Skip to content

P
PaddleDetection

s920243400 / PaddleDetection
与 Fork 源项目一致

Fork自 PaddlePaddle / PaddleDetection

通知 2
Star 0
Fork 0
P
PaddleDetection
未验证 提交 5b46f43c 编写于 作者: F Feng Ni 提交者： GitHub
浏览文件
操作

[cherry-pick] update rcnn modelzoo and config (#2238) 

* update faster modelzoo and config, test=dygraph
上级 0127fe3e
隐藏空白更改
内联 并排
Showing with 93 addition and 182 deletion
dygraph/configs/dcn/README.md
浏览文件 @ 5b46f43c
......@@ -2,14 +2,15 @@
| 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_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) |
| ResNet50-FPN | Faster | c3-c5 | 1 | 1x | - | 42.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/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 | 1 | 1x | - | 42.7 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_dcn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Faster | c3-c5 | 1 | 2x | - | 43.7 | - | [下载链接](https://paddledet.bj.bcebos.com/models/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 | 1 | 1x | - | 45.1 | - | [下载链接](https://paddledet.bj.bcebos.com/models/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 | - | 46.5 | - | [下载链接](https://paddledet.bj.bcebos.com/models/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 | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/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 | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/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 | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/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 | - | - | - | [下载链接](https://paddledet.bj.bcebos.com/models/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_r101_vd_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -13,17 +13,3 @@ ResNet:
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
epoch: 12
LearningRate:
base_lr: 0.02
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
TrainReader:
batch_size: 2
dygraph/configs/dcn/faster_rcnn_dcn_r50_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -14,17 +14,3 @@ ResNet:
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
epoch: 12
LearningRate:
base_lr: 0.02
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
TrainReader:
batch_size: 2
dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_1x_coco.yml 0 → 100644
浏览文件 @ 5b46f43c
_BASE_: [
'faster_rcnn_dcn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
weights: output/faster_rcnn_dcn_r50_vd_fpn_2x_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
dcn_v2_stages: [1,2,3]
dygraph/configs/dcn/faster_rcnn_dcn_r50_vd_fpn_2x_coco.yml
浏览文件 @ 5b46f43c
......@@ -16,7 +16,7 @@ ResNet:
epoch: 24
LearningRate:
base_lr: 0.02
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
......@@ -24,6 +24,3 @@ LearningRate:
- !LinearWarmup
start_factor: 0.1
steps: 1000
TrainReader:
batch_size: 2
dygraph/configs/dcn/faster_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -16,14 +16,3 @@ ResNet:
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
epoch: 12
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
dygraph/configs/dcn/mask_rcnn_dcn_r101_vd_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -13,14 +13,3 @@ ResNet:
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
epoch: 12
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
dygraph/configs/dcn/mask_rcnn_dcn_r50_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -14,14 +14,3 @@ ResNet:
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
epoch: 12
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
dygraph/configs/dcn/mask_rcnn_dcn_x101_vd_64x4d_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -16,14 +16,3 @@ ResNet:
return_idx: [0,1,2,3]
num_stages: 4
dcn_v2_stages: [1,2,3]
epoch: 12
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
dygraph/configs/faster_rcnn/README.md
浏览文件 @ 5b46f43c
......@@ -4,10 +4,20 @@
| 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) |
| ResNet50 | Faster | 1 | 1x | ---- | 36.7 | [下载链接](https://paddledet.bj.bcebos.com/models/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) |
| ResNet50-vd | Faster | 1 | 1x | ---- | 37.6 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_1x_coco.yml) |
| ResNet101 | Faster | 1 | 1x | ---- | 39.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_1x_coco.yml) |
| ResNet34-FPN | Faster | 1 | 1x | ---- | 37.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r34_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r34_fpn_1x_coco.yml) |
| ResNet34-vd-FPN | Faster | 1 | 1x | ---- | 38.5 | [下载链接](https://paddledet.bj.bcebos.com/models/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 | ---- | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/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) |
| ResNet50-FPN | Faster | 1 | 2x | ---- | 40.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.yml) |
| ResNet50-vd-FPN | Faster | 1 | 1x | ---- | 39.5 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_1x_coco.yml) |
| ResNet50-vd-FPN | Faster | 1 | 2x | ---- | 40.8 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_2x_coco.yml) |
