From cc1e805e4988102b7627c0b6d79d10bc2a2ba85f Mon Sep 17 00:00:00 2001 From: littletomatodonkey Date: Thu, 10 Sep 2020 01:58:20 +0000 Subject: [PATCH] fix readme --- README.md | 88 +++++++++++++++++++++++++++---------------------------- 1 file changed, 43 insertions(+), 45 deletions(-) diff --git a/README.md b/README.md index 0af3fc4d..78769ceb 100644 --- a/README.md +++ b/README.md @@ -109,9 +109,9 @@ ResNet及其Vd系列模型的精度、速度指标如下表所示，更多关于 | ResNet152 | 0.7826 | 0.9396 | 8.50198 | 19.17073 | 23.05 | 60.19 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_pretrained.tar) | | ResNet152_vd | 0.8059 | 0.9530 | 8.54376 | 19.52157 | 23.53 | 60.21 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet152_vd_pretrained.tar) | | ResNet200_vd | 0.8093 | 0.9533 | 10.80619 | 25.01731 | 30.53 | 74.74 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNet200_vd_pretrained.tar) | -| 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/ResNet50_vd_ssld_pretrained.tar) | -| 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/ResNet50_vd_ssld_v2_pretrained.tar) | -| 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/ResNet101_vd_ssld_pretrained.tar) | +| 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/ResNet50_vd_ssld_pretrained.tar) | +| 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/ResNet50_vd_ssld_v2_pretrained.tar) | +| 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/ResNet101_vd_ssld_pretrained.tar) | @@ -211,11 +211,11 @@ EfficientNet与ResNeXt101_wsl系列模型的精度、速度指标如下表所示 | 模型 | Top-1 Acc | Top-5 Acc | time(ms)
bs=1 | time(ms)
bs=4 | Flops(G) | Params(M) | 下载地址 | |---------------------------|-----------|-----------|------------------|------------------|----------|-----------|----------------------------------------------------------------------------------------------------| -| ResNeXt101_32x8d_wsl | 0.8255 | 0.9674 | 18.52528 | 34.25319 | 29.14 | 78.44 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x8d_wsl_pretrained.tar) | -| ResNeXt101_32x16d_wsl | 0.8424 | 0.9726 | 25.60395 | 71.88384 | 57.55 | 152.66 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x16d_wsl_pretrained.tar) | -| ResNeXt101_32x32d_wsl | 0.8497 | 0.9759 | 54.87396 | 160.04337 | 115.17 | 303.11 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x32d_wsl_pretrained.tar) | -| ResNeXt101_32x48d_wsl | 0.8537 | 0.9769 | 99.01698256 | 315.91261 | 173.58 | 456.2 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x48d_wsl_pretrained.tar) | -| Fix_ResNeXt101_32x48d_wsl | 0.8626 | 0.9797 | 160.0838242 | 595.99296 | 354.23 | 456.2 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/Fix_ResNeXt101_32x48d_wsl_pretrained.tar) | +| ResNeXt101_
32x8d_wsl | 0.8255 | 0.9674 | 18.52528 | 34.25319 | 29.14 | 78.44 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x8d_wsl_pretrained.tar) | +| ResNeXt101_
32x16d_wsl | 0.8424 | 0.9726 | 25.60395 | 71.88384 | 57.55 | 152.66 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x16d_wsl_pretrained.tar) | +| ResNeXt101_
32x32d_wsl | 0.8497 | 0.9759 | 54.87396 | 160.04337 | 115.17 | 303.11 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x32d_wsl_pretrained.tar) | +| ResNeXt101_
32x48d_wsl | 0.8537 | 0.9769 | 99.01698256 | 315.91261 | 173.58 | 456.2 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_32x48d_wsl_pretrained.tar) | +| Fix_ResNeXt101_
32x48d_wsl | 0.8626 | 0.9797 | 160.0838242 | 595.99296 | 354.23 | 456.2 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/Fix_ResNeXt101_32x48d_wsl_pretrained.tar) | | EfficientNetB0 | 0.7738 | 0.9331 | 3.442 | 6.11476 | 0.72 | 5.1 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB0_pretrained.tar) | | EfficientNetB1 | 0.7915 | 0.9441 | 5.3322 | 9.41795 | 1.27 | 7.52 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB1_pretrained.tar) | | EfficientNetB2 | 0.7985 | 0.9474 | 6.29351 | 10.95702 | 1.85 | 8.81 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB2_pretrained.tar) | @@ -224,7 +224,7 @@ EfficientNet与ResNeXt101_wsl系列模型的精度、速度指标如下表所示 | EfficientNetB5 | 0.8362 | 0.9672 | 20.48571 | 61.60252 | 19.51 | 29.61 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB5_pretrained.tar) | | EfficientNetB6 | 0.8400 | 0.9688 | 32.62402 | - | 36.27 | 42 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB6_pretrained.tar) | | EfficientNetB7 | 0.8430 | 0.9689 | 53.93823 | - | 72.35 | 64.92 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB7_pretrained.tar) | -| EfficientNetB0_small | 0.7580 | 0.9258 | 2.3076 | 4.71886 | 0.72 | 4.65 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB0_small_pretrained.tar) | +| EfficientNetB0_
