To Continue The Training.

[john-rocky]

Hello. I want to stop and continue my training. For it, I set "<model's name>_0215_104129" to --load_path. "_0215_104129" is dir name. Is this correct way? Or should I do another way ?

I'll happy if you answer me.

[Xavier-Zeng]

Hello. I want to do it like you, do you solve this problem?

[john-rocky]

You can continue your training without load path, only set dataset name. I could continue my training in this way.

Happy deep learning.

[weilanShi]

You

I tried your method, but it seems to be training from scratch.

[john-rocky]

I can't explain why you can't do it. I think you have to use same command (configuration: --dataset, --input_scale_size, etc...) as before to continue. But... I don't know sure.

[weilanShi]

I can't explain why you can't do it. I think you have to use same command (configuration: --dataset, --input_scale_size, etc...) as before to continue. But... I don't know sure.

Now，it can continue the training, and it needs to add the "load path"

[Orchid0714]

I can't explain why you can't do it. I think you have to use same command (configuration: --dataset, --input_scale_size, etc...) as before to continue. But... I don't know sure.

Now，it can continue the training, and it needs to add the "load path"

hi, I just start learning the BEGAN algorithm, I download this code and data, but when I run the code, there is an error: OSError: Unable to open file (unable to open file: name = 'E:/TEST/BEGANmaster/datasets/CelebA_64_64.h5', errno = 13, error message = 'Permission denied', flags = 0, o_flags = 0) I don't know how to solve this problem, can you give me some suggestions? Thank you.

[ivanlen]

I can't explain why you can't do it. I think you have to use same command (configuration: --dataset, --input_scale_size, etc...) as before to continue. But... I don't know sure.

Now，it can continue the training, and it needs to add the "load path"

Can you write the full command please?