Comments (3)
Dear @HKQX,
Thank you for your interest in our work. Doing separate backward passes for different inputs (source images and mixed images) allows freeing the first compute graph after the first backward, which reduces the overall GPU memory consumption compared to one backward pass of the accumulated loss. This is a similar concept to gradient accumulation:
- https://pytorch-lightning.readthedocs.io/en/stable/advanced/training_tricks.html#accumulate-gradients
- https://kozodoi.me/python/deep%20learning/pytorch/tutorial/2021/02/19/gradient-accumulation.html#:~:text=Gradient%20accumulation%20modifies%20the%20last,been%20processed%20by%20the%20model.
Best,
Lukas
from daformer.
Dear @HKQX,
Thank you for your interest in our work. Doing separate backward passes for different inputs (source images and mixed images) allows freeing the first compute graph after the first backward, which reduces the overall GPU memory consumption compared to one backward pass of the accumulated loss. This is a similar concept to gradient accumulation:
- https://pytorch-lightning.readthedocs.io/en/stable/advanced/training_tricks.html#accumulate-gradients
- https://kozodoi.me/python/deep%20learning/pytorch/tutorial/2021/02/19/gradient-accumulation.html#:~:text=Gradient%20accumulation%20modifies%20the%20last,been%20processed%20by%20the%20model.
Best, Lukas
Thank you for your reply.When I run the code, I find that the data of src.loss_imnet_feat_dist is nan. The reason for nan is that during the calculation of Thing-Class ImageNet Feature Distance (FD), this image does not contain these classes [6, 7, 11, 12, 13, 14, 15, 16, 17, 18]. Have you noticed this problem? And the memory usage is close to 12G, 2080ti should not be able to complete the code running,do you need to adjust anything? Looking forward to your reply
from daformer.
Please, have a look at issue #11 regarding nan in the FD loss. I am able to run this repository on an RTX 2080 Ti. It's tight but it fits.
from daformer.
Related Issues (20)
- MiT-B3 log HOT 1
- T-SNE code HOT 2
- Model for validation HOT 1
- Unable to reproduce results
- About the threshold HOT 1
- how to loader different images from one dataloader.
- resizing to 1024,512 cityscape HOT 1
- why use cityscapes_half_512x512.py need more GPU memory? HOT 1
- Training weights cannot be downloaded HOT 10
- Global understanding of the `forward_train` function in dacs.py
- Google Drive Download Seems down HOT 1
- Questions about CNNs-based results better than Transformer-based results HOT 7
- Question about default .py for config HOT 1
- Classes for Palette for DarkZurich
- Save intermediate weight, and resume training
- decode.loss_seg and mix.decode.loss_seg
- synthia dataset get unexpected json
- test.sh: 4: Bad substitution
- MIT weight无法获得 HOT 3
- using mask in one_mix method in mmseg/models/utils/dacs_transforms.py
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 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. 📊📈🎉
-
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 ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from daformer.