问题
I'm training a VGG-16 model from scratch using a dataset containing 3k images. I use Tensorflow platform and 8 cpus without any gpu.
Training rate - 0.01,
Weight decay - 0.0005,
Momentum - 0.9,
Batch size - 64,
I've kept training for about three days. But the training accuracy has been unchanged, around 15%-20% after 20 epochs. Could anyone give me some hints to improve the accuracy?
回答1:
It seems like I have used too large learning rate. Or weight decay does not work as it promises. After I changed my hyper parameters into,
Training rate - 0.001,
Weight decay - 0,
Momentum - 0.9,
Batch size - 64.
Eveything is good. Now I can get accuracy around 90 percent after 25 epochs. Just for your information.
来源：https://stackoverflow.com/questions/43720817/how-many-epochs-does-it-take-to-train-vgg-16