Brian Davis

It should work fine to just train a normal autoencoder. The thought was that including hwr as part of the encoder's task would force it to learn character features. Including...

This is just trying to train the handwriting recognition network, right? Things to try: 1. Be sure the images are getting resized correctly (64 pix height) 2. GPU size. I'd...

The charset file defines the characters the model can see and produce. Besure each model component gets `data_loader: char_file` updated in the config and are trained. Also be sure to...

I had modified someones FID code to resize handwriting images properly: https://github.com/herobd/pytorch-fid-handwriting You'll need to generate a bunch of handwriting images (which I think was the point of the `Random`...

Hmm, double check the charset.json to be sure it looks like mine (especially starting at index of 1 instead of 0). If nothing's wrong I would print the inputs to...

Input length is the image width (after downsampling), the target length is the length of the target string. The model predicts something for each image unit (after the network downsamples...

You're referring to the output images? Your're sure it's writing new images? I've never seen it generate blank images. Generally at the beginning of training it generates weird blurry images.

What do the losses look like? You can use `python graph.py -c path/to/latest/snapshot.pth` to graph them.

Also, do you have any of the generated ("_samples_") images from the beginning of training?

Maybe turn down the learning rate? It would be good to see what the loss is doing.