ran337287

能支持模型训练吗

1

**自动分段模型训练** 用了自己的数据中英文结合的，发现分段效果不太好。请问能支持特定数据的模型训练吗？

Hello,@BestSonny . I have a question that the scales of default box are calculated by formulations or setup by your experience?

text_recognition_demo.py with GPU

10

When I run text_recognition_demo.py with parameters gpu=-1(that is cpu), it can return the results. But if I set gpu=0, there is something wrong. The error is ` ValueError：numpy and cupy...

hello @AaronYALai , in run_InfoGAN.py, 'D_loss=D_criterion(outputs[:,0],labels)' is the mean of 2*batchSize loss between outputs and labels, but I think D_loss=truth_input_loss+fake_input_loss, that should be the mean of 1*batchSize loss. I'm looking...

each kernel shares the same offsets？

3

#According to test.py, the line 'offset=conv(inputs)' is to learn the offset of neighbor domain of each pixel, so the size of offsets is 1*18*H*W. if the size of input is...

How to train the ReplitLM model

1

When training, it is based on tramsformers' training course. It is started on the A100-80g machine, but the per gpu batch-size can be set to 2 at most, and there...