MLBoy_DaisukeMajima

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

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.

To jcpeterson. Hi. Please tell me which should I set "model name__0215_104219"(dir) or model.ckpt-5394.data-00000-of-00001 or model.ckpt-5394.index or model.ckpt-5394.meta(these are files) to --load path.

It is already exist. I think. https://github.com/Ma-Dan/EdgeConnect-CoreML

Hi. I tried make RealESRGAN CoreML model have flexible input and output shape. It was possible, but memory usage reach to sky rockets even 512 * 512 input. I share...

Some CoreML models use large memory. Try Vision Request with completion handler. It save the memory than running without it.

If the model input shape is fixed (320*320), the memory usage is 110MB in my project. I think the flexible input shape make the memory problem.

I tried but failed. 2022年4月1日(金) 21:13 ioskevinshah ***@***.***>: > https://github.com/Honlan/BeautyGAN > > — > Reply to this email directly, view it on GitHub > , or unsubscribe > > ....

also failed🥺

But I want to convert those, so I will revenge .