-
Hi, I have been running your code with the option `-activation_function=1`, i.e. with ReLUs according to the README. However, I noticed that binning for mutual info calculation is performed in between…
-
Hello, could you tell me what the meaning of "color-levels" is?
-
In the paper they generated images for a given imagenet class, but in the model architecture they dont specify where you input the class id to the model huh
-
As I told in #125, I've made a revision of this project where a feed the model using the gray-scale channel of a dataset of images (similar **but no equal** to what DeepMind made with **PixelCNN**).
…
-
Hi,
just now I successfully ran the train_pixelsnail.py on the top levels (size: 8×8) of my own dataset, which consists of 300,000 encoded outcome from images (size: 64×64) of different sizes, rotati…
-
As I understand it, implementing function transformations final-style should be preferred over initial-style whenever possible because the latter (while being more general) usually results in more com…
-
Observations:
1. The reconstruction image is not good.
2. In the current code, the training procedure is very unstable.
3. The dictionary loss (the commitment loss) decreases initially, but signi…
-
First of all thank you for making all of the lectures and other content public. This is really helpful.
I took a look at the demo implementations for lecture 3 and found some bugs which I am report…
-
Hello,
Thank you for providing this fantastic repository.
I noticed that after fitting my PixelCNN model, in `pythae/samplers/pixelcnn_sampler/pixelcnn_sampler.py` it seems to delete the trainin…
-
Hello again,
Thanks again for the great work. I had another question in regards to the sampling function inside of the PixelCNNSampler located in `pythae/samplers/pixelcnn_sampler`. I noticed that …