samim

change in extract_features needed due to caffe update

1

This code line: features = out[net.outputs[0]].squeeze(axis=(2,3)) Has to be this in order to work with the newest caffe: features = out[net.outputs[0]] Additionally remove this line: caffe.set_phase_test()

Model?

1

Great work on this post/code! Was curios if you could release your pretrained model? Would be super fun to run a little experiment ;-) ie : f_emb = ModelIO.load('/home/luke/datasets/coco/predict/fullencoder_maxfeatures.50000') ie:...

Trainig code?

3

Great work! Are you planing on releasing the model training / fine-tuning code? Or is this not the case, as with AudioLDM1?