redlt

> Update : I tried with larger & different dataset and different learning rate than what was mentioned in tutorial and my model was successful in detecting the objects. >...

Hi @hyz-xmaster, thanks for your early reply. I have seen your answer. Although I haven't still grasped your code, I can have a shallow understanding that you use the training...

> eval() is not equivalent to requires_grad. Thank you for your early reply. I have learned that turn off the `requires_grad` can accelerate this module, but when we do inference,...

> It seems that you are using `self.num_proposals` proposals for evaluation, as shown [here](https://github.com/PeizeSun/SparseR-CNN/blob/main/projects/SparseRCNN/sparsercnn/detector.py#L209), while the common practice in COCO evaluation is to use 100 proposals. > > I test...

I guess you may need one gpu with 16G RAM. I only have the 12G one, so I modified the config to resize the picture. What make me confused is...

> @lt1103725556 https://blog.csdn.net/qq_33671888/article/details/89254537 Thanks a lot!