Hao
@Laicheng0830 this could be a problem, pretrained models are widely used.
if I remember correctly, there is another issue discuss this problem.
Hi, the loss is incorrect. It seems it is caused by a TensorLayer update, and the image value should be -1~1, the scale functions in utilise.py may need to modify:...
Wow, great! Let me know if your training is success~ Btw, could you commit your change to this repo? Many thanks for the contribution ~
hi, you should delete `x = x - 0.5` as well, let me change it, I just go home.
wow, so quick. I thought it should be bad as you didn't delete `x = x - 0.5` ...
yes, it is missing, that is why you need to train one ..
you don't need to remove it, it can only work when you have a pre-trained model.
@eugeneu check readme
@eugeneu could you try this vgg19? https://github.com/tensorlayer/pretrained-models/tree/master/models