CXH_NJUST
Results
2
issues of
CXH_NJUST
你好! 很感谢你们启发性的工作! 我在复现的过程中发现coco的fss_list文件中train下data_list_0文件中图片和标注都要比其他其他list少一半,最后得到的coco上split0 1shot的mean iou结果只有37.8(比原论文中结果少了5.51),而其他的split的结果都比较正常。请问这是什么原因呢? 谢谢!
Thanks for your great job!!! Now, I know how to infer GLIGEN with diffusers[https://github.com/gligen/diffusers/tree/gligen/examples/gligen](url). But how can I train GLIGEN with diffusers like ControlNet[https://github.com/huggingface/diffusers/blob/main/examples/controlnet/train_controlnet.py](url)? Thanks again.