 93.96% | 21.816 | 11.646 |
|[ResNet152_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_vd_pretrained.tar) | 80.59% | 95.30% | 22.041 | 11.858 |
|[ResNet200_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet200_vd_pretrained.tar) | 80.93% | 95.33% | 28.015 | 14.896 |
### ResNeXt Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_32x4d_pretrained.tar) | 77.75% | 93.82% | 12.863 | 9.837 |
|[ResNeXt50_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_32x4d_pretrained.tar) | 79.56% | 94.62% | 13.673 | 9.991 |
|[ResNeXt50_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 28.162 | 18.271 |
|[ResNeXt50_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_64x4d_pretrained.tar) | 80.12% | 94.86% | 20.888 | 17.687 |
|[ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x4d_pretrained.tar) | 78.65% | 94.19% | 24.154 | 21.387 |
|[ResNeXt101_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_32x4d_pretrained.tar) | 80.33% | 95.12% | 24.701 | 18.032 |
|[ResNeXt101_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 41.073 | 38.736 |
|[ResNeXt101_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar) | 80.78% | 95.20% | 42.277 | 40.929 |
|[ResNeXt152_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_32x4d_pretrained.tar) | 78.98% | 94.33% | 37.007 | 31.301 |
|[ResNeXt152_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_64x4d_pretrained.tar) | 79.51% | 94.71% | 58.966 | 57.267 |
|[ResNeXt152_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_vd_64x4d_pretrained.tar) | 81.08% | 95.34% | 60.947 | 49.117 |
|[ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_32x4d_pretrained.tar) | 77.75% | 93.82% | 12.863 | 9.241 |
|[ResNeXt50_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_32x4d_pretrained.tar) | 79.56% | 94.62% | 13.673 | 9.162 |
|[ResNeXt50_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 28.162 | 15.935 |
|[ResNeXt50_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_64x4d_pretrained.tar) | 80.12% | 94.86% | 20.888 | 15.938 |
|[ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x4d_pretrained.tar) | 78.65% | 94.19% | 24.154 | 17.661 |
|[ResNeXt101_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_32x4d_pretrained.tar) | 80.33% | 95.12% | 24.701 | 17.249 |
|[ResNeXt101_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 41.073 | 31.288 |
|[ResNeXt101_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar) | 80.78% | 95.20% | 42.277 | 32.620 |
|[ResNeXt152_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_32x4d_pretrained.tar) | 78.98% | 94.33% | 37.007 | 26.981 |
|[ResNeXt152_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_64x4d_pretrained.tar) | 79.51% | 94.71% | 58.966 | 47.915 |
|[ResNeXt152_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_vd_64x4d_pretrained.tar) | 81.08% | 95.34% | 60.947 | 47.406 |
### DenseNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[DenseNet121](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet121_pretrained.tar) | 75.66% | 92.58% | 12.437 | 5.813 |
|[DenseNet161](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet161_pretrained.tar) | 78.57% | 94.14% | 27.717 | 12.861 |
|[DenseNet169](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet169_pretrained.tar) | 76.81% | 93.31% | 18.941 | 8.146 |
|[DenseNet201](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet201_pretrained.tar) | 77.63% | 93.66% | 26.583 | 10.549 |
|[DenseNet264](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet264_pretrained.tar) | 77.96% | 93.85% | 41.495 | 15.574 |
|[DenseNet121](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet121_pretrained.tar) | 75.66% | 92.58% | 12.437 | 5.592 |
|[DenseNet161](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet161_pretrained.tar) | 78.57% | 94.14% | 27.717 | 12.254 |
|[DenseNet169](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet169_pretrained.tar) | 76.81% | 93.31% | 18.941 | 7.742 |
|[DenseNet201](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet201_pretrained.tar) | 77.63% | 93.66% | 26.583 | 10.066 |
