fastai-faceshape
Trying out the basic fastai things with notebooks
Science Score: 18.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.9%) to scientific vocabulary
Repository
Trying out the basic fastai things with notebooks
Basic Info
- Host: GitHub
- Owner: cadolphs
- License: mit
- Language: Python
- Default Branch: main
- Size: 18.8 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
fastai-faceshape
Trained a fastai model for face shape detection in a Kaggle Notebook for fast iteration.
Then uploaded the fastai learner to HuggingFace
To use the model in a gradio web interface, just clone the repo, install the requirements (modal), get a HuggingFace token and do
MODAL_GPU=ANY modal serve simple_script.py
to get a web endpoint where you can upload images.
Note: The latest version of gradio has nice features like webcam integration, but, for some reason, was hanging when I tried to run the inference. So I downgraded it to ~ 3.6.
Owner
- Name: Clemens Adolphs
- Login: cadolphs
- Kind: user
- Repositories: 2
- Profile: https://github.com/cadolphs
Citation (CITATIONS)
Kitsuchart Pasupa, Wisuwat Sunhem, Chu Kiong Loo, A Hybrid Approach to Building Face Shape Classifier for Hairstyle Recommender System, Expert Systems With Applications (2018), doi: https://doi.org/10.1016/j.eswa.2018.11.011