Skip to content

P
PaddleDetection

PaddlePaddle / PaddleDetection
大约 1 年 前同步成功

通知 695
Star 11112
Fork 2696
P
PaddleDetection
未验证 提交 2f709dd1 编写于 作者: F Feng Ni 提交者： GitHub
浏览文件
操作

[Dygraph] fix modelzoo link (#2100) 

* fix modelzoo link

* fix config, remove some faster mask modelzoo

* fix readme
上级 e7dd6e05
隐藏空白更改
内联 并排
Showing with 97 addition and 90 deletion
dygraph/README.md
浏览文件 @ 2f709dd1
......@@ -12,12 +12,14 @@
- SSD
- FCOS
- SOLOv2
- PP-YOLO
- TTFNet
扩展特性：
- [x] **Synchronized Batch Norm**
- [√] **Synchronized Batch Norm**
- [√] **Modulated Deformable Convolution**
- [x] **Group Norm**
- [x] **Modulated Deformable Convolution**
- [x] **Deformable PSRoI Pooling**
## 文档教程
......
dygraph/configs/cascade_rcnn/README.md
浏览文件 @ 2f709dd1
......@@ -4,8 +4,8 @@
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 |
| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50-FPN | Cascade Faster | 1 | 1x | ---- | 41.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/cascade_faster_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Cascade Mask | 1 | 1x | ---- | 41.6 | 35.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/cascade_mask_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Cascade Faster | 1 | 1x | ---- | 41.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_rcnn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | Cascade Mask | 1 | 1x | ---- | 41.6 | 35.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/cascade_mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/cascade_rcnn/cascade_mask_rcnn_r50_fpn_1x_coco.yml) |
## Citations
```
......
dygraph/configs/dcn/README.md
浏览文件 @ 2f709dd1
......@@ -3,13 +3,13 @@
| 骨架网络 | 网络类型 | 卷积 | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | Mask AP | 下载 | 配置文件 |
| :------------------- | :------------- | :-----: |:--------: | :-----: | :-----------: |:----: | :-----: | :----------------------------------------------------------: | :----: |
| ResNet50-FPN | Faster | c3-c5 | 2 | 1x | - | 41.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Faster | c3-c5 | 2 | 2x | - | 42.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r50_vd_fpn_2x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x.yml) |
| ResNet101-vd-FPN | Faster | c3-c5 | 2 | 1x | - | 44.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r101_vd_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x.yml) |
| ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 45.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.pdparams) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) |
| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | - | 41.9 | 37.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r50_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x.yml) |
| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | - | 42.9 | 38.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r50_vd_fpn_2x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x.yml) |
| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 44.6 | 39.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r101_vd_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x.yml) |
| ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 46.2 | 40.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x.yml) |
| ResNet50-vd-FPN | Faster | c3-c5 | 2 | 2x | - | 42.4 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-vd-FPN | Faster | c3-c5 | 2 | 1x | - | 44.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r101_vd_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Faster | c3-c5 | 1 | 1x | - | 45.2 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) |[配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
| ResNet50-FPN | Mask | c3-c5 | 1 | 1x | - | 41.9 | 37.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Mask | c3-c5 | 1 | 2x | - | 42.9 | 38.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 44.6 | 39.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Mask | c3-c5 | 1 | 1x | - | 46.2 | 40.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml) |
**注意事项:**
......
dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
......@@ -2,7 +2,7 @@ _BASE_: [
'faster_rcnn_dcn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco/model_final.pdparams
weights: output/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco/model_final
ResNet:
# for ResNeXt: groups, base_width, base_channels
......
dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
......@@ -2,7 +2,7 @@ _BASE_: [
'mask_rcnn_dcn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
weights: output/mask_rcnn_dcn_r101_fpn_1x_coco/model_final.pdparams
weights: output/mask_rcnn_dcn_r101_fpn_1x_coco/model_final
ResNet:
# index 0 stands for res2
......
dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
......@@ -2,7 +2,7 @@ _BASE_: [
'mask_rcnn_dcn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco/model_final.pdparams
weights: output/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco/model_final
ResNet:
