Model Zoo¶
1. 图象分类¶
数据集：ImageNet1000类
1.1 量化¶
| 模型 | 压缩方法 | Top-1/Top-5 Acc | 模型体积（MB） | 下载 |
|---|---|---|---|---|
| MobileNetV1 | - | 70.99%/89.68% | xx | 下载链接 |
| MobileNetV1 | quant_post | xx%/xx% | xx | 下载链接 |
| MobileNetV1 | quant_aware | xx%/xx% | xx | 下载链接 |
| MobileNetV2 | - | 72.15%/90.65% | xx | 下载链接 |
| MobileNetV2 | quant_post | xx%/xx% | xx | 下载链接 |
| MobileNetV2 | quant_aware | xx%/xx% | xx | 下载链接 |
| ResNet50 | - | 76.50%/93.00% | xx | 下载链接 |
| ResNet50 | quant_post | xx%/xx% | xx | 下载链接 |
| ResNet50 | quant_aware | xx%/xx% | xx | 下载链接 |
1.2 剪裁¶
| 模型 | 压缩方法 | Top-1/Top-5 Acc | 模型体积（MB） | GFLOPs | 下载 |
|---|---|---|---|---|---|
| MobileNetV1 | Baseline | 70.99%/89.68% | 17 | 1.11 | 下载链接 |
| MobileNetV1 | uniform -50% | 69.4%/88.66% (-1.59%/-1.02%) | 9 | 0.56 | 下载链接 |
| MobileNetV1 | sensitive -30% | 70.4%/89.3% (-0.59%/-0.38%) | 12 | 0.74 | 下载链接 |
| MobileNetV1 | sensitive -50% | 69.8% / 88.9% (-1.19%/-0.78%) | 9 | 0.56 | 下载链接 |
| MobileNetV2 | - | 72.15%/90.65% | 15 | 0.59 | 下载链接 |
| MobileNetV2 | uniform -50% | 65.79%/86.11% (-6.35%/-4.47%) | 11 | 0.296 | 下载链接 |
| ResNet34 | - | 72.15%/90.65% | 84 | 7.36 | 下载链接 |
| ResNet34 | uniform -50% | 70.99%/89.95% (-1.36%/-0.87%) | 41 | 3.67 | 下载链接 |
| ResNet34 | auto -55.05% | 70.24%/89.63% (-2.04%/-1.06%) | 33 | 3.31 | 下载链接 |
1.3 蒸馏¶
| 模型 | 压缩方法 | Top-1/Top-5 Acc | 模型体积（MB） | 下载 |
|---|---|---|---|---|
| MobileNetV1 | student | 70.99%/89.68% | 17 | 下载链接 |
| ResNet50_vd | teacher | 79.12%/94.44% | 99 | 下载链接 |
| MobileNetV1 | ResNet50_vd1 distill | 72.77%/90.68% (+1.78%/+1.00%) | 17 | 下载链接 |
| MobileNetV2 | student | 72.15%/90.65% | 15 | 下载链接 |
| MobileNetV2 | ResNet50_vd distill | 74.28%/91.53% (+2.13%/+0.88%) | 15 | 下载链接 |
| ResNet50 | student | 76.50%/93.00% | 99 | 下载链接 |
| ResNet101 | teacher | 77.56%/93.64% | 173 | 下载链接 |
| ResNet50 | ResNet101 distill | 77.29%/93.65% (+0.79%/+0.65%) | 99 | 下载链接 |
!!! note “Note“
<a name="trans1">[1]</a>：带_vd后缀代表该预训练模型使用了Mixup，Mixup相关介绍参考[mixup: Beyond Empirical Risk Minimization](https://arxiv.org/abs/1710.09412)
2. 目标检测¶
2.1 量化¶
数据集： COCO 2017
| 模型 | 压缩方法 | 数据集 | Image/GPU | 输入608 Box AP | 输入416 Box AP | 输入320 Box AP | 模型体积（MB） | 下载 |
|---|---|---|---|---|---|---|---|---|
| MobileNet-V1-YOLOv3 | - | COCO | 8 | 29.3 | 29.3 | 27.1 | xx | 下载链接 |
| MobileNet-V1-YOLOv3 | quant_post | COCO | 8 | xx | xx | xx | xx | 下载链接 |
| MobileNet-V1-YOLOv3 | quant_aware | COCO | 8 | xx | xx | xx | xx | 下载链接 |
| R50-dcn-YOLOv3 obj365_pretrain | - | COCO | 8 | 41.4 | xx | xx | xx | 下载链接 |
| R50-dcn-YOLOv3 obj365_pretrain | quant_post | COCO | 8 | xx | xx | xx | xx | 下载链接 |
