unihornWwan

> Yes, you're right. We need to retrain the entire network Thank you for your reply. In addition, if I want to replace the detector, do I also have to...

> What about develop branch. Does it have the same problem? 您好，我遇到了同样的问题，使用教程中提供的 PPM-100 数据集训练时在 iter=1000 报错，经过排查这个问题出现在 vdl 过程中 (Matting/ppmatting/core/train.py 255 行)，调用多层进行至 imgarray2bytes 方法时，图中第 94 行导致图片的shape由 (512， 512，3）变为 （306912，）， 此后 fromarray...

> The T=1 pretrained model files do not contain the `time_attention_weights` weights. Hello, I am having the same problem and trying to change time_attention in build model to self_att n...

> I'm struggling with the some error: `video_len = len(batched_inputs[0]['file_names']) KeyError: 'file_names' ` Did you find a solution please? Hi, I have the same problem, have you solved it ?...

> Hello, can you provide the pre-trained models of SeqFormer? > > Thanks, https://github.com/wjf5203/SeqFormer There are some models, but detectron2 is not used in this project and may not be...