Training errors

[WeeeNHao]

When I used your model to train my dataset(single category), the mask had both softmax and argmax values of 0

[WeeeNHao]

and why assert image_batch.max() <= 3, f'image_batch max: {image_batch.max()}'? After image normalization, the maximum value is less than 1? Why less than 3

[hitachinsk]

1. Your model may fail to converge.
2. This is a legacy, please ignore this operation.

[WeeeNHao]

您的邮件我已经收到了！