small | 0.7580 | 0.9258 | 2.3076 | 4.71886 | 0.72 | 4.65 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/EfficientNetB0_small_pretrained.tar) | ### ResNeSt与RegNet系列 @@ -234,7 +234,7 @@ ResNeSt与RegNet系列模型的精度、速度指标如下表所示，更多关 | 模型 | Top-1 Acc | Top-5 Acc | time(ms)
bs=1 | time(ms)
bs=4 | Flops(G) | Params(M) | 下载地址 | |------------------------|-----------|-----------|------------------|------------------|----------|-----------|------------------------------------------------------------------------------------------------------| -| ResNeSt50_fast_1s1x64d | 0.8035 | 0.9528 | - | - | 8.68 | 26.3 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeSt50_fast_1s1x64d_pretrained.pdparams) | +| ResNeSt50_
fast_1s1x64d | 0.8035 | 0.9528 | - | - | 8.68 | 26.3 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeSt50_fast_1s1x64d_pretrained.pdparams) | | ResNeSt50 | 0.8102 | 0.9542 | - | - | 10.78 | 27.5 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ResNeSt50_pretrained.pdparams) | | RegNetX_4GF | 0.785 | 0.9416 | 6.46478 | 11.19862 | 8 | 22.1 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/RegNetX_4GF_pretrained.pdparams) | @@ -245,46 +245,44 @@ ResNeSt与RegNet系列模型的精度、速度指标如下表所示，更多关 | 模型 | Top-1 Acc | Top-5 Acc | SD855 time(ms)
bs=1 | Flops(G) | Params(M) | 模型大小(M) | 下载地址 | |----------------------------------|-----------|-----------|------------------------|----------|-----------|---------|-----------------------------------------------------------------------------------------------------------| -| MobileNetV1_x0_25 | 0.5143 | 0.7546 | 3.21985 | 0.07 | 0.46 | 1.9 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_25_pretrained.tar) | -| MobileNetV1_x0_5 | 0.6352 | 0.8473 | 9.579599 | 0.28 | 1.31 | 5.2 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_5_pretrained.tar) | -| MobileNetV1_x0_75 | 0.6881 | 0.8823 | 19.436399 | 0.63 | 2.55 | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_75_pretrained.tar) | +| MobileNetV1_
x0_25 | 0.5143 | 0.7546 | 3.21985 | 0.07 | 0.46 | 1.9 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_25_pretrained.tar) | +| MobileNetV1_
x0_5 | 0.6352 | 0.8473 | 9.579599 | 0.28 | 1.31 | 5.2 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_5_pretrained.tar) | +| MobileNetV1_
x0_75 | 0.6881 | 0.8823 | 19.436399 | 0.63 | 2.55 | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_x0_75_pretrained.tar) | | MobileNetV1 | 0.7099 | 0.8968 | 32.523048 | 1.11 | 4.19 | 16 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV1_pretrained.tar) | -| 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/MobileNetV1_ssld_pretrained.tar) | -| MobileNetV2_x0_25 | 0.5321 | 0.7652 | 3.79925 | 0.05 | 1.5 | 6.1 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | -| MobileNetV2_x0_5 | 0.6503 | 0.8572 | 8.7021 | 0.17 | 1.93 | 7.8 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | -| MobileNetV2_x0_75 | 0.6983 | 0.8901 | 15.531351 | 0.35 | 2.58 | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_75_pretrained.tar) | +| 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/MobileNetV1_ssld_pretrained.tar) | +| MobileNetV2_
x0_25 | 0.5321 | 0.7652 | 3.79925 | 0.05 | 1.5 | 6.1 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_25_pretrained.tar) | +| MobileNetV2_
x0_5 | 0.6503 | 0.8572 | 8.7021 | 0.17 | 1.93 | 7.8 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_5_pretrained.tar) | +| MobileNetV2_