|[DenseNet264](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet264_pretrained.tar) | 77.96% | 93.85% | 41.495 | 14.740 |
### DPN Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[DPN68](https://paddle-imagenet-models-name.bj.bcebos.com/DPN68_pretrained.tar) | 76.78% | 93.43% | 18.446 | 6.324 |
|[DPN92](https://paddle-imagenet-models-name.bj.bcebos.com/DPN92_pretrained.tar) | 79.85% | 94.80% | 25.748 | 22.182 |
|[DPN98](https://paddle-imagenet-models-name.bj.bcebos.com/DPN98_pretrained.tar) | 80.59% | 95.10% | 29.421 | 13.657 |
|[DPN107](https://paddle-imagenet-models-name.bj.bcebos.com/DPN107_pretrained.tar) | 80.89% | 95.32% | 41.071 | 19.115 |
|[DPN131](https://paddle-imagenet-models-name.bj.bcebos.com/DPN131_pretrained.tar) | 80.70% | 95.14% | 41.179 | 18.278 |
|[DPN68](https://paddle-imagenet-models-name.bj.bcebos.com/DPN68_pretrained.tar) | 76.78% | 93.43% | 18.446 | 6.199 |
|[DPN92](https://paddle-imagenet-models-name.bj.bcebos.com/DPN92_pretrained.tar) | 79.85% | 94.80% | 25.748 | 21.029 |
|[DPN98](https://paddle-imagenet-models-name.bj.bcebos.com/DPN98_pretrained.tar) | 80.59% | 95.10% | 29.421 | 13.411 |
|[DPN107](https://paddle-imagenet-models-name.bj.bcebos.com/DPN107_pretrained.tar) | 80.89% | 95.32% | 41.071 | 18.885 |
|[DPN131](https://paddle-imagenet-models-name.bj.bcebos.com/DPN131_pretrained.tar) | 80.70% | 95.14% | 41.179 | 18.246 |
### SENet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[SE_ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) | 79.52% | 94.75% | 10.345 | 7.662 |
|[SE_ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) | 78.44% | 93.96% | 14.916 | 12.126 |
|[SE_ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) | 79.12% | 94.20% | 30.085 | 24.110 |
|[SENet_154_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SENet_154_vd_pretrained.tar) | 81.40% | 95.48% | 71.892 | 64.855 |
|[SE_ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) | 79.52% | 94.75% | 10.345 | 7.631 |
|[SE_ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) | 78.44% | 93.96% | 14.916 | 12.305 |
|[SE_ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) | 79.12% | 94.20% | 30.085 | 23.218 |
|[SENet154_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_pretrained.tar) | 81.40% | 95.48% | 71.892 | 53.131 |
### Inception Series
| Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[GoogLeNet](https://paddle-imagenet-models-name.bj.bcebos.com/GoogLeNet_pretrained.tar) | 70.70% | 89.66% | 6.528 | 3.076 |
|[Xception41](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_pretrained.tar) | 79.30% | 94.53% | 13.757 | 10.831 |
|[Xception41_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_deeplab_pretrained.tar) | 79.55% | 94.38% | 14.268 | 10.301 |
|[Xception65](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_pretrained.tar) | 81.00% | 95.49% | 19.216 | 15.981 |
|[Xception65_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_deeplab_pretrained.tar) | 80.32% | 94.49% | 19.536 | 16.365 |
|[Xception71](https://paddle-imagenet-models-name.bj.bcebos.com/Xception71_pretrained.tar) | 81.11% | 95.45% | 23.291 | 18.974 |
|[InceptionV4](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar) | 80.77% | 95.26% | 32.413 | 18.154 |
|[GoogLeNet](https://paddle-imagenet-models-name.bj.bcebos.com/GoogLeNet_pretrained.tar) | 70.70% | 89.66% | 6.528 | 2.919 |
|[Xception41](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_pretrained.tar) | 79.30% | 94.53% | 13.757 | 7.885 |
|[Xception41_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_deeplab_pretrained.tar) | 79.55% | 94.38% | 14.268 | 7.257 |
|[Xception65](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_pretrained.tar) | 81.00% | 95.49% | 19.216 | 10.742 |
|[Xception65_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_deeplab_pretrained.tar) | 80.32% | 94.49% | 19.536 | 10.713 |
|[Xception71](https://paddle-imagenet-models-name.bj.bcebos.com/Xception71_pretrained.tar) | 81.11% | 95.45% | 23.291 | 12.154 |
|[InceptionV4](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar) | 80.77% | 95.26% | 32.413 | 17.728 |
