Closed shizidushu closed 2 years ago
Thanks for your attention. When training, as the same as typical classification task, softmax operation is actually in loss function. When validating, softmax is used to generate a probability distribution, which is useful for the following operations (e.g., for the visible threshold).
Why apply softmax in
validate_simdr
: https://github.com/leeyegy/SimDR/blob/67216117f08d2ccfb65324859758aa007976831a/lib/core/function.py#L324-L328And not apply softmax in
train_simdr
? https://github.com/leeyegy/SimDR/blob/67216117f08d2ccfb65324859758aa007976831a/lib/core/function.py#L249-L255I guess softmax operation is not needed in the validate phase? As there is an
LogSoftmax
operation to the output when calculating loss.