# for ResNeXt: groups, base_width, base_channels
......
dygraph/configs/faster_rcnn/README.md
浏览文件 @ 2f709dd1
......@@ -2,13 +2,12 @@
## Model Zoo
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 |
| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50 | Faster | 1 | 1x | ---- | 35.1 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r50_1x_coco.yml) |
| ResNet50-FPN | Faster | 1 | 1x | ---- | 37.0 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.yml) |
| ResNet34-FPN | Faster | 2 | 1x | ---- | 36.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r34_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r34_fpn_1x_coco.yml) |
| ResNet101 | Faster | 1 | 1x | ---- | 38.3 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r101_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml) |
| ResNet101-FPN | Faster | 1 | 1x | ---- | 38.7 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r101_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_1x_coco.yml) |
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 |
| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50 | Faster | 1 | 1x | ---- | 35.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_1x_coco.yml) |
| ResNet34-vd-FPN | Faster | 2 | 1x | ---- | 37.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r34_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r34_vd_fpn_1x_coco.yml) |
| ResNet50-FPN | Faster | 1 | 1x | ---- | 37.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.yml) |
| ResNeXt101-vd-FPN | Faster | 1 | 1x | ---- | 42.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.yml) |
## Citations
```
......
dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
......@@ -2,7 +2,7 @@ _BASE_: [
'faster_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
weights: output/faster_rcnn_r101_vd_fpn_1x_coco/model_final.pdparams
weights: output/faster_rcnn_r101_vd_fpn_1x_coco/model_final
ResNet:
# index 0 stands for res2
......
dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_1x_coco.yml → dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_2x_coco.yml
浏览文件 @ 2f709dd1
_BASE_: [
'faster_rcnn_r50_1x_coco.yml',
'faster_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
weights: output/faster_rcnn_r101_vd_1x_coco/model_final
weights: output/faster_rcnn_r101_vd_fpn_2x_coco/model_final
ResNet:
# index 0 stands for res2
......@@ -14,13 +13,13 @@ ResNet:
return_idx: [0,1,2,3]
num_stages: 4
epoch: 12
epoch: 24
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 1000
dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_1x_coco.yml 0 → 100644
浏览文件 @ 2f709dd1
_BASE_: [
'faster_rcnn_r50_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
weights: output/faster_rcnn_r50_vd_1x_coco/model_final
ResNet:
# index 0 stands for res2
depth: 50
variant: d
norm_type: bn
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
......@@ -3,7 +3,7 @@ _BASE_: [
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/faster_rcnn_x101_vd_64x4d_fpn_1x_coco/model_final.pdparams
weights: output/faster_rcnn_x101_vd_64x4d_fpn_1x_coco/model_final
ResNet:
# for ResNeXt: groups, base_width, base_channels
......
dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.yml 已删除 100644 → 0
浏览文件 @ e7dd6e05
_BASE_: [
'faster_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/faster_rcnn_x101_vd_64x4d_fpn_2x_coco/model_final.pdparams
ResNet:
# for ResNeXt: groups, base_width, base_channels
depth: 101
groups: 64
base_width: 4
base_channels: 64
variant: d
norm_type: bn
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
epoch: 24
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.1
steps: 1000
dygraph/configs/fcos/README.md
浏览文件 @ 2f709dd1
......@@ -12,9 +12,9 @@ FCOS (Fully Convolutional One-Stage Object Detection) is a fast anchor-free obje
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 |
| :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50-FPN | FCOS | 2 | 1x | ---- | 39.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/fcos/fcos_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | FCOS+DCN | 2 | 1x | ---- | 44.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | FCOS+multiscale_train | 2 | 2x | ---- | 42.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) |
| ResNet50-FPN | FCOS | 2 | 1x | ---- | 39.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | FCOS+DCN | 2 | 1x | ---- | 44.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_dcn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_dcn_r50_fpn_1x_coco.yml) |
| ResNet50-FPN | FCOS+multiscale_train | 2 | 2x | ---- | 42.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/fcos_r50_fpn_multiscale_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/fcos/fcos_r50_fpn_multiscale_2x_coco.yml) |
**Notes:**
......
dygraph/configs/mask_rcnn/README.md
浏览文件 @ 2f709dd1
......@@ -2,10 +2,10 @@
## Model Zoo
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 |
