Skip to content

Commit a61b509

Browse files
LaraStuStuLaraStuStu
committed
Merge branch 'develop' of https://github.com/PaddlePaddle/PaddleX into develop
2 parents eecbea7 + 82beca8 commit a61b509

File tree

4 files changed

+15
-8
lines changed

4 files changed

+15
-8
lines changed

‎docs/appendix/model_zoo.md‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -36,6 +36,7 @@
3636
3737
| 模型 | 模型大小 | 预测时间(毫秒) | BoxAP（%） |
3838
|:-------|:-----------|:-------------|:----------|
39+
|[FasterRCNN-ResNet18-FPN](https://bj.bcebos.com/paddlex/pretrained_weights/faster_rcnn_r18_fpn_1x.tar) | 173.2M | - | 32.6 |
3940
|[FasterRCNN-ResNet50](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_1x.tar)|136.0MB| 197.715 | 35.2 |
4041
|[FasterRCNN-ResNet50_vd](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_vd_1x.tar)| 136.1MB | 475.700 | 36.4 |
4142
|[FasterRCNN-ResNet101](https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_1x.tar)| 212.5MB | 582.911 | 38.3 |
@@ -55,6 +56,7 @@
5556
5657
| 模型 | 模型大小 | 预测时间(毫秒) | BoxAP (%) | MaskAP (%) |
5758
|:-------|:-----------|:-------------|:----------|:----------|
59+
|[MaskRCNN-ResNet18-FPN](https://bj.bcebos.com/paddlex/pretrained_weights/mask_rcnn_r18_fpn_1x.tar) | 189.1MB | - | 33.6 | 30.5 |
5860
|[MaskRCNN-ResNet50](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_2x.tar) | 143.9MB | 87 | 38.2 | 33.4 |
5961
|[MaskRCNN-ResNet50-FPN](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_2x.tar)| 177.7MB | 63.9 | 38.7 | 34.7 |
6062
|[MaskRCNN-ResNet50_vd-FPN](https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_vd_fpn_2x.tar) | 177.7MB | 63.1 | 39.8 || 35.4 |

‎docs/train/instance_segmentation.md‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -10,9 +10,9 @@ PaddleX目前提供了MaskRCNN实例分割模型结构,多种backbone模型，
1010

1111
| 模型(点击获取代码) | Box MMAP/Seg MMAP | 模型大小 | GPU预测速度 | Arm预测速度 | 备注 |
1212
| :---------------- | :------- | :------- | :--------- | :--------- | :----- |
13-
| [MaskRCNN-ResNet50-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/instance_segmentation/mask_rcnn_r50_fpn.py) | 38.7%/34.7% | 170.0MB | 160.185ms | - | 模型精度高，适用于服务端部署 |
14-
| [MaskRCNN-ResNet18-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/instance_segmentation/mask_rcnn_r18_fpn.py) | -/- | 120.0MB | - | - | 模型精度高，适用于服务端部署 |
15-
| [MaskRCNN-HRNet-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/instance_segmentation/mask_rcnn_hrnet_fpn.py) | 38.7%/34.7% | 116.MB | - | - | 模型精度高，预测速度快，适用于服务端部署 |
13+
| [MaskRCNN-ResNet50-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/instance_segmentation/mask_rcnn_r50_fpn.py) | 38.7%/34.7% | 177.7MB | 160.185ms | - | 模型精度高，适用于服务端部署 |
14+
| [MaskRCNN-ResNet18-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/instance_segmentation/mask_rcnn_r18_fpn.py) | 33.6/30.5 | 189.1MB | - | - | 模型精度高，适用于服务端部署 |
15+
| [MaskRCNN-HRNet-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/instance_segmentation/mask_rcnn_hrnet_fpn.py) | 38.7%/34.7% | 120.7MB | - | - | 模型精度高，预测速度快，适用于服务端部署 |
1616

