Feature mapping neural networks


I am new to PyTorch and need help for a video animation project. My dataset contains 3904x60 audio features(input) and corresponding 3904x3 video features(output). The goal is to train a neural network model such that given an unknown audio feature, the model maps it into its corresponding video feature. In other words, the neural network performs a 60 to 3 feature mapping. I have some experience in python but this is the first time I use PyTorch to build a neural network model. Any advice or tutorial will be appreciated! :slight_smile:

As suggested in this thread, it would be interesting to know, what kind of values you are using for the target tensor.
Are you dealing with float features or do you have a class target for each sample?