-
Weight pruning seems to be a valuable tool to improve neural networks' ability to generalize by throwing away those parts (weights) of the network which do not significantly contribute to convergence …
-
I am developing gpu friendly app , to do so I aimed for pruning the model weights to reduce gpu memory usage and increase speed
pruning strategy
`parameters_to_prune = (
(generator.dense_m…
-
Hi!
weights and its gradients are set to 0 in the code which i think is different from real pruning.
-
## Type of question
**how to implement a specific feature, or about general context and help around the operator-sdk**
## Question
**What did you do?**
```
type MyJobSpec struct {
/…
-
## 🐛 Bug
Given a a subclass of nn.module which has nn.Sequential() parameters. If we register a pruning method on a subset of those parameters, deep_copy fails.
## To Reproduce
Steps to repro…
-
Hi
I have a pangenome graph spanning 20 different genomes for each chromosome I produced using PGGB.
I also have high and low coverage genomic short reads from many other different cultivars.
…
-
## 🐛 Bug
## To Reproduce
Steps to reproduce the behavior:
1. Add identity pruning to a module's weight to reparameterize it
1. Call `register_forward_pre_hook` to register additional hoo…
-
## 🐛 Bug
After calling `torch.nn.utils.prune.remove` on a parameter, future calls to `loss.backward()` result in:
```
RuntimeError: Trying to backward through the graph a second time, but the buf…
-
Hi,
Thanks for making the code public! I'm wondering if you plan to further make the code for Appendix C.9 (the structured pruning) public? If that's not the case, can you elaborate on what adaptat…
-
## 🚀 Tensor and nn.Module Pruning
Tensor method and/or `nn` util to sparsify tensors and/or model, according to various pruning techniques in the literature.
## Motivation
State-of-the-art deep …