Semi-supervised-learning
Semi-supervised-learning copied to clipboard
microsoft
A Unified Semi-Supervised Learning Codebase (NeurIPS'22)
I trained the FreeMatch algorithm on the audio datasets GTZAN and ESC-50. If I want to achieve its Top-5 performance, where should I test it? Can you provide relevant code?
Can the package work for multilabel class problem? I keep encountering error RuntimeError: Expected floating point type for target with class probabilities, got Long
 Look at this official configuration written by USB, which means that for every training epoch, it will perform 1024 iterations, and each iteration will use 8 labeled images. Therefore,...
I've noticed that in certain methods like PiModel and MeanTeacher, batch normalization is frozen during inference on unlabeled data. I'm curious about the rationale behind this decision. Unlike in FixMatch,...
In general how you decide the number of labels for each dataset? would you please provide the intuition behind the chosen numbers. and would you please guide me on how...
## About configs I would like to customize the usage of datasets and the duration of model training. Could you please tell me how to determine some of the hyperparameters...
When I was using the freematch algorithm to train on the esc50 dataset, I encountered the following problem:   I downloaded the relevant data of the model to a...
Bumps [requests](https://github.com/psf/requests) from 2.31.0 to 2.32.0. Release notes Sourced from requests's releases. v2.32.0 2.32.0 (2024-05-20) 🐍 PYCON US 2024 EDITION 🐍 Security Fixed an issue where setting verify=False on the...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Bumps [jinja2](https://github.com/pallets/jinja) from 3.1.2 to 3.1.4. Release notes Sourced from jinja2's releases. 3.1.4 This is the Jinja 3.1.4 security release, which fixes security issues and bugs but does not otherwise...