Hi, Cadene, why don't you update the feature extractor when training?

Hi, Cadene,

Thank you very much for your code, it's very helpful. But it seems that you use resnet as a seperate feature extractor instead of updating it when training the VQA model. Could I ask you the reason of that? Intuitively, it might give better results to train the feature extractor and the VQA model together, since the size of training data is not small.

Thank you in advance.

The issue asks why the ResNet feature extractor is separate from VQA model training, but it names no files, tests, or entry points. Trace the model and training setup to determine how the extractor is used, then define the intended behavior before considering any joint-training change.

Written by the indexing model from the issue text.