glow
glow copied to clipboard
openai
Code for reproducing results in "Glow: Generative Flow with Invertible 1x1 Convolutions"
In the paper, the objective function to minimize is  However in the code, objective first add this constant **_c_**, **_logpz_**, and then apply a negative sign to the objective...
It seems there is an error in the NLL computations on MNIST. The article reports NLL in "bits per pixels". The "per pixel" part is computed by dividing by the...
Bumps [pillow](https://github.com/python-pillow/Pillow) from 5.2.0 to 6.2.0. Release notes *Sourced from [pillow's releases](https://github.com/python-pillow/Pillow/releases).* > ## 6.2.0 > https://pillow.readthedocs.io/en/stable/releasenotes/6.2.0.html > > ## 6.1.0 > https://pillow.readthedocs.io/en/stable/releasenotes/6.1.0.html > > ## 6.0.0 > No release...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
hi, https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L576-L584 Why use cross h to get mean and logs? Is there any difference to get mean and logs from its contiguous splits of h? I guess maybe you...
Hi, there! I am trying to calculate the log-likelihood of data points. To do so, I directly modified the provided loss function: Then, I tested it on the cifar-10 dataset,...
https://github.com/openai/glow/blob/eaff2177693a5d84a1cf8ae19e8e0441715b82f8/model.py#L552 this is equivalent to evaluate (z-mean)/scale on a standard Gaussian, but you didn't account for the determinant of this transformation.
It seems that the MNIST images are tiled so they have three (identical) color channels, matching the CIFAR-10 format (data_loaders/get_mnist_cifar, lines 43-44:) `x_train = np.tile(np.reshape(x_train, (-1, 32, 32, 1)), (1,...
The article briefly describe the architecture, and refer to Real NVP for more details.  This lead me to believe Glow implemented the Squeeze operation as done by Real NVP....
Hi, I am trying to train the glow model on CIFAR-10. I only have one gpu. It seems that it take me one day to train only 50 epochs. Is...
