ffhh
ffhh
I use new env, the problem just disappered, thanks.
@Dugudaibo 很奇怪，CPU训练速度比GPU高，请问后来怎么解决的？
> I try to turn poly question into rectangles annotations.Just like this: > > x=[] > y=[] > for point in i['points']: > x.append(point['x']) > y.append(point['y']) > ll.extend([min(x),min(y)]) > ll.extend([max(x),min(y)])...
the labels of each batch is imbalanced, but the distribution of labels in one epoch is balanced
再加一层卷积池化就行吧
https://github.com/Cadene/pretrained-models.pytorch/pull/145
https://github.com/AITTSMD/MTCNN-Tensorflow/issues/92
https://github.com/AITTSMD/MTCNN-Tensorflow/issues/92
Same as the other archs
@John1231983 when closing the eyes, the landmarks is not very accurately. Maybe there is almost no eye-closing data in the dataset?