-
[CS 520](https://web.stanford.edu/class/cs520/)
* [Introduction](https://web.stanford.edu/class/cs520/abstracts/re.html)
* [Slides](https://web.stanford.edu/class/cs520/abstracts/re.pdf)
* [Video…
-
> the turbo model is an optimized version of large-v3 that offers faster transcription speed with a minimal degradation in accuracy.
[openai/whisper: Robust Speech Recognition via Large-Scale Weak …
-
Benchmark the selected experiments described in:
[Balakrishnan, G., Zhao, A., Sabuncu, M.R., Guttag, J. and Dalca, A.V., 2019. Voxelmorph: a learning framework for deformable medical image registrati…
-
-
**Is your feature request related to a problem? Please describe.**
We've just implemented the confidence distribution chart, which shows you how your weak supervision confidence is distributed amongs…
-
I tried training for Weak supervision using the SynthText Strong supervision model on a custom data set.
I trained for just three epochs with 1000 iterations each but when I use the models that get…
-
**Is your feature request related to a problem? Please describe.**
I had annotated data through weak supervision rules, which I really love, however, having many rules can be complex and combining th…
-
Label the data by some heuristic functions (like regular expression).
This feature is inspired by [snorkel](https://github.com/HazyResearch/snorkel).
![image](https://user-images.githubusercontent…
-
**Is your feature request related to a problem? Please describe.**
During annotation, I would like to have the option to select a buttons for a active creation of weak-supervision rules during annota…
-
May I ask if the config here performs full supervision or weak supervision?
`python main.py -c config/s3dis/randla_erda.yaml --gpus 2`
with `pseudo-fout-pmlp2-mom-Gsum-normdot-w.1`
In head.py we…