About
This is a collection of image segmentation projects adjusted for fundus blood vessel segmentation.
1. unet_keras result:
2. unet_torch result:
4. mrsg_torch result (sota):
Run
Provide four flavors:
| Module | How to run | Model weights location | Notebooks |
|---|---|---|---|
| model.unet_keras | run_training.py, run_testing.py | test/test_best_weights.h5 | 1. U-Net - Introduction.ipynb, 2. Fundus Blood Vessel Segmentation.ipynb |
| model.unet_torch | train.py, test.py | weights/checkpoint.pth | README.md |
| model.multiple_torch | all codes are inside .ipynb files | best_binclass_model.h5, best_multiclass_model.h5 | 1. binary segmentation (camvid).ipynb and 2. multiclass segmentation (camvid).ipynb |
| model.mrsg_torch | python train.py --cfg lib/All.yaml, python inference.py --lib/DRIVE.yaml | results/test/ALL/model/*.pth | README.md |
Credits
The following github projects are used:
| Module | based on | url |
|---|---|---|
| model.unet_keras | Retina blood vessel segmentation with a convolution neural network (U-net) | https://github.com/orobix/retina-unet |
| model.unet_torch | Retina-Blood-Vessel-Segmentation-in-PyTorch | https://github.com/nikhilroxtomar/Retina-Blood-Vessel-Segmentation-in-PyTorch |
| model.multiple_torch | Python library with Neural Networks for Image Segmentation based on Keras and TensorFlow. | https://github.com/qubvel/segmentation_models |
| model.mrsg_torch | Retinal Vessel Segmentation with Pixel-wise Adaptive Filters (ISBI 2022) | https://github.com/Limingxing00/Retinal-Vessel-Segmentation-ISBI2022/ |
Todo
make a thorough refactor; vessel region detection
1 maintainer
Metadata
1 maintainer
Release files for seg 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| seg-0.0.1.tar.gz | 53.3 MB | Without provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| seg-0.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 106.6 MB
Release files / seg-0.0.1.tar.gz
| Download URL | seg-0.0.1.tar.gz |
|---|---|
| Size | 53.3 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
57eed765e1d18d55c185da2f093f771791adc8dc53af786320f514a3c9b8cc63
|
|
BLAKE2b-256 checksum How to use checksums |
b6d69482f6cd8ebbeb71b7d83b0fdbec1e5b0d91947343295943a004be5829cb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.12
|
Release files / seg-0.0.1-py3-none-any.whl
| Download URL | seg-0.0.1-py3-none-any.whl |
|---|---|
| Size | 53.3 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
eabbfa5023d40d978e6cb5c2bf3cd295ebed7f62db30edc7607eea63b453d1b6
|
|
BLAKE2b-256 checksum How to use checksums |
eb753bc48ea2c55f432c6510574feec1ba25ff17374a0e243e21fcb1e8e785ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.1 CPython/3.9.12
|
Security for seg 0.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
