GodMan

Results 20 comments of GodMan

I'm sorry I don't understand your question. Can you give me more information about mobilenet_v2_base code ? Nevertheless, you don't need to change any other code except replacing your loss...

I‘m sorry for my late reply. tf.where actually is a wrapper for array_ops.where function. I don't know your target_tensor type, you just need replace your original loss function using the...

Have you achieved your goal for dealing with jittering? Hope for your methods sharing. Thank you .

Me too. Have you solved the problem? HOW?

Have you solved the problem? How?

I also meet this problem, the reason is that you have run some tf code on gpu and can not exit successfully, so you need to kill it. Following this...

请问抖动这个问题有好的解决方案吗?求分享

> Setting the learning rate a little smaller can solve this problem. In fact, I succeeded. So why large lr may cause this problem?

Maybe this is what you need. https://github.com/a312863063/seeprettyface-generator-yellow/blob/master/model/%E6%A8%A1%E5%9E%8B%E4%B8%8B%E8%BD%BD%E5%90%8E%E6%94%BE%E5%9C%A8%E8%BF%99%E9%87%8C.txt