drop_path_prob = 0.2 or 0.3?

[D-X-Y]

Hi,

In the paper, it said that "path dropout of probability 0.3", but in the cnn/train.py the default value of drop_path_prob is 0.2. May I ask whether the experiments in the paper use 0.2 or 0.3? And does it affect the results a lot?

Best Regards,

[quark0]

Please use 0.2 as in the code (we'll fix the typo in the paper). Setting it to 0.2 or 0.3 won't make a big difference, but it's important to have some non-zero dropout probabilities there.