QianYang

Hi, thanks for your excellent work. I found the GPU utilization was quit low when running the evaluate_parsing_JPPNet-s2.py even though I changed the batch_size to 8. Could you tell me...

Could you please give a detailed description about the runtime environment

2

Hi, thank you for your work. Could you please give a detailed description about the runtime environment? For example, what is the version of Python, Tensorflow and Matlab.

The effect of softmax loss and rank loss

21

When training the APN layers, it seems that rank loss tries to make the three scale softmax losses listed in descending order and enlarge the gap among them. On the...