| R50-dcn-YOLOv3 obj365_pretrain | quant_aware | COCO | 8 | xx | xx | xx | xx | 下载链接 |
数据集：WIDER-FACE
| 模型 | 压缩方法 | Image/GPU | 输入尺寸 | Easy/Medium/Hard | 模型体积（MB） | 下载 |
|---|---|---|---|---|---|---|
| BlazeFace | - | 8 | 640 | 0.915/0.892/0.797 | xx | 下载链接 |
| BlazeFace | quant_post | 8 | 640 | xx/xx/xx | xx | 下载链接 |
| BlazeFace | quant_aware | 8 | 640 | xx/xx/xx | xx | 下载链接 |
| BlazeFace-Lite | - | 8 | 640 | 0.909/0.885/0.781 | xx | 下载链接 |
| BlazeFace-Lite | quant_post | 8 | 640 | xx/xx/xx | xx | 下载链接 |
| BlazeFace-Lite | quant_aware | 8 | 640 | xx/xx/xx | xx | 下载链接 |
| BlazeFace-NAS | - | 8 | 640 | 0.837/0.807/0.658 | xx | 下载链接 |
| BlazeFace-NAS | quant_post | 8 | 640 | xx/xx/xx | xx | 下载链接 |
| BlazeFace-NAS | quant_aware | 8 | 640 | xx/xx/xx | xx | 下载链接 |
2.2 剪裁¶
数据集：Pasacl VOC & COCO 2017
| 模型 | 压缩方法 | 数据集 | Image/GPU | 输入608 Box AP | 输入416 Box AP | 输入320 Box AP | 模型体积(MB) | GFLOPs (608*608) | 下载 |
|---|---|---|---|---|---|---|---|---|---|
| MobileNet-V1-YOLOv3 | Baseline | Pascal VOC | 8 | 76.2 | 76.7 | 75.3 | 94 | 40.49 | 下载链接 |
| MobileNet-V1-YOLOv3 | sensitive -52.88% | Pascal VOC | 8 | 77.6 (+1.4) | 77.7 (1.0) | 75.5 (+0.2) | 31 | 19.08 | 下载链接 |
| MobileNet-V1-YOLOv3 | - | COCO | 8 | 29.3 | 29.3 | 27.0 | 95 | 41.35 | 下载链接 |
| MobileNet-V1-YOLOv3 | sensitive -51.77% | COCO | 8 | 26.0 (-3.3) | 25.1 (-4.2) | 22.6 (-4.4) | 32 | 19.94 | 下载链接 |
| R50-dcn-YOLOv3 | - | COCO | 8 | 39.1 | - | - | 177 | 89.60 | 下载链接 |
| R50-dcn-YOLOv3 | sensitive -9.37% | COCO | 8 | 39.3 (+0.2) | - | - | 150 | 81.20 | 下载链接 |
| R50-dcn-YOLOv3 | sensitive -24.68% | COCO | 8 | 37.3 (-1.8) | - | - | 113 | 67.48 | 下载链接 |
| R50-dcn-YOLOv3 obj365_pretrain | - | COCO | 8 | 41.4 | - | - | 177 | 89.60 | 下载链接 |
| R50-dcn-YOLOv3 obj365_pretrain | sensitive -9.37% | COCO | 8 | 40.5 (-0.9) | - | - | 150 | 81.20 | 下载链接 |
| R50-dcn-YOLOv3 obj365_pretrain | sensitive -24.68% | COCO | 8 | 37.8 (-3.3) | - | - | 113 | 67.48 | 下载链接 |
2.3 蒸馏¶
数据集：Pasacl VOC & COCO 2017
| 模型 | 压缩方法 | 数据集 | Image/GPU | 输入608 Box AP | 输入416 Box AP | 输入320 Box AP | 模型体积（MB） | 下载 |
|---|---|---|---|---|---|---|---|---|
| MobileNet-V1-YOLOv3 | - | Pascal VOC | 8 | 76.2 | 76.7 | 75.3 | 94 | 下载链接 |
| ResNet34-YOLOv3 | - | Pascal VOC | 8 | 82.6 | 81.9 | 80.1 | 162 | 下载链接 |
| MobileNet-V1-YOLOv3 | ResNet34-YOLOv3 distill | Pascal VOC | 8 | 79.0 (+2.8) | 78.2 (+1.5) | 75.5 (+0.2) | 94 | 下载链接 |
| MobileNet-V1-YOLOv3 | - | COCO | 8 | 29.3 | 29.3 | 27.0 | 95 | 下载链接 |
| ResNet34-YOLOv3 | - | COCO | 8 | 36.2 | 34.3 | 31.4 | 163 | 下载链接 |
| MobileNet-V1-YOLOv3 | ResNet34-YOLOv3 distill | COCO | 8 | 31.4 (+2.1) | 30.0 (+0.7) | 27.1 (+0.1) | 95 | 下载链接 |
3. 图像分割¶
数据集：Cityscapes