| ResNet101-FPN | Faster | 1 | 2x | ---- | 41.4 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.yml) |
| ResNet101-vd-FPN | Faster | 1 | 1x | ---- | 42.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_1x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml) |
| ResNet101-vd-FPN | Faster | 1 | 2x | ---- | 43.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r101_vd_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_2x_coco.yml) |
| ResNeXt101-vd-FPN | Faster | 1 | 1x | ---- | 43.4 | [下载链接](https://paddledet.bj.bcebos.com/models/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) |
| ResNeXt101-vd-FPN | Faster | 1 | 2x | ---- | 44.0 | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.yml) |
## Citations
```
......
dygraph/configs/faster_rcnn/faster_rcnn_r101_fpn_2x_coco.yml
浏览文件 @ 5b46f43c
......@@ -21,5 +21,5 @@ LearningRate:
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
start_factor: 0.1
steps: 1000
dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -12,14 +12,3 @@ ResNet:
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
epoch: 12
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 1000
dygraph/configs/faster_rcnn/faster_rcnn_r101_vd_fpn_2x_coco.yml
浏览文件 @ 5b46f43c
......@@ -21,5 +21,5 @@ LearningRate:
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.3333333333333333
start_factor: 0.1
steps: 1000
dygraph/configs/faster_rcnn/faster_rcnn_r34_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -12,23 +12,3 @@ ResNet:
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
FPN:
in_channels: [64, 128, 256, 512]
out_channel: 256
min_level: 0
max_level: 4
spatial_scale: [0.25, 0.125, 0.0625, 0.03125]
LearningRate:
base_lr: 0.02
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
TrainReader:
batch_size: 2
dygraph/configs/faster_rcnn/faster_rcnn_r34_vd_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -13,23 +13,3 @@ ResNet:
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
FPN:
in_channels: [64, 128, 256, 512]
out_channel: 256
min_level: 0
max_level: 4
spatial_scale: [0.25, 0.125, 0.0625, 0.03125]
LearningRate:
base_lr: 0.02
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
TrainReader:
batch_size: 2
dygraph/configs/faster_rcnn/faster_rcnn_r50_2x_coco.yml 已删除 100644 → 0
浏览文件 @ 0127fe3e
_BASE_: [
'faster_rcnn_r50_1x_coco.yml',
]
weights: output/faster_rcnn_r50_2x_coco/model_final
epoch: 24
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
dygraph/configs/faster_rcnn/faster_rcnn_r50_fpn_2x_coco.yml
浏览文件 @ 5b46f43c
......@@ -5,14 +5,11 @@ weights: output/faster_rcnn_r50_fpn_2x_coco/model_final
epoch: 24
LearningRate:
base_lr: 0.02
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
TrainReader:
batch_size: 2
start_factor: 0.1
steps: 1000
dygraph/configs/faster_rcnn/faster_rcnn_r50_vd_fpn_1x_coco.yml 0 → 100644
浏览文件 @ 5b46f43c
_BASE_: [
'faster_rcnn_r50_fpn_1x_coco.yml',
]
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_vd_pretrained.tar
weights: output/faster_rcnn_r50_vd_fpn_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_r50_vd_fpn_2x_coco.yml
浏览文件 @ 5b46f43c
......@@ -15,14 +15,11 @@ ResNet:
epoch: 24
LearningRate:
base_lr: 0.02
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [16, 22]
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
TrainReader:
batch_size: 2
start_factor: 0.1
steps: 1000
dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_1x_coco.yml
浏览文件 @ 5b46f43c
......@@ -16,14 +16,3 @@ ResNet:
freeze_at: 0
return_idx: [0,1,2,3]
num_stages: 4
epoch: 12
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [8, 11]
- !LinearWarmup
start_factor: 0.1
steps: 1000
dygraph/configs/faster_rcnn/faster_rcnn_x101_vd_64x4d_fpn_2x_coco.yml 0 → 100644
浏览文件 @ 5b46f43c
_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
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/gn/README.md
浏览文件 @ 5b46f43c
......@@ -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 | Faster | 1 | 2x | - | 41.9 | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/faster_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/gn/faster_rcnn_r50_fpn_gn_2x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 2x | - | - | - | [下载链接](https://paddlemodels.bj.bcebos.com/object_detection/dygraph/mask_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/gn/mask_rcnn_r50_fpn_gn_2x_coco.yml) |
| ResNet50-FPN | Faster | 1 | 2x | - | 41.9 | - | [下载链接](https://paddledet.bj.bcebos.com/models/faster_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/gn/faster_rcnn_r50_fpn_gn_2x_coco.yml) |
| ResNet50-FPN | Mask | 1 | 2x | - | 42.3 | 38.4 | [下载链接](https://paddledet.bj.bcebos.com/models/mask_rcnn_r50_fpn_gn_2x_coco.pdparams) | [配置文件](https://github.com/PaddlePaddle/PaddleDetection/tree/master/dygraph/configs/gn/mask_rcnn_r50_fpn_gn_2x_coco.yml) |
**注意：** Faster R-CNN baseline仅使用 `2fc` head，而此处使用[`4conv1fc` head](https://arxiv.org/abs/1803.08494)（4层conv之间使用GN），并且FPN也使用GN，而对于Mask R-CNN是在mask head的4层conv之间也使用GN。
......
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