Corpus ID: 49585114

OTHER MODIFICATIONS

@inproceedings{Karpathy2016OTHERM,
  title={OTHER MODIFICATIONS},
  author={A. Karpathy},
  year={2016}
}
PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at https://github.com/openai/pixel-cnn. Our implementation contains a number of modifications to the original model that both simplify its structure and improve its performance. 1) We use a discretized logistic mixture likelihood on the pixels, rather than a 256-way softmax, which we find to speed up training. 2) We condition on… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 20 REFERENCES
Conditional Image Generation with PixelCNN Decoders
Generative Image Modeling Using Spatial LSTMs
U-Net: Convolutional Networks for Biomedical Image Segmentation
Pixel Recurrent Neural Networks
NICE: Non-linear Independent Components Estimation
Wide Residual Networks
Video Pixel Networks
...
1
2
...