Closed dreamer-1996 closed 2 years ago
Sorry for the late reply, there was a bug in val.py
, I'll fix in next commit.
In the mean time, please change this line
https://github.com/datvuthanh/HybridNets/blob/c15ba5b3c019c8a7fea71e017c18c05b163adb18/train.py#L203
to
optimizer.load_state_dict(ckpt['optimizer'].state_dict())
and it'll load the optimizer from weight correctly.
Thank you for your reply.
Hello, I tried to follow your suggestion to train the model. So accordingly, at first I freeze the segmentation and trained for some epoch.
After that I am freezing the backbone and detection head.
But I am getting the error
Can you please suggest how to solve this issue?
Thank you in advance