This section deals with the use of the list loss function to train a neural net to generate an embedding of images. The embedding of images is thus used to idenitfy images that are similar for image search purposes
run the scripts in train_tiny_scripts to generate an initial model that learns "shape" features and such to distinguish between natural images
run train_med_scripts to run training on the medical image dataset. Should provide a prevState variable to the bash scripts pointing to the last checkpoitn of step 1
Run bash script that loads model from step2 and generates embeddings of the data in the embeddigns folder
TODO 1. MAP across categories 2. gradCAM visualization of activation layers 3. TSNE plots of embedding space?