self_supervised
self_supervised copied to clipboard
Implementation of popular SOTA self-supervised learning algorithms as Fastai Callbacks.
Bumps [nokogiri](https://github.com/sparklemotion/nokogiri) from 1.13.2 to 1.14.3. Release notes Sourced from nokogiri's releases. 1.14.3 / 2023-04-11 Security [CRuby] Vendored libxml2 is updated to address CVE-2023-29469, CVE-2023-28484, and one other security-related issue....
Bumps [activesupport](https://github.com/rails/rails) from 6.0.3.2 to 6.0.6.1. Release notes Sourced from activesupport's releases. v6.0.6.1 Active Support No changes. Active Model No changes. Active Record Make sanitize_as_sql_comment more strict Though this method...
arch = "xresnet34" encoder = create_encoder(arch, pretrained=False, n_in=3) AttributeError: 'function' object has no attribute 'children'
I wanted to try `arch = 'tresnet_m_miil_in21k' encoder = create_encoder(arch, pretrained=True, n_in=3)` But got this error `Traceback (most recent call last): File "train_affectnet_simclr.py", line 58, in model = create_simclr_model(encoder, hidden_size=2048,...
Bumps [addressable](https://github.com/sporkmonger/addressable) from 2.7.0 to 2.8.1. Changelog Sourced from addressable's changelog. Addressable 2.8.1 refactor Addressable::URI.normalize_path to address linter offenses (#430) remove redundant colon in Addressable::URI::CharacterClasses::AUTHORITY regex (#438) update gemspec to...
Thanks for the library, I'm really looking forward to use it, but I ran into some problems with the intro tutorial. I tried running the intro_tutorial.ipynb on google_colab. There are...
Bumps [tzinfo](https://github.com/tzinfo/tzinfo) from 1.2.7 to 1.2.10. Release notes Sourced from tzinfo's releases. v1.2.10 Fixed a relative path traversal bug that could cause arbitrary files to be loaded with require when...
**Describe the bug** SupCon module doesn't exist in pip installation, nor in github release archive. Although it does exist in [github](https://github.com/KeremTurgutlu/self_supervised/blob/main/self_supervised/vision/supcon.py) and the docs still exist. **To Reproduce** Steps to...
Two Typography errors were found in the Barlow-twin import of the README file and Index.ipynb notebook. I have replaced `from self_supervised.vision.simclr import *` with `from self_supervised.vision.barlow_twins import *`
Is it possible to train the model with multi GPUs? It looks can't work with learn.distrib_ctx():