Comments (3)
Thanks for the feature request @Guitaricet . This has been a reccurent feature request for a while, but there is no current obvious path to support that just yet, as most kernel implementations are just not easily parallelizable over RNG. vmap
is a potential avenue, but last time I tried I ended up quickly blocked.
You'll see torchaug mentioned in #2929 (comment) which supports what you need. Some kernels are natively implemented with support for per-sample RNG, but for most transforms the batches are instead split into sub-batches, transformed and then re-concatenated, so it's more of a per-subbatch-RNG AFAIU. If you try it and it works for your use-case I'd love to hear it, and perhaps consider something simliar in torchvision (CC @juliendenize who's the author of torchaug).
from vision.
Hi thanks for the ping @NicolasHug , you're right about how Torchaug works it offers the flexibility to do per-subbatch-RNG when a per-sample RNG is not possible in Torch.
I'd like to also hearing from you @Guitaricet if you try it and if it works, I try to maintain it as much as I can and follow Torchvision advances but I'd need more feedback from users to make it better. I'd love it if eventually Torchvision could natively support such features 😄.
from vision.
Thank you, I will take a look!
from vision.
Related Issues (20)
- torchvision.datasets.mnist has a broken url in mirrors to download the dataset
- Allow ffmpeg-python backend for torchvision.io.write_video?
- RandomPhotometricDistort has undocumented channel shuffle feature HOT 1
- Runaway mask_loss for MaskRCNN when using non-binary mask. HOT 2
- Inconsistent Behavior with transforms.v2 for Multiple Arguments HOT 1
- adjust_hue broken on ARM64
- [Bug] Unable to build documentation on local machine HOT 2
- procrustes alignment for pytorch HOT 3
- Windows CUDA unittests jobs are failing
- Cant find nms function in code? HOT 1
- encode_jpeg generates noise when processing 4k image HOT 5
- size mismatch for rpn HOT 4
- SetupTools update breaks Vision Nightly aarch64 builds are failing for CPU and GPU HOT 3
- prioritize batching for torchvision::nms HOT 2
- ImportError: cannot import name 'datapoints' from 'torchvision.prototype' HOT 1
- crossvit vs vision transformer HOT 2
- GPU accelerated video loading with optimizations for reading at specific timestamps or time intervals HOT 1
- add typing to torchvision.models.detection.faster_rcnn HOT 2
- ConvertImageDtype not converting properly from uint8
- loss_box_reg increasing while training mask rcnn
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 vision.