x0_75 | 0.6983 | 0.8901 | 15.531351 | 0.35 | 2.58 | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x0_75_pretrained.tar) | | MobileNetV2 | 0.7215 | 0.9065 | 23.317699 | 0.6 | 3.44 | 14 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_pretrained.tar) | -| MobileNetV2_x1_5 | 0.7412 | 0.9167 | 45.623848 | 1.32 | 6.76 | 26 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | -| MobileNetV2_x2_0 | 0.7523 | 0.9258 | 74.291649 | 2.32 | 11.13 | 43 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | -| 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/MobileNetV2_ssld_pretrained.tar) | -| MobileNetV3_large_x1_25 | 0.7641 | 0.9295 | 28.217701 | 0.714 | 7.44 | 29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_25_pretrained.tar) | -| MobileNetV3_large_x1_0 | 0.7532 | 0.9231 | 19.30835 | 0.45 | 5.47 | 21 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar) | -| MobileNetV3_large_x0_75 | 0.7314 | 0.9108 | 13.5646 | 0.296 | 3.91 | 16 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_75_pretrained.tar) | -| MobileNetV3_large_x0_5 | 0.6924 | 0.8852 | 7.49315 | 0.138 | 2.67 | 11 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_5_pretrained.tar) | -| MobileNetV3_large_x0_35 | 0.6432 | 0.8546 | 5.13695 | 0.077 | 2.1 | 8.6 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_35_pretrained.tar) | -| MobileNetV3_small_x1_25 | 0.7067 | 0.8951 | 9.2745 | 0.195 | 3.62 | 14 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_25_pretrained.tar) | -| MobileNetV3_small_x1_0 | 0.6824 | 0.8806 | 6.5463 | 0.123 | 2.94 | 12 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_pretrained.tar) | -| MobileNetV3_small_x0_75 | 0.6602 | 0.8633 | 5.28435 | 0.088 | 2.37 | 9.6 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_75_pretrained.tar) | -| MobileNetV3_small_x0_5 | 0.5921 | 0.8152 | 3.35165 | 0.043 | 1.9 | 7.8 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_5_pretrained.tar) | -| MobileNetV3_small_x0_35 | 0.5303 | 0.7637 | 2.6352 | 0.026 | 1.66 | 6.9 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_35_pretrained.tar) | -| 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/MobileNetV3_small_x0_35_ssld_pretrained.tar) | -| 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/MobileNetV3_large_x1_0_ssld_pretrained.tar) | -| MobileNetV3_large_x1_0_ssld_int8 | 0.7605 | - | 14.395 | - | - | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_int8_pretrained.tar) | -| 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/MobileNetV3_small_x1_0_ssld_pretrained.tar) | +| MobileNetV2_
x1_5 | 0.7412 | 0.9167 | 45.623848 | 1.32 | 6.76 | 26 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x1_5_pretrained.tar) | +| MobileNetV2_
x2_0 | 0.7523 | 0.9258 | 74.291649 | 2.32 | 11.13 | 43 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV2_x2_0_pretrained.tar) | +| 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/MobileNetV2_ssld_pretrained.tar) | +| MobileNetV3_
large_x1_25 | 0.7641 | 0.9295 | 28.217701 | 0.714 | 7.44 | 29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_25_pretrained.tar) | +| MobileNetV3_
large_x1_0 | 0.7532 | 0.9231 | 19.30835 | 0.45 | 5.47 | 21 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_pretrained.tar) | +| MobileNetV3_
large_x0_75 | 0.7314 | 0.9108 | 13.5646 | 0.296 | 3.91 | 16 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_75_pretrained.tar) | +| MobileNetV3_
large_x0_5 | 0.6924 | 0.8852 | 7.49315 | 0.138 | 2.67 | 11 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_5_pretrained.tar) | +| MobileNetV3_
large_x0_35 | 0.6432 | 0.8546 | 5.13695 | 0.077 | 2.1 | 8.6 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x0_35_pretrained.tar) | +| MobileNetV3_
small_x1_25 | 0.7067 | 0.8951 | 9.2745 | 0.195 | 3.62 | 14 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_25_pretrained.tar) | +| MobileNetV3_
small_x1_0 | 0.6824 | 0.8806 | 6.5463 | 0.123 | 2.94 | 12 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x1_0_pretrained.tar) | +| MobileNetV3_