### DarkNet
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[DarkNet53](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_ImageNet1k_pretrained.tar) | 78.04% | 94.05% | 11.969 | 7.153 |
|[DarkNet53](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_ImageNet1k_pretrained.tar) | 78.04% | 94.05% | 11.969 | 6.300 |
### ResNeXt101_wsl Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ResNeXt101_32x8d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x8d_wsl_pretrained.tar) | 82.55% | 96.74% | 33.310 | 27.648 |
|[ResNeXt101_32x16d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x16d_wsl_pretrained.tar) | 84.24% | 97.26% | 54.320 | 46.064 |
|[ResNeXt101_32x32d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x32d_wsl_pretrained.tar) | 84.97% | 97.59% | 97.734 | 87.961 |
|[ResNeXt101_32x8d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x8d_wsl_pretrained.tar) | 82.55% | 96.74% | 33.310 | 27.628 |
|[ResNeXt101_32x16d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x16d_wsl_pretrained.tar) | 84.24% | 97.26% | 54.320 | 47.599 |
|[ResNeXt101_32x32d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x32d_wsl_pretrained.tar) | 84.97% | 97.59% | 97.734 | 81.660 |
|[ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x48d_wsl_pretrained.tar) | 85.37% | 97.69% | 161.722 | |
|[Fix_ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/Fix_ResNeXt101_32x48d_wsl_pretrained.tar) | 86.26% | 97.97% | 236.091 | |
......
PaddleCV/image_classification/README_en.md
浏览文件 @ b430a921
......@@ -218,128 +218,128 @@ Pretrained models can be downloaded by clicking related model names.
### AlexNet
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[AlexNet](http://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar) | 56.72% | 79.17% | 3.083 | 2.728 |
|[AlexNet](http://paddle-imagenet-models-name.bj.bcebos.com/AlexNet_pretrained.tar) | 56.72% | 79.17% | 3.083 | 2.566 |
### SqueezeNet
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[SqueezeNet1_0](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_0_pretrained.tar) | 59.60% | 81.66% | 2.740 | 1.688 |
|[SqueezeNet1_1](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_1_pretrained.tar) | 60.08% | 81.85% | 2.751 | 1.270 |
|[SqueezeNet1_0](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_0_pretrained.tar) | 59.60% | 81.66% | 2.740 | 1.719 |
|[SqueezeNet1_1](https://paddle-imagenet-models-name.bj.bcebos.com/SqueezeNet1_1_pretrained.tar) | 60.08% | 81.85% | 2.751 | 1.282 |
### VGG Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[VGG11](https://paddle-imagenet-models-name.bj.bcebos.com/VGG11_pretrained.tar) | 69.28% | 89.09% | 8.223 | 6.821 |
|[VGG13](https://paddle-imagenet-models-name.bj.bcebos.com/VGG13_pretrained.tar) | 70.02% | 89.42% | 9.512 | 7.783 |
|[VGG16](https://paddle-imagenet-models-name.bj.bcebos.com/VGG16_pretrained.tar) | 72.00% | 90.69% | 11.315 | 9.067 |
|[VGG19](https://paddle-imagenet-models-name.bj.bcebos.com/VGG19_pretrained.tar) | 72.56% | 90.93% | 13.096 | 10.388 |
|[VGG11](https://paddle-imagenet-models-name.bj.bcebos.com/VGG11_pretrained.tar) | 69.28% | 89.09% | 8.223 | 6.619 |
|[VGG13](https://paddle-imagenet-models-name.bj.bcebos.com/VGG13_pretrained.tar) | 70.02% | 89.42% | 9.512 | 7.566 |
|[VGG16](https://paddle-imagenet-models-name.bj.bcebos.com/VGG16_pretrained.tar) | 72.00% | 90.69% | 11.315 | 8.985 |
|[VGG19](https://paddle-imagenet-models-name.bj.bcebos.com/VGG19_pretrained.tar) | 72.56% | 90.93% | 13.096 | 9.997 |
### MobileNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[MobileNetV1_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_25_pretrained.tar) | 51.43% | 75.46% | 2.283 | 0.866 |
|[MobileNetV1_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_5_pretrained.tar) | 63.52% | 84.73% | 2.378 | 1.058 |
|[MobileNetV1_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_75_pretrained.tar) | 68.81% | 88.23% | 2.540 | 1.386 |
|[MobileNetV1_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_25_pretrained.tar) | 51.43% | 75.46% | 2.283 | 0.838 |
