-
Hey, Youngjoon. Nice code!
Did you reproduct the similar result with that paper?
-
I have been trying to use the `shap.DeepExplainer` with a `self-attention residual convolutional neural network` (implemented in `pytorch`) using a `3D input` (example, feature, time) - the model perf…
-
### 🐛 Describe the bug
Issue summary:
As part of process to add CUDA ARM nightly wheel, we are seeing long build compilation time. Needs ~5hrs to compile https://github.com/pytorch/pytorch/actio…
-
### 🐛 Describe the bug
AMP consumes about 30x gpu memory when used on `bmm`.
Code:
```
import torch
import torch.nn as nn
class MyModule(nn.Module):
def __init__(self):
super…
Teoge updated
2 years ago
-
### 🐛 Describe the bug
original issue: https://github.com/pytorch/pytorch/issues/98796
There was a PR to fix it: https://github.com/pytorch/pytorch/commit/a54043516fad1a37134f280f3e75f85a5b2daa13
…
-
Hi
Thanks for the excellent repo. I was wondering what's the status of this repo for Pytorch v1.3. I want to use the Newton-CG method using line search to reimplement a meta-learning paper. Will y…
-
### 🐛 Describe the bug
I'm trying to generate a TensorRT engine of `RetinaNet` that uses `GeneralizedRCNNTransform`. By bypassing a couple of layers, it works fine for a static batch size. However, w…
-
## 🐛 Bug
At the forward step, pass a small ResNet model occupies me more than 15G GPU with torch1.8. Torch1.6 does not have this issue using the same code.
## To Reproduce
Steps to reproduce …
-
### 🐛 Describe the bug
## Description
Hi there,
I would like to get per-sample gradients (application: transformer classifier for text). in a preliminary test, I noticed that when computing the…
-
Hello everyone,
When generating a bitstream for my CNN model I seem to run into the problem of no model being generated using vitis AI 3.5, however I do not seem to get any error message. Could any…