Underwater-Color-Correction
Underwater-Color-Correction copied to clipboard
cameronfabbri
Should I set the is_training flag for the BN layer?
I encountered a different output of the same image during the test. Looked at the nets/pix2pix.py file, it seems that the batch_norm function does not set the is_training flag. And when defining the optimizer, it does not add a dependency on UPDATE_OPS. tf.contrib.layers.batch_norm Is it because the network training can't learn a good mean and variance, so that the is_training state of the BN layer is forced to be True? But this results in different outputs when the batch size is different.
Looking forward to your reply! Thank you.
I don't know exactly what's your problem, but you SHOULDN't use batch normalization in the decoder part of the generator. Just use it in the encoder part ..
I know what you mean. I did not change their network structure. But I don't think they used the Tensorflow BN layer API in the right way.
@IPNUISTlegal 非要改动的话，只能把BN按照正确的方式重写了。只是发论文看效果的话我感觉不改问题也不大。 我没有改他的代码。我测了一下，大体上讲一张一张送进去（batch size=1）测试是效果比较好的（最接近他们论文的插图），而且一张一张送进去不会出现输出不稳定的情况。一个多张图片的batch送进去会导致不同的batch情况下，同一张图结果不同。