Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: xinntao/facexlib
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: master
Choose a base ref
...
head repository: OpenTalker/facexlib
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: master
Choose a head ref
Able to merge. These branches can be automatically merged.
  • 4 commits
  • 4 files changed
  • 1 contributor

Commits on Aug 22, 2023

  1. Update awing_arch.py

    vinthony authored Aug 22, 2023
    Copy the full SHA
    7a9f72e View commit details

Commits on Aug 23, 2023

  1. Update README.md

    vinthony authored Aug 23, 2023

    Verified

    This commit was signed with the committer’s verified signature. The key has expired.
    addaleax Anna Henningsen
    Copy the full SHA
    6caa32b View commit details

Commits on Sep 16, 2023

  1. Update __init__.py

    vinthony authored Sep 16, 2023
    Copy the full SHA
    dcb9af0 View commit details

Commits on Oct 18, 2023

  1. Update VERSION

    vinthony authored Oct 18, 2023
    Copy the full SHA
    77a44db View commit details
Showing with 7 additions and 44 deletions.
  1. +4 −41 README.md
  2. +1 −1 VERSION
  3. +1 −1 facexlib/alignment/__init__.py
  4. +1 −1 facexlib/alignment/awing_arch.py
45 changes: 4 additions & 41 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,41 +1,4 @@
# ![icon](assets/icon_small.png) FaceXLib

[![PyPI](https://img.shields.io/pypi/v/facexlib)](https://pypi.org/project/facexlib/)
[![download](https://img.shields.io/github/downloads/xinntao/facexlib/total.svg)](https://github.com/xinntao/facexlib/releases)
[![Open issue](https://img.shields.io/github/issues/xinntao/facexlib)](https://github.com/xinntao/facexlib/issues)
[![Closed issue](https://img.shields.io/github/issues-closed/xinntao/facexlib)](https://github.com/xinntao/facexlib/issues)
[![LICENSE](https://img.shields.io/github/license/xinntao/facexlib.svg)](https://github.com/xinntao/facexlib/blob/master/LICENSE)
[![python lint](https://github.com/xinntao/facexlib/actions/workflows/pylint.yml/badge.svg)](https://github.com/xinntao/facexlib/blob/master/.github/workflows/pylint.yml)
[![Publish-pip](https://github.com/xinntao/facexlib/actions/workflows/publish-pip.yml/badge.svg)](https://github.com/xinntao/facexlib/blob/master/.github/workflows/publish-pip.yml)

[English](README.md) **|** [简体中文](README_CN.md)

---

**facexlib** aims at providing ready-to-use **face-related** functions based on current SOTA open-source methods. <br>
Only PyTorch reference codes are available. For training or fine-tuning, please refer to their original repositories listed below. <br>
Note that we just provide a collection of these algorithms. You need to refer to their original LICENCEs for your intended use.

If facexlib is helpful in your projects, please help to :star: this repo. Thanks:blush: <br>
Other recommended projects: &emsp; :arrow_forward: [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) &emsp; :arrow_forward: [GFPGAN](https://github.com/TencentARC/GFPGAN) &emsp; :arrow_forward: [BasicSR](https://github.com/xinntao/BasicSR)

---

## :sparkles: Functions

| Function | Sources | Original LICENSE |
| :--- | :---: | :---: |
| [Detection](facexlib/detection/README.md) | [Pytorch_Retinaface](https://github.com/biubug6/Pytorch_Retinaface) | MIT |
| [Alignment](facexlib/alignment/README.md) |[AdaptiveWingLoss](https://github.com/protossw512/AdaptiveWingLoss) | Apache 2.0 |
| [Recognition](facexlib/recognition/README.md) | [InsightFace_Pytorch](https://github.com/TreB1eN/InsightFace_Pytorch) | MIT |
| [Parsing](facexlib/parsing/README.md) | [face-parsing.PyTorch](https://github.com/zllrunning/face-parsing.PyTorch) | MIT |
| [Matting](facexlib/matting/README.md) | [MODNet](https://github.com/ZHKKKe/MODNet) | CC 4.0 |
| [Headpose](facexlib/headpose/README.md) | [deep-head-pose](https://github.com/natanielruiz/deep-head-pose) | Apache 2.0 |
| [Tracking](facexlib/tracking/README.md) | [SORT](https://github.com/abewley/sort) | GPL 3.0 |
| [Assessment](facexlib/assessment/README.md) | [hyperIQA](https://github.com/SSL92/hyperIQA) | - |
| [Utils](facexlib/utils/README.md) | Face Restoration Helper | - |

## :eyes: Demo and Tutorials
# ![icon](assets/icon_small.png) FaceXLib x OpenTalker

## :wrench: Dependencies and Installation

@@ -46,7 +9,7 @@ Other recommended projects: &emsp; :arrow_forward: [Real-ESRGAN](https://github.
### Installation

```bash
pip install facexlib
pip install git+https://github.com/OpenTalker/facexlib.git
```

### Pre-trained models
@@ -58,6 +21,6 @@ If your network is not stable, you can download in advance (may with other downl

This project is released under the MIT license. <br>

## :e-mail: Contact
## Acknowledgement

If you have any question, open an issue or email `xintao.wang@outlook.com`.
Please visit https://github.com/xinntao/facexlib for the original code.
2 changes: 1 addition & 1 deletion VERSION
Original file line number Diff line number Diff line change
@@ -1 +1 @@
0.3.0
0.3.1
2 changes: 1 addition & 1 deletion facexlib/alignment/__init__.py
Original file line number Diff line number Diff line change
@@ -16,7 +16,7 @@ def init_alignment_model(model_name, half=False, device='cuda', model_rootpath=N

model_path = load_file_from_url(
url=model_url, model_dir='facexlib/weights', progress=True, file_name=None, save_dir=model_rootpath)
model.load_state_dict(torch.load(model_path)['state_dict'], strict=True)
model.load_state_dict(torch.load(model_path, map_location='cpu')['state_dict'], strict=True)
model.eval()
model = model.to(device)
return model
2 changes: 1 addition & 1 deletion facexlib/alignment/awing_arch.py
Original file line number Diff line number Diff line change
@@ -15,7 +15,7 @@ def calculate_points(heatmaps):
indexes = np.argmax(heatline, axis=2)

preds = np.stack((indexes % W, indexes // W), axis=2)
preds = preds.astype(np.float, copy=False)
preds = preds.astype(np.float64, copy=False)

inr = indexes.ravel()