PixelRNNs are generative neural networks that sequentially predicts the pixels in an image along the two spatial dimensions. They model the discrete probability of the raw pixel values and encode the complete set of dependencies in the image. Variants include the Row LSTM and the Diagonal BiLSTM, that scale more easily to larger datasets. Pixel values are treated as discrete random variables by using a softmax layer in the conditional distributions. Masked convolutions are employed to allow PixelRNNs to model full dependencies between the color channels.
Source: Pixel Recurrent Neural NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Decoder | 2 | 20.00% |
Image Generation | 2 | 20.00% |
Gesture Recognition | 1 | 10.00% |
Hand Gesture Recognition | 1 | 10.00% |
Hand-Gesture Recognition | 1 | 10.00% |
Image Compression | 1 | 10.00% |
Conditional Image Generation | 1 | 10.00% |
Density Estimation | 1 | 10.00% |