|[MobileNetV1_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_5_pretrained.tar) | 63.52% | 84.73% | 2.378 | 1.052 |
|[MobileNetV1_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_75_pretrained.tar) | 68.81% | 88.23% | 2.540 | 1.376 |
|[MobileNetV1](http://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar) | 70.99% | 89.68% | 2.609 |1.615 |
|[MobileNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | 53.21% | 76.52% | 4.267 | 3.777 |
|[MobileNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | 65.03% | 85.72% | 4.514 | 4.150 |
|[MobileNetV2_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_75_pretrained.tar) | 69.83% | 89.01% | 4.313 | 3.720 |
|[MobileNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15% | 90.65% | 4.546 | 5.278 |
|[MobileNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | 74.12% | 91.67% | 5.235 | 6.909 |
|[MobileNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | 75.23% | 92.58% | 6.680 | 7.658 |
|[MobileNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | 53.21% | 76.52% | 4.267 | 2.791 |
|[MobileNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | 65.03% | 85.72% | 4.514 | 3.008 |
|[MobileNetV2_x0_75](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_75_pretrained.tar) | 69.83% | 89.01% | 4.313 | 3.504 |
|[MobileNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | 72.15% | 90.65% | 4.546 | 3.874 |
|[MobileNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | 74.12% | 91.67% | 5.235 | 4.771 |
|[MobileNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | 75.23% | 92.58% | 6.680 | 5.649 |
|[MobileNetV3_small_x1_0](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_pretrained.tar) | 67.46% | 87.12% | 6.809 | |
### ShuffleNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ShuffleNetV2](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_pretrained.tar) | 68.80% | 88.45% | 6.101 | 3.616 |
|[ShuffleNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_25_pretrained.tar) | 49.90% | 73.79% | 5.956 | 2.961 |
|[ShuffleNetV2_x0_33](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_33_pretrained.tar) | 53.73% | 77.05% | 5.896 | 2.941 |
|[ShuffleNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_5_pretrained.tar) | 60.32% | 82.26% | 6.048 | 3.088 |
|[ShuffleNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x1_5_pretrained.tar) | 71.63% | 90.15% | 6.113 | 3.699 |
|[ShuffleNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x2_0_pretrained.tar) | 73.15% | 91.20% | 6.430 | 4.553 |
|[ShuffleNetV2_swish](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_swish_pretrained.tar) | 70.03% | 89.17% | 6.078 | 6.282 |
|[ShuffleNetV2_x0_25](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_25_pretrained.tar) | 49.90% | 73.79% | 5.956 | 2.505 |
|[ShuffleNetV2_x0_33](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_33_pretrained.tar) | 53.73% | 77.05% | 5.896 | 2.519 |
|[ShuffleNetV2_x0_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_5_pretrained.tar) | 60.32% | 82.26% | 6.048 | 2.642 |
|[ShuffleNetV2_x1_5](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x1_5_pretrained.tar) | 71.63% | 90.15% | 6.113 | 3.164 |
|[ShuffleNetV2_x2_0](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x2_0_pretrained.tar) | 73.15% | 91.20% | 6.430 | 3.954 |
|[ShuffleNetV2_swish](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_swish_pretrained.tar) | 70.03% | 89.17% | 6.078 | 4.976 |
### ResNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ResNet18](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_pretrained.tar) | 70.98% | 89.92% | 3.456 | 2.484 |
|[ResNet18_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_vd_pretrained.tar) | 72.26% | 90.80% | 3.847 | 2.473 |
|[ResNet34](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar) | 74.57% | 92.14% | 5.668 | 3.767 |
|[ResNet34_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_vd_pretrained.tar) | 75.98% | 92.98% | 6.089 | 3.531 |
|[ResNet50](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar) | 76.50% | 93.00% | 8.787 | 5.434 |
