JoshuaPiinRueyPan

I got it! The Augmenter.to_deterministic() does not tend to be used inside that batch. Instead, it's used between two batches. Therefore, what I need can be implemented by: ``` def...

Hi @asadmujtaba , Could you make sure that the GPU is used through Deploy? If you found that the training speed is acceptable (I get 286.82 s/epoch in the NV...

Sorry, there's no any documents other than the blog post. You can refer to the settings/*.py to see what else you can adjust before jump into the source code.

Hi, I do not use the tensorflow-cpu so I can't imagine how long it would takes... To me, I spend about 330 (s) to Train an epoch, and about 100...

Hi, Sorry for the confusing variable name. The PRETRAIN_MODEL_PATH_NAME in TrainSettings.py is the path to, say if you have trained this network already, and you want to finetune again. You...

While you train the network (Train.py), Tensorflow will automatically save the model in the path: PATH_TO_SAVE_MODEL (in TrainSettings.py). In such path, you can find many directories such as 'save_epoch_12' which...

Add more data. To compare with the previous works, I use only the Hocket Dataset. If you want to deploy it to the real work, you should add more training...

I guess you want to save the result of the prediction? Just run the Deploy.py as: >> Deploy.py $(PATH_FILE_NAME_OF_SOURCE_VIDEO) $(PATH_FILE_NAME_TO_SAVE_RESULT)

Hi, You are right. I think it's due to the length of the video. As you pointed out, you probabily need to cut the video clips... PS. I think you...

It seems that your Graphic Card does not have enough memory. I use NV GTX 1080 Ti, and while training it consumes nearly 10 GB memory...