| :------------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50 | Mask | 1 | 1x | ---- | 36.4 | 31.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/mask_rcnn_r50_1x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 1x | ---- | 38.3 | 34.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/mask_rcnn_r50_fpn_1x_coco.yml) |
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | Mask AP | 下载 | 配置文件 |
| :------------------- | :------------| :-----: | :-----: | :------------: | :-----: | :-----: | :-----------------------------------------------------: | :-----: |
| ResNet50 | Mask | 1 | 1x | ---- | 36.4 | 31.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_1x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 1x | ---- | 38.3 | 34.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/mask_rcnn/mask_rcnn_r50_fpn_1x_coco.yml) |
## Citations
```
......
dygraph/configs/mask_rcnn/mask_rcnn_r101_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
......@@ -2,7 +2,7 @@ _BASE_: [
'mask_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_pretrained.tar
weights: output/mask_rcnn_r101_fpn_1x_coco/model_final.pdparams
weights: output/mask_rcnn_r101_fpn_1x_coco/model_final
ResNet:
# index 0 stands for res2
......
dygraph/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_2x_coco.yml → dygraph/configs/mask_rcnn/mask_rcnn_r101_vd_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
_BASE_: [
'mask_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/mask_rcnn_x101_vd_64x4d_fpn_2x_coco/model_final.pdparams
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
weights: output/mask_rcnn_r101_vd_fpn_1x_coco/model_final
ResNet:
# for ResNeXt: groups, base_width, base_channels
# index 0 stands for res2
depth: 101
variant: d
groups: 64
base_width: 4
base_channels: 64
norm_type: bn
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
epoch: 24
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.1
steps: 1000
dygraph/configs/mask_rcnn/mask_rcnn_x101_vd_64x4d_fpn_1x_coco.yml
浏览文件 @ 2f709dd1
......@@ -3,7 +3,7 @@ _BASE_: [
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/mask_rcnn_x101_vd_64x4d_fpn_1x_coco/model_final.pdparams
weights: output/mask_rcnn_x101_vd_64x4d_fpn_1x_coco/model_final
ResNet:
# for ResNeXt: groups, base_width, base_channels
......
dygraph/configs/solov2/README.md
浏览文件 @ 2f709dd1
......@@ -19,8 +19,8 @@ SOLOv2 (Segmenting Objects by Locations) is a fast instance segmentation framewo
| BlendMask | R50-FPN | True | 3x | 37.8 | 13.5 | V100 | - | - |
| SOLOv2 (Paper) | R50-FPN | False | 1x | 34.8 | 18.5 | V100 | - | - |
| SOLOv2 (Paper) | X101-DCN-FPN | True | 3x | 42.4 | 5.9 | V100 | - | - |
| SOLOv2 | R50-FPN | False | 1x | 35.5 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/solov2_r50_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/solov2/solov2_r50_fpn_1x_coco.yml) |
| SOLOv2 | R50-FPN | True | 3x | 37.9 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/solov2_r50_3x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/solov2/solov2_r50_fpn_3x_coco.yml) |
| SOLOv2 | R50-FPN | False | 1x | 35.5 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/solov2_r50_fpn_1x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/solov2/solov2_r50_fpn_1x_coco.yml) |
| SOLOv2 | R50-FPN | True | 3x | 37.9 | 21.9 | V100 | [model](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/solov2_r50_fpn_3x_coco.pdparams) | [config](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/solov2/solov2_r50_fpn_3x_coco.yml) |
**Notes:**
......
dygraph/configs/ssd/README.md
浏览文件 @ 2f709dd1
......@@ -6,8 +6,8 @@
| 骨架网络 | 网络类型 | 每张GPU图片个数 | 学习率策略 |推理时间(fps) | Box AP | 下载 | 配置文件 |
| :-------------- | :------------- | :-----: | :-----: | :------------: | :-----: | :-----------------------------------------------------: | :-----: |
| VGG | SSD | 8 | 240e | ---- | 78.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd_vgg16_300_240e_voc.yml) |
| MobileNet v1 | SSD | 32 | 120e | ---- | 73.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_mobilenet_v1_300_120e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd_mobilenet_v1_300_120e_voc.yml) |
| VGG | SSD | 8 | 240e | ---- | 78.2 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_vgg16_300_240e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd/ssd_vgg16_300_240e_voc.yml) |
| MobileNet v1 | SSD | 32 | 120e | ---- | 73.3 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/ssd_mobilenet_v1_300_120e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/ssd/ssd_mobilenet_v1_300_120e_voc.yml) |
**注意：** SSD-VGG使用4GPU在总batch size为32下训练240个epoch。SSD-MobileNetv1使用2GPU在总batch size为64下训练120周期。
......
dygraph/configs/ssd/_base_/ssd_mobilenet_reader.yml
浏览文件 @ 2f709dd1
......@@ -13,7 +13,7 @@ TrainReader:
- PadBoxOp: {num_max_boxes: 90}
batch_transforms:
- NormalizeImageOp: {mean: [127.5, 127.5, 127.5], std: [127.502231, 127.502231, 127.502231], is_scale: false}
- Permute: {}
- PermuteOp: {}
batch_size: 32
shuffle: true
drop_last: true
......@@ -24,7 +24,7 @@ EvalReader:
- DecodeOp: {}
- ResizeOp: {target_size: [300, 300], keep_ratio: False, interp: 1}
