Open hemp110 opened 6 years ago
Actually, we could only care the fc6 and fc7 layers, so fc8 and fc10 layers have no need to pre-train.
Thanks for sharing the code. I wander how long it will take to train your BGAN.py program with CPU?
I haven't tested it on CPU, but I trained it on GPU, which costed about 5 hours.
Thanks for sharing the code. When I run the BGAN code, I find that the pretrained vgg19-like model is crucial. So how to train the model on ImageNet since it has two branch layers fc8 and fc10?