Open aytackanaci opened 6 years ago
I am a user of open-reid. For my understanding, it's ok to use the output of previous layer as feature, but 2048-d will result much more computation than 128-d.
But it's not using the 128-d layer either. It's using the final FC layer that has dimensions equal to the number labels. For example for market1501, it is 751.
I am also confused with this problem. Why does it use the final FC layer output as feature vector? In this way, the dimension of the feature vector is changing as the dataset. I think it should use the final FC layer input for feature vector. Have u dealt with it?
Hi, First thanks for this repo, it's really handy.
It looks to me this code uses the last FC layer as the feature vector for computing re-id scores. Shouldn't it use the previous layer for as the features? Am I missing something here?
Line 24 at evaluators.py doesn't provide any
modules
parameteroutputs = extract_cnn_feature(model, imgs)