- NormalizeImageOp: {mean: [127.5, 127.5, 127.5], std: [127.502231, 127.502231, 127.502231], is_scale: false}
- Permute: {}
- PermuteOp: {}
batch_size: 1
drop_empty: false
......@@ -36,5 +36,5 @@ TestReader:
- DecodeOp: {}
- ResizeOp: {target_size: [300, 300], keep_ratio: False, interp: 1}
- NormalizeImageOp: {mean: [127.5, 127.5, 127.5], std: [127.502231, 127.502231, 127.502231], is_scale: false}
- Permute: {}
- PermuteOp: {}
batch_size: 1
dygraph/configs/yolov3/README.md
浏览文件 @ 2f709dd1
......@@ -9,26 +9,26 @@
| DarkNet53(paper) | 608 | 8 | 270e | ---- | 33.0 | - | - |
| DarkNet53(paper) | 416 | 8 | 270e | ---- | 31.0 | - | - |
| DarkNet53(paper) | 320 | 8 | 270e | ---- | 28.2 | - | - |
| DarkNet53 | 608 | 8 | 270e | ---- | 39.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
| DarkNet53 | 416 | 8 | 270e | ---- | 37.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
| DarkNet53 | 320 | 8 | 270e | ---- | 34.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_darknet53_270e_coco.yml) |
| MobileNet-V1 | 608 | 8 | 270e | ---- | 28.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
| MobileNet-V1 | 416 | 8 | 270e | ---- | 28.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
| MobileNet-V1 | 320 | 8 | 270e | ---- | 26.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_coco.yml) |
| MobileNet-V3 | 608 | 8 | 270e | ---- | 31.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
| MobileNet-V3 | 416 | 8 | 270e | ---- | 29.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
| MobileNet-V3 | 320 | 8 | 270e | ---- | 26.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_coco.yml) |
| DarkNet53 | 608 | 8 | 270e | ---- | 39.0 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.yml) |
| DarkNet53 | 416 | 8 | 270e | ---- | 37.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.yml) |
| DarkNet53 | 320 | 8 | 270e | ---- | 34.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_darknet53_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_darknet53_270e_coco.yml) |
| MobileNet-V1 | 608 | 8 | 270e | ---- | 28.8 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) |
| MobileNet-V1 | 416 | 8 | 270e | ---- | 28.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) |
| MobileNet-V1 | 320 | 8 | 270e | ---- | 26.5 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_coco.yml) |
| MobileNet-V3 | 608 | 8 | 270e | ---- | 31.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) |
| MobileNet-V3 | 416 | 8 | 270e | ---- | 29.7 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) |
| MobileNet-V3 | 320 | 8 | 270e | ---- | 26.9 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_coco.yml) |
### YOLOv3 on Pasacl VOC
| 骨架网络 | 输入尺寸 | 每张GPU图片个数 | 学习率策略 |推理时间(fps)| Box AP | 下载 | 配置文件 |
| :----------- | :--: | :-----: | :-----: |:------------: |:----: | :-------: | :----: |
| MobileNet-V1 | 608 | 8 | 270e | - | 75.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
| MobileNet-V1 | 416 | 8 | 270e | - | 76.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
| MobileNet-V1 | 320 | 8 | 270e | - | 73.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v1_270e_voc.yml) |
| MobileNet-V3 | 608 | 8 | 270e | - | 79.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
| MobileNet-V3 | 416 | 8 | 270e | - | 78.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
| MobileNet-V3 | 320 | 8 | 270e | - | 76.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/yolov3_mobilenet_v3_large_270e_voc.yml) |
| MobileNet-V1 | 608 | 8 | 270e | - | 75.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) |
| MobileNet-V1 | 416 | 8 | 270e | - | 76.1 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) |
| MobileNet-V1 | 320 | 8 | 270e | - | 73.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v1_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v1_270e_voc.yml) |
| MobileNet-V3 | 608 | 8 | 270e | - | 79.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) |
| MobileNet-V3 | 416 | 8 | 270e | - | 78.6 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) |
| MobileNet-V3 | 320 | 8 | 270e | - | 76.4 | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/yolov3_mobilenet_v3_large_270e_voc.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/yolov3/yolov3_mobilenet_v3_large_270e_voc.yml) |
**注意：** YOLOv3均使用8GPU训练，训练270个epoch
......
dygraph/docs/MODEL_ZOO_cn.md
浏览文件 @ 2f709dd1
......@@ -55,3 +55,11 @@ Paddle提供基于ImageNet的骨架网络预训练模型。所有预训练模型
### SOLOv2
请参考[SOLOv2](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/solov2/)
### PP-YOLO
请参考[PP-YOLO](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/ppyolo/)
### TTFNet
请参考[TTFNet](https://github.com/PaddlePaddle/PaddleDetection/tree/dygraph/configs/ttfnet/)
dygraph/ppdet/engine/export_utils.py
浏览文件 @ 2f709dd1
......@@ -33,8 +33,8 @@ TRT_MIN_SUBGRAPH = {
'RetinaNet': 40,
'EfficientDet': 40,
'Face': 3,
'TTFNet': 40,
'FCOS': 40,
'TTFNet': 3,
'FCOS': 16,
'SOLOv2': 60,
}
......
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