bangyidong
bangyidong
> There is an error with bounding boxes' coordinates,when some of coordinate values become 65535. > > So, we can open the file named "minibatch.py" , find the line: >...
I have solved this problem .Thank you!
https://github.com/pytorch/vision
Have you tried using Root-ResNet-18/34 on faster-rcnn？
Do you still have the plan to release the code and model? thanks.
> Dataset in VOC format can be processed using [this code](https://github.com/bowenc0221/Decoupled-Classification-Refinement/blob/master/lib/dataset/pascal_voc.py). And the evaluation is in [this code](https://github.com/bowenc0221/Decoupled-Classification-Refinement/blob/master/lib/dataset/pascal_voc_eval.py). > > Then you can modify the config file with [this code](https://github.com/bowenc0221/Decoupled-Classification-Refinement/blob/master/faster_rcnn/train_end2end.py#L77)...