library that made for besuto and made by besuto
Project description
this is library nade for besuto and made by besuto REFERENCE
MTCNN - used for face detection - source : https://github.com/ipazc/mtcnn VGGFACE - used for face feature extraction - papers : https://www.robots.ox.ac.uk/~vgg/publications/2018/Cao18/cao18.pdf - source : https://github.com/rcmalli/keras-vggface?fbclid=IwAR0wOMKDbjdQjNULYziO78RZM3dBkRJ4vCgjyZcVXffbgQYO9Ui4QDAhTIw UPDATE LOG
besuto 0.0.1 unfinished release to learn Pypi upload machanic
besuto 0.0.2 realease the image Augmentation function (for my school project) and face extracttion which use pretrain model in mtcnn library
besuto 0.0.3 realease the pipeline for training all VggFace model from the paper https://www.robots.ox.ac.uk/~vgg/publications/2015/Parkhi15/parkhi15.pdf https://www.robots.ox.ac.uk/~vgg/publications/2018/Cao18/cao18.pdf
besuto 0.0.4 fix bug that keras_application is not found
besuto 0.0.5 - fix corrupted ui in load_face_dataset function - fix functional type error in trains function
besuto 0.0.6 - fix loop massage problem in Augmentation (can be solve by add %%capture at the top of that cell in jupyter notebook) - write library doc and instruction (writed some of them)
besuto 0.0.7 - add faces feature extractor in augment module
besuto 0.0.8 - 0.0.7 but not bug
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file besuto-0.0.9.tar.gz
.
File metadata
- Download URL: besuto-0.0.9.tar.gz
- Upload date:
- Size: 3.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.0 importlib_metadata/3.7.2 packaging/20.9 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.8.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 91a4d2365faaab3e4eb5d2377d899cdc435438a037d480c7523429cce56794ee |
|
MD5 | 8157a39afa1b8d93c2b27503c9d97bf0 |
|
BLAKE2b-256 | 04b0793b961307f4942a2cbe1b1da602ce850bca5fc652d5151c3fe212e6d041 |