small_x0_75 | 0.6602 | 0.8633 | 5.28435 | 0.088 | 2.37 | 9.6 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_75_pretrained.tar) | +| MobileNetV3_
small_x0_5 | 0.5921 | 0.8152 | 3.35165 | 0.043 | 1.9 | 7.8 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_5_pretrained.tar) | +| MobileNetV3_
small_x0_35 | 0.5303 | 0.7637 | 2.6352 | 0.026 | 1.66 | 6.9 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_small_x0_35_pretrained.tar) | +| 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/MobileNetV3_small_x0_35_ssld_pretrained.tar) | +| 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/MobileNetV3_large_x1_0_ssld_pretrained.tar) | +| MobileNetV3_large_
x1_0_ssld_int8 | 0.7605 | - | 14.395 | - | - | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_int8_pretrained.tar) | +| 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/MobileNetV3_small_x1_0_ssld_pretrained.tar) | | ShuffleNetV2 | 0.6880 | 0.8845 | 10.941 | 0.28 | 2.26 | 9 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_pretrained.tar) | -| ShuffleNetV2_x0_25 | 0.4990 | 0.7379 | 2.329 | 0.03 | 0.6 | 2.7 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_25_pretrained.tar) | -| ShuffleNetV2_x0_33 | 0.5373 | 0.7705 | 2.64335 | 0.04 | 0.64 | 2.8 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_33_pretrained.tar) | -| ShuffleNetV2_x0_5 | 0.6032 | 0.8226 | 4.2613 | 0.08 | 1.36 | 5.6 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_5_pretrained.tar) | -| ShuffleNetV2_x1_5 | 0.7163 | 0.9015 | 19.3522 | 0.58 | 3.47 | 14 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x1_5_pretrained.tar) | -| ShuffleNetV2_x2_0 | 0.7315 | 0.9120 | 34.770149 | 1.12 | 7.32 | 28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x2_0_pretrained.tar) | -| ShuffleNetV2_swish | 0.7003 | 0.8917 | 16.023151 | 0.29 | 2.26 | 9.1 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_swish_pretrained.tar) | +| ShuffleNetV2_
x0_25 | 0.4990 | 0.7379 | 2.329 | 0.03 | 0.6 | 2.7 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_25_pretrained.tar) | +| ShuffleNetV2_
x0_33 | 0.5373 | 0.7705 | 2.64335 | 0.04 | 0.64 | 2.8 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_33_pretrained.tar) | +| ShuffleNetV2_
x0_5 | 0.6032 | 0.8226 | 4.2613 | 0.08 | 1.36 | 5.6 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x0_5_pretrained.tar) | +| ShuffleNetV2_
x1_5 | 0.7163 | 0.9015 | 19.3522 | 0.58 | 3.47 | 14 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x1_5_pretrained.tar) | +| ShuffleNetV2_
x2_0 | 0.7315 | 0.9120 | 34.770149 | 1.12 | 7.32 | 28 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_x2_0_pretrained.tar) | +| ShuffleNetV2_
swish | 0.7003 | 0.8917 | 16.023151 | 0.29 | 2.26 | 9.1 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/ShuffleNetV2_swish_pretrained.tar) | | DARTS_GS_4M | 0.7523 | 0.9215 | 47.204948 | 1.04 | 4.77 | 21 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/DARTS_GS_4M_pretrained.tar) | | DARTS_GS_6M | 0.7603 | 0.9279 | 53.720802 | 1.22 | 5.69 | 24 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/DARTS_GS_6M_pretrained.tar) | -| GhostNet_x0_5 | 0.6688 | 0.8695 | 5.7143 | 0.082 | 2.6 | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/GhostNet_x0_5_pretrained.pdparams) | -| GhostNet_x1_0 | 0.7402 | 0.9165 | 13.5587 | 0.294 | 5.2 | 20 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/GhostNet_x1_0_pretrained.pdparams) | -| GhostNet_x1_3 | 0.7579 | 0.9254 | 19.9825 | 0.44 | 7.3 | 29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/GhostNet_x1_3_pretrained.pdparams) | - - +| GhostNet_
x0_5 | 0.6688 | 0.8695 | 5.7143 | 0.082 | 2.6 | 10 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/GhostNet_x0_5_pretrained.pdparams) | +| GhostNet_
x1_0 | 0.7402 | 0.9165 | 13.5587 | 0.294 | 5.2 | 20 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/GhostNet_x1_0_pretrained.pdparams) | +| GhostNet_
x1_3 | 0.7579 | 0.9254 | 19.9825 | 0.44 | 7.3 | 29 | [下载链接](https://paddle-imagenet-models-name.bj.bcebos.com/GhostNet_x1_3_pretrained.pdparams) | -- GitLab