ocr-vqgan
ocr-vqgan copied to clipboard
OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from VQGA...
Results
2
ocr-vqgan issues
Sort by
recently updated
recently updated
newest added
Hi! I attempted to train the model using the main.py script. The script starts off well but seems to get stuck when attempting to download the ocr_craft model. There's no...
Thank you for sharing the code,I used taming-tranformer to did the image reconstruction for Street View,but smaller text sections don't work well. If i use this model to train this...