1717

1818
## 开始训练

‎docs/train/object_detection.md‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -13,8 +13,8 @@ PaddleX目前提供了FasterRCNN和YOLOv3两种检测结构,多种backbone模型
1313
| [YOLOv3-MobileNetV1](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/yolov3_mobilenetv1.py) | 29.3% | 99.2MB | 15.442ms | - | 模型小，预测速度快，适用于低性能或移动端设备 |
1414
| [YOLOv3-MobileNetV3](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/yolov3_mobilenetv3.py) | 31.6% | 100.7MB | 143.322ms | - | 模型小，移动端上预测速度有优势 |
1515
| [YOLOv3-DarkNet53](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/yolov3_darknet53.py) | 38.9 | 249.2MB | 42.672ms | - | 模型较大，预测速度快，适用于服务端 |
16-
| [FasterRCNN-ResNet50-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/faster_rcnn_r50_fpn.py) | 37.2% | 136.0MB | 197.715ms | - | 模型精度高，适用于服务端部署 |
17-
| [FasterRCNN-ResNet18-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/faster_rcnn_r18_fpn.py) | - | - | - | - | 模型精度高，适用于服务端部署 |
16+
| [FasterRCNN-ResNet50-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/faster_rcnn_r50_fpn.py) | 37.2% | 167.7MB | 197.715ms | - | 模型精度高，适用于服务端部署 |
17+
| [FasterRCNN-ResNet18-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/faster_rcnn_r18_fpn.py) | 32.6% | 173.2MB | - | - | 模型精度高，适用于服务端部署 |
1818
| [FasterRCNN-HRNet-FPN](https://github.com/PaddlePaddle/PaddleX/blob/develop/tutorials/train/object_detection/faster_rcnn_hrnet_fpn.py) | 36.0% | 115.MB | 81.592ms | - | 模型精度高，预测速度快，适用于服务端部署 |
1919

2020

‎paddlex/cv/models/utils/pretrain_weights.py‎

Lines changed: 8 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -88,6 +88,8 @@
8888
'https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r34.tar',
8989
'YOLOv3_ResNet50_vd_COCO':
9090
'https://paddlemodels.bj.bcebos.com/object_detection/yolov3_r50vd_dcn.tar',
91+
'FasterRCNN_ResNet18_COCO':
92+
'https://bj.bcebos.com/paddlex/pretrained_weights/faster_rcnn_r18_fpn_1x.tar',
9193
'FasterRCNN_ResNet50_COCO':
9294
'https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r50_fpn_2x.tar',
9395
'FasterRCNN_ResNet50_vd_COCO':
@@ -98,6 +100,8 @@
98100
'https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_r101_vd_fpn_2x.tar',
99101
'FasterRCNN_HRNet_W18_COCO':
100102
'https://paddlemodels.bj.bcebos.com/object_detection/faster_rcnn_hrnetv2p_w18_2x.tar',
103+
'MaskRCNN_ResNet18_COCO':
104+
'https://bj.bcebos.com/paddlex/pretrained_weights/mask_rcnn_r18_fpn_1x.tar',
101105
'MaskRCNN_ResNet50_COCO':
102106
'https://paddlemodels.bj.bcebos.com/object_detection/mask_rcnn_r50_fpn_2x.tar',
103107
'MaskRCNN_ResNet50_vd_COCO':
@@ -136,9 +140,10 @@ def get_pretrain_weights(flag, class_name, backbone, save_dir):
136140
return flag
137141
warning_info = "{} does not support to be finetuned with weights pretrained on the {} dataset, so pretrain_weights is forced to be set to {}"
138142
if flag == 'COCO':
139-
if class_name == "FasterRCNN" and backbone in ['ResNet18'] or \
140-
class_name == "MaskRCNN" and backbone in ['ResNet18'] or \
141-
class_name == 'DeepLabv3p' and backbone in ['Xception41', 'MobileNetV2_x0.25', 'MobileNetV2_x0.5', 'MobileNetV2_x1.5', 'MobileNetV2_x2.0']:
143+
if class_name == 'DeepLabv3p' and backbone in [
144+
'Xception41', 'MobileNetV2_x0.25', 'MobileNetV2_x0.5',
145+
'MobileNetV2_x1.5', 'MobileNetV2_x2.0'
146+
]:
142147
model_name = '{}_{}'.format(class_name, backbone)
143148
logging.warning(warning_info.format(model_name, flag, 'IMAGENET'))
144149
flag = 'IMAGENET'

0 commit comments

Comments
 (0)