Open iaroslav-ai opened 8 years ago
This gist link shows how to transfer the trained alexnet model over to a network with only 10 outputs in the last fully connected layer. It may give enough information on how to get the feature extraction layers out of a VGG model and attach them to a different output network. let me know if that helps.
Could you add a code which extracts VGG features from images for image captioning task? This would be a nice starting point if someone wants to try playing with tuning the image captioning setup or just obtain image captions.