Comments (7)
hanzhanggit
commented on July 28, 2024
When I dig into the code, I find the major issue is due to
features = self.resnet(images)
But I don't know why pytorch 0.11 takes much more memory compared to pytorch 0.10 for the basic CNN models.
from pytorch-tutorial.
hanzhanggit
commented on July 28, 2024
I also post this problem here
from pytorch-tutorial.
yunjey
commented on July 28, 2024
This is PyTorch version issue. You can see here. You can solve this problem if you use Python 3.5 instead of 2.7. Also, you can fix this problem by replacing 'requires_grad' to 'volatiles'.
This issue is automatically resolved when a new version of PyTorch is released.
from pytorch-tutorial.
hanzhanggit
commented on July 28, 2024
Hi,
Thanks for the reply. It seems that the problem is still there for pytorch
0.1.12. In addition, for my user case, I need to fine-tune on top of resnet
models, I think the volatiles did not work for since it will neglect all
the grad for the whole network.
Best,
Han
2017-04-27 20:38 GMT-04:00 yunjey <[email protected]>:
β¦ This is PyTorch version issue. You can see here
<https://discuss.pytorch.org/t/params-requires-grad-false-has-elevated-memory-usage-in-v0-1-11/1625>.
You can solve this problem if you use Python 3.5 instead of 2.7. Also, you
can fix this problem by replacing 'requires_grad' to 'volatiles'.
This issue is automatically resolved when a new version of PyTorch is
released.
β
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub
<#26 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AXeZrzrWvAjcHzIPCwPQ9OWQuvthCBXhks5r0TTsgaJpZM4NKbFv>
.
from pytorch-tutorial.
karandwivedi42
commented on July 28, 2024
+1 Using pytorch 0.1.12 on python 3.6, the problem still exists.
Edit: Issue has been solved in master branch. Will be a part of next release.
from pytorch-tutorial.
jtoy
commented on July 28, 2024
great, looking forward to testing this. I think im running into a similar issue.
from pytorch-tutorial.
yunjey
commented on July 28, 2024
Now, i fixed this issue using volatile and children.
from pytorch-tutorial.
Related Issues (20)
- Issues in running tensorboard tutorial HOT 1
- Initialize DecoderCNN in Image captioning
- Some problems occurred when I used model evaluation
- RuntimeError in Logistic Regression python file
- Using LSTM method in Python
- size mismatch for pretrained models HOT 2
- pytorch
- No Jupyter Notebooks. HOT 1
- About the learning method of neural_style_transfer
- Does anyone know the source code of channel calculation in pytorch?
- make ur repo cloneable and not editable by anyone.
- TypeError: conv2d(): argument 'input' (position 1) must be Tensor, not tuple HOT 1
- AttributeError: module 'torch.nn' has no attribute 'linear' HOT 2
- ValueError: num_samples should be a positive integer value, but got num_samples=0 HOT 1
- main.py failed HOT 2
- some question about the position of 'optimizer.zero_grad()' HOT 4
- Pytorch tutorial HOT 1
- How can I get a PDF version of the tutorial HOT 2
- Cuda is true why don`t use itοΌ
- GNN model
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pytorch-tutorial.