|[ResNet50_vc](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vc_pretrained.tar) |78.35% | 94.03% | 9.013 | 5.463 |
|[ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar) | 79.12% | 94.44% | 9.058 | 5.510 |
|[ResNet50_vd_v2](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_v2_pretrained.tar) | 79.84% | 94.93% | 9.058 | 5.510 |
|[ResNet101](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar) | 77.56% | 93.64% | 15.447 | 8.779 |
|[ResNet101_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar) | 80.17% | 94.97% | 15.685 | 8.878 |
|[ResNet152](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_pretrained.tar) | 78.26% | 93.96% | 21.816 | 12.148 |
|[ResNet152_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_vd_pretrained.tar) | 80.59% | 95.30% | 22.041 | 12.259 |
|[ResNet200_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet200_vd_pretrained.tar) | 80.93% | 95.33% | 28.015 | 15.278 |
|[ResNet18](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_pretrained.tar) | 70.98% | 89.92% | 3.456 | 2.261 |
|[ResNet18_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet18_vd_pretrained.tar) | 72.26% | 90.80% | 3.847 | 2.404 |
|[ResNet34](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_pretrained.tar) | 74.57% | 92.14% | 5.668 | 3.424 |
|[ResNet34_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet34_vd_pretrained.tar) | 75.98% | 92.98% | 6.089 | 3.544 |
|[ResNet50](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_pretrained.tar) | 76.50% | 93.00% | 8.787 | 5.137 |
|[ResNet50_vc](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vc_pretrained.tar) |78.35% | 94.03% | 9.013 | 5.285 |
|[ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar) | 79.12% | 94.44% | 9.058 | 5.259 |
|[ResNet50_vd_v2](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_v2_pretrained.tar) | 79.84% | 94.93% | 9.058 | 5.259 |
|[ResNet101](http://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar) | 77.56% | 93.64% | 15.447 | 8.473 |
|[ResNet101_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar) | 80.17% | 94.97% | 15.685 | 8.574 |
|[ResNet152](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_pretrained.tar) | 78.26% | 93.96% | 21.816 | 11.646 |
|[ResNet152_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_vd_pretrained.tar) | 80.59% | 95.30% | 22.041 | 11.858 |
|[ResNet200_vd](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet200_vd_pretrained.tar) | 80.93% | 95.33% | 28.015 | 14.896 |
### ResNeXt Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_32x4d_pretrained.tar) | 77.75% | 93.82% | 12.863 | 9.837 |
|[ResNeXt50_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_32x4d_pretrained.tar) | 79.56% | 94.62% | 13.673 | 9.991 |
|[ResNeXt50_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 28.162 | 18.271 |
|[ResNeXt50_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_64x4d_pretrained.tar) | 80.12% | 94.86% | 20.888 | 17.687 |
|[ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x4d_pretrained.tar) | 78.65% | 94.19% | 24.154 | 21.387 |
|[ResNeXt101_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_32x4d_pretrained.tar) | 80.33% | 95.12% | 24.701 | 18.032 |
|[ResNeXt101_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 41.073 | 38.736 |
|[ResNeXt101_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar) | 80.78% | 95.20% | 42.277 | 40.929 |
|[ResNeXt152_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_32x4d_pretrained.tar) | 78.98% | 94.33% | 37.007 | 31.301 |
|[ResNeXt152_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_64x4d_pretrained.tar) | 79.51% | 94.71% | 58.966 | 57.267 |
|[ResNeXt152_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_vd_64x4d_pretrained.tar) | 81.08% | 95.34% | 60.947 | 49.117 |
|[ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_32x4d_pretrained.tar) | 77.75% | 93.82% | 12.863 | 9.241 |
|[ResNeXt50_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_32x4d_pretrained.tar) | 79.56% | 94.62% | 13.673 | 9.162 |
|[ResNeXt50_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 28.162 | 15.935 |
