-
Hello, I wonder your nll is correct?
In,
https://github.com/VLL-HD/conditional_invertible_neural_networks/blob/master/mnist_minimal_example/eval.py#L44-L45
I think, your z is the latent varia…
-
### 🐛 Describe the bug
first in apex kernel, the kernel is registered as torch recommand way.
use setup.py codegen static register function to support custom op
``` python
CUDAExtension(
…
-
### 🐛 Describe the bug
I'm testing activation checkpointing on FSDP models, to my surprise, PyTorch's native checkpoint_wrapper seems not working at all, not saving any memory whatsoever, I switched …
-
Dear Ting,
Thanks for adding the TF2 SavedModels. Looks like the `trainable_variables_list' for the SavedModels are empty, and I cannot finetune the full network from these SavedModels. Is there…
-
# Feature or enhancement
### Proposal:
I'd like to add a `resolve_lexical` method to concrete `pathlib` objects:
```
def resolve_lexical(self, /, strict=False):
"""Make the path absolut…
-
Can diffusion model be used into image to image translation ?
-
There's lots of duplicate data in our dataset config file and normalizing it will greatly improve maintainability, increase flexibility, and reduce the physical size of the file. Specifically, the var…
-
Hi,
I am trying to reproduce your results, and am wondering how long does it take to train the nsf-v3 model on a single speaker (CMU US SLT).
I want to know after approximately how many iteratio…
-
Recently we've been doing work on the state tracking in the Preroll, Paint, and hopefully soon Diff methods and we noticed that Paint will sometimes pixel snap the transform, but Preroll does not (and…
-
* Restructure code.
* Add pooling layers. (max pooling is covered with the gradient, sum pooling should work with LRP rules; means need to add reverse hook).
* Add merge layers; i.e. add reverse hoo…