sankexin
sankexin
## error log | 日志或报错信息 | ログ terminate called after throwing an instance of 'c10::Error' what(): forward() is missing value for argument 'r1'. Declaration: forward(__torch__.model.model.MattingNetwork self, Tensor src, Tensor r1,...
`import argparse import torch from torch.utils.mobile_optimizer import optimize_for_mobile from model import MattingNetwork import torch.utils.data.distributed rec = (torch.zeros([1, 1, 1, 1, 1]).to("cuda"),) * 4 src = torch.randn(1, 1, 3, 1080, 1920).to("cuda")...
fsod is much better than coco ，how long will support fsod dataset? and when you release test custom class and custom picture code？ acturely, it is very important. 
1、如果图片比较小，比如高小于960这个工具会自动resize图片，这样会造成以前标注好的包含小图片的文件到了这个工具里后所有坐标都对应不上，还把以前标注的东西全毁了。 2、有些图片很大，超过这个工具的窗口的地方无法进行标注。 希望楼主处理一下这两个bug，尤其是不要让它resize小图片，能像labelimg一样什么图片都能不改变图片就正常显示更好，如果还能有些快捷键操作更不错。
  I have read your paper. But the operation in the picture can not give a real reason for your effect,. In the case of no pre-defined box, the...
## error log | 日志或报错信息 | ログ ############# pass_level1 unknown Parameter value kind prim::Constant of TensorType, t.dim = 1 unknown Parameter value kind prim::Constant unknown Parameter value kind prim::Constant of...
it is very good! I want to have a try now, can you send me the train and test code? [email protected]
how to use deepspeed train the swin like which in your paper? there is no deepspeed info in zhe project .
detect by this weight:  result:  I was beginning to think it was a post-process error,but when I print the pred of detect.py,the y of keypoint of the person...
hello, where is checkpoints?