|[ResNeXt50_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_vd_64x4d_pretrained.tar) | 80.12% | 94.86% | 20.888 | 15.938 |
|[ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x4d_pretrained.tar) | 78.65% | 94.19% | 24.154 | 17.661 |
|[ResNeXt101_vd_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_32x4d_pretrained.tar) | 80.33% | 95.12% | 24.701 | 17.249 |
|[ResNeXt101_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt50_64x4d_pretrained.tar) | 78.43% | 94.13% | 41.073 | 31.288 |
|[ResNeXt101_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar) | 80.78% | 95.20% | 42.277 | 32.620 |
|[ResNeXt152_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_32x4d_pretrained.tar) | 78.98% | 94.33% | 37.007 | 26.981 |
|[ResNeXt152_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_64x4d_pretrained.tar) | 79.51% | 94.71% | 58.966 | 47.915 |
|[ResNeXt152_vd_64x4d](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt152_vd_64x4d_pretrained.tar) | 81.08% | 95.34% | 60.947 | 47.406 |
### DenseNet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[DenseNet121](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet121_pretrained.tar) | 75.66% | 92.58% | 12.437 | 5.813 |
|[DenseNet161](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet161_pretrained.tar) | 78.57% | 94.14% | 27.717 | 12.861 |
|[DenseNet169](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet169_pretrained.tar) | 76.81% | 93.31% | 18.941 | 8.146 |
|[DenseNet201](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet201_pretrained.tar) | 77.63% | 93.66% | 26.583 | 10.549 |
|[DenseNet264](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet264_pretrained.tar) | 77.96% | 93.85% | 41.495 | 15.574 |
|[DenseNet121](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet121_pretrained.tar) | 75.66% | 92.58% | 12.437 | 5.592 |
|[DenseNet161](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet161_pretrained.tar) | 78.57% | 94.14% | 27.717 | 12.254 |
|[DenseNet169](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet169_pretrained.tar) | 76.81% | 93.31% | 18.941 | 7.742 |
|[DenseNet201](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet201_pretrained.tar) | 77.63% | 93.66% | 26.583 | 10.066 |
|[DenseNet264](https://paddle-imagenet-models-name.bj.bcebos.com/DenseNet264_pretrained.tar) | 77.96% | 93.85% | 41.495 | 14.740 |
### DPN Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[DPN68](https://paddle-imagenet-models-name.bj.bcebos.com/DPN68_pretrained.tar) | 76.78% | 93.43% | 18.446 | 6.324 |
|[DPN92](https://paddle-imagenet-models-name.bj.bcebos.com/DPN92_pretrained.tar) | 79.85% | 94.80% | 25.748 | 22.182 |
|[DPN98](https://paddle-imagenet-models-name.bj.bcebos.com/DPN98_pretrained.tar) | 80.59% | 95.10% | 29.421 | 13.657 |
|[DPN107](https://paddle-imagenet-models-name.bj.bcebos.com/DPN107_pretrained.tar) | 80.89% | 95.32% | 41.071 | 19.115 |
|[DPN131](https://paddle-imagenet-models-name.bj.bcebos.com/DPN131_pretrained.tar) | 80.70% | 95.14% | 41.179 | 18.278 |
|[DPN68](https://paddle-imagenet-models-name.bj.bcebos.com/DPN68_pretrained.tar) | 76.78% | 93.43% | 18.446 | 6.199 |
|[DPN92](https://paddle-imagenet-models-name.bj.bcebos.com/DPN92_pretrained.tar) | 79.85% | 94.80% | 25.748 | 21.029 |
|[DPN98](https://paddle-imagenet-models-name.bj.bcebos.com/DPN98_pretrained.tar) | 80.59% | 95.10% | 29.421 | 13.411 |
|[DPN107](https://paddle-imagenet-models-name.bj.bcebos.com/DPN107_pretrained.tar) | 80.89% | 95.32% | 41.071 | 18.885 |
|[DPN131](https://paddle-imagenet-models-name.bj.bcebos.com/DPN131_pretrained.tar) | 80.70% | 95.14% | 41.179 | 18.246 |
### SENet Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[SE_ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) | 79.52% | 94.75% | 10.345 | 7.662 |
|[SE_ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) | 78.44% | 93.96% | 14.916 | 12.126 |
|[SE_ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) | 79.12% | 94.20% | 30.085 | 24.110 |
|[SENet_154_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SENet_154_vd_pretrained.tar) | 81.40% | 95.48% | 71.892 | 64.855 |
