apply roi tanh warping in tensorflow for face parsing
Project description
roi_tanh_warping_tensorflow
This is a tensorflow re-impelementation of the Face Parsing With RoI Tanh-Warping paper published at CVPR 2019. This is intended to be used for face-parsing training in tensorflow.
Install
you can use pip install roi-tanh-tensorflow
How to use
The main function to call from src.tanh_warper is apply_roi_tanh_warping. This function works as follows
from roi_tanh.tanh_warper import apply_roi_tanh_warping
apply_roi_tanh_warping(image: np.ndarray, label: np.ndarray, size:Tuple[int])
The expected input are a single image and its corresponding label.
run a unit test
python -m src.roi_tanh.tanh_warper --unit_test
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 roi_tanh_tensorflow-0.0.4.tar.gz.
File metadata
- Download URL: roi_tanh_tensorflow-0.0.4.tar.gz
- Upload date:
- Size: 9.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c85ee656174234c7c54bdaf0f4e8955f4c09da3470e8279c0aa40d46aa203135
|
|
| MD5 |
cda3807b59fcf917876f7a725ed3f486
|
|
| BLAKE2b-256 |
6c0dcc0fd36e2cdb391bca92fb4916e7fff6c5ee4f6e522d59eac808b7fd8cae
|
File details
Details for the file roi_tanh_tensorflow-0.0.4-py3-none-any.whl.
File metadata
- Download URL: roi_tanh_tensorflow-0.0.4-py3-none-any.whl
- Upload date:
- Size: 11.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.9.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b994e75566d37bb47470ec24b7b4e2e224c37d7693d36f243b96e9264b5c85ca
|
|
| MD5 |
78751284eea837b04814701a3d893e24
|
|
| BLAKE2b-256 |
f2dbc4e16052c9943ebb74e44c01b51f742ee6bf4268a9e965c01dc805b8adb0
|
