-
Notifications
You must be signed in to change notification settings - Fork 2.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
DiffusionDet 论文复现提交 #7834
DiffusionDet 论文复现提交 #7834
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
需要更新最新代码解决冲突
|
||
| Backbone | Proposals | lr schedule | Box AP | download | config | | ||
| :-------------- | :-----: | :------------: | :-----: | :-----: | :-----: | | ||
| ResNet50-FPN | 100 | 3x | 43.0 | [download](https://paddledet.bj.bcebos.com/models/sparse_rcnn_r50_fpn_3x_pro100_coco.pdparams) | [config](./sparse_rcnn_r50_fpn_3x_pro100_coco.yml) | |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
链接需要更新,可将模型发至jerrywgz@126.com 然后地址更新为https://paddledet.bj.bcebos.com/models/xcxx.pdparams xxx为模型配置名称
# batch_whwh = self.inputs["img_whwh"] | ||
# targets = [] | ||
|
||
# for i in range(len(batch_gt_class)): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
去除无关代码
|
||
| Backbone | Proposals | lr schedule | Box AP | download | config | | ||
| :-------------- | :-----: | :------------: | :-----: | :-----: | :-----: | | ||
| ResNet50-FPN | 100 | 3x | 43.0 | [download](https://paddledet.bj.bcebos.com/models/sparse_rcnn_r50_fpn_3x_pro100_coco.pdparams) | [config](./sparse_rcnn_r50_fpn_3x_pro100_coco.yml) | |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
模型精度与原版仍有差距
目前完成了 DiffusionDet 小数据集上测试, AP可以达到41,提交一版请求 review
全量数据集仍在训练中
配置文件运行
configs/diffusiondet/diffusiondet_r50_fpn_3x_pro500_coco.yml