|[SE_ResNet50_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNet50_vd_pretrained.tar) | 79.52% | 94.75% | 10.345 | 7.631 |
|[SE_ResNeXt50_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt50_32x4d_pretrained.tar) | 78.44% | 93.96% | 14.916 | 12.305 |
|[SE_ResNeXt101_32x4d](https://paddle-imagenet-models-name.bj.bcebos.com/SE_ResNeXt101_32x4d_pretrained.tar) | 79.12% | 94.20% | 30.085 | 23.218 |
|[SENet154_vd](https://paddle-imagenet-models-name.bj.bcebos.com/SENet154_vd_pretrained.tar) | 81.40% | 95.48% | 71.892 | 53.131 |
### Inception Series
| Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[GoogLeNet](https://paddle-imagenet-models-name.bj.bcebos.com/GoogLeNet_pretrained.tar) | 70.70% | 89.66% | 6.528 | 3.076 |
|[Xception41](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_pretrained.tar) | 79.30% | 94.53% | 13.757 | 10.831 |
|[Xception41_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_deeplab_pretrained.tar) | 79.55% | 94.38% | 14.268 | 10.301 |
|[Xception65](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_pretrained.tar) | 81.00% | 95.49% | 19.216 | 15.981 |
|[Xception65_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_deeplab_pretrained.tar) | 80.32% | 94.49% | 19.536 | 16.365 |
|[Xception71](https://paddle-imagenet-models-name.bj.bcebos.com/Xception71_pretrained.tar) | 81.11% | 95.45% | 23.291 | 18.974 |
|[InceptionV4](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar) | 80.77% | 95.26% | 32.413 | 18.154 |
|[GoogLeNet](https://paddle-imagenet-models-name.bj.bcebos.com/GoogLeNet_pretrained.tar) | 70.70% | 89.66% | 6.528 | 2.919 |
|[Xception41](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_pretrained.tar) | 79.30% | 94.53% | 13.757 | 7.885 |
|[Xception41_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception41_deeplab_pretrained.tar) | 79.55% | 94.38% | 14.268 | 7.257 |
|[Xception65](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_pretrained.tar) | 81.00% | 95.49% | 19.216 | 10.742 |
|[Xception65_deeplab](https://paddle-imagenet-models-name.bj.bcebos.com/Xception65_deeplab_pretrained.tar) | 80.32% | 94.49% | 19.536 | 10.713 |
|[Xception71](https://paddle-imagenet-models-name.bj.bcebos.com/Xception71_pretrained.tar) | 81.11% | 95.45% | 23.291 | 12.154 |
|[InceptionV4](https://paddle-imagenet-models-name.bj.bcebos.com/InceptionV4_pretrained.tar) | 80.77% | 95.26% | 32.413 | 17.728 |
### DarkNet
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[DarkNet53](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_ImageNet1k_pretrained.tar) | 78.04% | 94.05% | 11.969 | 7.153 |
|[DarkNet53](https://paddle-imagenet-models-name.bj.bcebos.com/DarkNet53_ImageNet1k_pretrained.tar) | 78.04% | 94.05% | 11.969 | 6.300 |
### ResNeXt101_wsl Series
|Model | Top-1 | Top-5 | Paddle Fluid inference time(ms) | Paddle TensorRT inference time(ms) |
|- |:-: |:-: |:-: |:-: |
|[ResNeXt101_32x8d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x8d_wsl_pretrained.tar) | 82.55% | 96.74% | 33.310 | 27.648 |
|[ResNeXt101_32x16d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x16d_wsl_pretrained.tar) | 84.24% | 97.26% | 54.320 | 46.064 |
|[ResNeXt101_32x32d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x32d_wsl_pretrained.tar) | 84.97% | 97.59% | 97.734 | 87.961 |
|[ResNeXt101_32x8d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x8d_wsl_pretrained.tar) | 82.55% | 96.74% | 33.310 | 27.628 |
|[ResNeXt101_32x16d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x16d_wsl_pretrained.tar) | 84.24% | 97.26% | 54.320 | 47.599 |
|[ResNeXt101_32x32d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x32d_wsl_pretrained.tar) | 84.97% | 97.59% | 97.734 | 81.660 |
|[ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x48d_wsl_pretrained.tar) | 85.37% | 97.69% | 161.722 | |
|[Fix_ResNeXt101_32x48d_wsl](https://paddle-imagenet-models-name.bj.bcebos.com/Fix_ResNeXt101_32x48d_wsl_pretrained.tar) | 86.26% | 97.97% | 236.091 | |
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或