High-performance cross-platform MTCNN face detection with CUDA and Apple Neural Engine support
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Project description
pymtcnn
MTCNN face detection with CoreML (Apple Silicon) and CUDA support.
Installation
pip install pymtcnn
Usage
from pymtcnn import MTCNN
detector = MTCNN() # auto-selects best backend
boxes, landmarks = detector.detect(image)
What it does
- Detects faces and 5-point facial landmarks
- Auto-selects backend: CoreML on Mac, CUDA on NVIDIA, CPU fallback
- ~34 FPS on Apple Silicon, ~50 FPS on CUDA
Citation
If you use this in research, please cite:
Wilson IV, J., Rosenberg, J., Gray, M. L., & Razavi, C. R. (2025). A split-face computer vision/machine learning assessment of facial paralysis using facial action units. Facial Plastic Surgery & Aesthetic Medicine. https://doi.org/10.1177/26893614251394382
License
CC BY-NC 4.0 — free for non-commercial use with attribution.
Project details
Verified details
These details have been verified by PyPIProject links
GitHub Statistics
Maintainers
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file pymtcnn-1.1.5.tar.gz.
File metadata
- Download URL: pymtcnn-1.1.5.tar.gz
- Upload date:
- Size: 3.7 MB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
92794223306c5404b274ae0d68aeba7b153afe7845ba7aa2aca856c60f7b729f
|
|
| MD5 |
ee6142c7259d158d2110ca786a874a81
|
|
| BLAKE2b-256 |
51fcd98a5cd47e9babcfc3813c0bedcb009adff35557e3cd7a019109ded883ae
|
Provenance
The following attestation bundles were made for pymtcnn-1.1.5.tar.gz:
Publisher:
publish.yml on johnwilsoniv/pymtcnn
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
pymtcnn-1.1.5.tar.gz -
Subject digest:
92794223306c5404b274ae0d68aeba7b153afe7845ba7aa2aca856c60f7b729f - Sigstore transparency entry: 908619041
- Sigstore integration time:
-
Permalink:
johnwilsoniv/pymtcnn@c6edfeb17194aebaf1ebb54b633a275898128587 -
Branch / Tag:
refs/tags/v1.1.5 - Owner: https://github.com/johnwilsoniv
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@c6edfeb17194aebaf1ebb54b633a275898128587 -
Trigger Event:
release
-
Statement type:
File details
Details for the file pymtcnn-1.1.5-py3-none-any.whl.
File metadata
- Download URL: pymtcnn-1.1.5-py3-none-any.whl
- Upload date:
- Size: 3.7 MB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/6.1.0 CPython/3.13.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
61d760a950b4d74bc34cb1f801620e66665ddbdc78b5a081134a463f8985ef40
|
|
| MD5 |
e7545614b9d0999defc9761be63275c8
|
|
| BLAKE2b-256 |
4f1025cfd1af35cfbf325dda12cb682e6a6801eea93c99c82693aa9691721b81
|
Provenance
The following attestation bundles were made for pymtcnn-1.1.5-py3-none-any.whl:
Publisher:
publish.yml on johnwilsoniv/pymtcnn
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
pymtcnn-1.1.5-py3-none-any.whl -
Subject digest:
61d760a950b4d74bc34cb1f801620e66665ddbdc78b5a081134a463f8985ef40 - Sigstore transparency entry: 908619064
- Sigstore integration time:
-
Permalink:
johnwilsoniv/pymtcnn@c6edfeb17194aebaf1ebb54b633a275898128587 -
Branch / Tag:
refs/tags/v1.1.5 - Owner: https://github.com/johnwilsoniv
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@c6edfeb17194aebaf1ebb54b633a275898128587 -
Trigger Event:
release
-
Statement type:
