cae
cae copied to clipboard
Compressive Autoencoder.
Extracted from #29: - [ ] Reconstruction quality - [ ] Different latent sizes
Easily store the latent representation of the image into a custom file format: ``` : number of H patches, number of W patches, patch size ```
Hello. When I run the test.py, the only thing I can get is the decoded image, but I want to know the compression ratio, so could you please tell me...
```python cae = CAE( latent_size=(32, 32, 32), padding=PADDING.zero, ) ``` --- - [ ] latent size - [ ] padding type
I saw from ur readme doc that you take ~100k images for training. I would like to know more abt the training details, such as: 1. What is the resolution...
Hello and thank you for sharing your good repository. With attention, I can see a plaid pattern in reconstructed images which I believe is the result of patching the image...