thunth
thunth
I guess that error is because of the TensorFlow version. This work was implemented using TensorFlow 1.x and maybe you are using version 2.x. If that is the case, changing...
I solved it by adding the following function to the class Logger in file 'utils.py' ``` def flush(self): pass ```
Thank you, @YTEP-ZHI, for your reply ^^ I would appreciate it if someone could explain why the GPU memory is not released after the training is stopped forcibly.
@chenxinhe1 Did you get the source code of _ReasonNet_?
> @thunguyenth 您好,没有哦,如果您有的话,恳请共享一下,拜谢 Hi @chenxinhe1, I'm sorry. I also wanted to ask for the code.
Hi @deepmeng, I think I experienced a quite similar problem. I trained the Stage 2 (e2e) model with 3 GPUs (4090), 64GB RAM, and 64GB swap. At the beginning, it...