Comments (7)
VarNet only works with batch size 1, that is per GPU. This is because the slices have varying size. If you want to increase mini-batch size, that is number of training examples averaged per gradient update just increase the number of GPUs used for training.
from fastmri.
This is a good point. I believe 32 GPUs were used.
from fastmri.
Thank you for the info. Have you experimented with how to adjust the learning rate with different batch sizes, or how much impact it has on reconstruction quality? Intuitively, I would use a factor of N lower learning rate for a factor of N less GPUs (smaller batch size), but this would require some trial-and-error to figure out. I'm interested because I want to reproduce the results from the paper, but don't have access to 32 GPUs. Thanks again.
from fastmri.
I don't have much experience myself. I've gotten up to about 0.914 SSIM with two GPUs and the same learning rate and a smaller model for testing the repository refactor. Your strategy for lowering the learning rate by the GPU factor seems like a reasonable one.
from fastmri.
Keeping the learning rate the same would be my recommendation, but you should consider reducing the number of layers, otherwise it's not going to be train in a reasonable amount of time.
from fastmri.
Okay, thanks for the input. I am going to experiment with model size and if the number of GPUs have an effect on SSIM. I'm closing this issue now.
from fastmri.
However, when I tried to train VarNet with batch_size = 2, it shows the error in the validation sanity check:
...
237, in get_low_frequency_lines
while mask[..., r, :]:
RuntimeError: bool value of Tensor with more than one value is ambiguous
Do you have any idea? Thanks!
from fastmri.
Related Issues (20)
- Allow the data objects (module and dataset) to filter on contrast HOT 3
- Error related to raw_sample_filter in _create_data_loader HOT 3
- torch.eig is deprecated for a long time and is being removed HOT 4
- Error related to raw_sample_filter in _create_data_loader
- Problems with AnnotatedSliceDataset class HOT 3
- Unable to view public leaderboard submissions on the website HOT 2
- train_unet_demo produces wrong image HOT 1
- Unable to submit results to brain track HOT 1
- Unable to view public leaderboard submissions on the website HOT 2
- Tiny fastMRI data split proposal HOT 1
- A upgrade to PytorchLightning 2.0 and PyTorch 2.0 HOT 2
- Wrong annotations in AnnotatedSliceDataset HOT 5
- Training abruptly crashes on single GPU HOT 5
- Issue with argparse in PyTorch Lightning v2 HOT 1
- conda-forge build of fastmri? HOT 6
- Corrupted file for brain DICOM data HOT 2
- 'ExperimentWriter' object has no attribute 'add_image' HOT 4
- AttributeError: Can't pickle local object 'SliceDataset.__init__.<locals>.<lambda>' HOT 3
- TypeError: slice indices must be integers or None or have an index method
- Pre-trained model weights no longer available
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 fastmri.