FaceForensics | Github of the FaceForensics | Video Utils library

by ondyari Python Version: Current License: Non-SPDX

X-Ray Key Features Code Snippets(3)Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | FaceForensics Summary

FaceForensics is a Python library typically used in Telecommunications, Media, Media, Entertainment, Video, Video Utils applications. FaceForensics has no vulnerabilities and it has medium support. However FaceForensics has 2 bugs, it build file is not available and it has a Non-SPDX License. You can download it from GitHub.

FaceForensics++ is a forensics dataset consisting of 1000 original video sequences that have been manipulated with four automated face manipulation methods: Deepfakes, Face2Face, FaceSwap and NeuralTextures. The data has been sourced from 977 youtube videos and all videos contain a trackable mostly frontal face without occlusions which enables automated tampering methods to generate realistic forgeries. As we provide binary masks the data can be used for image and video classification as well as segmentation. In addition, we provide 1000 Deepfakes models to generate and augment new data. For more information, please consult our updated paper.

Support

Quality

Security

License

Reuse

Support

FaceForensics has a medium active ecosystem.

It has 2038 star(s) with 502 fork(s). There are 73 watchers for this library.

It had no major release in the last 6 months.

There are 61 open issues and 11 have been closed. On average issues are closed in 10 days. There are 13 open pull requests and 0 closed requests.

It has a neutral sentiment in the developer community.

The latest version of FaceForensics is current.

Quality

FaceForensics has 2 bugs (0 blocker, 0 critical, 0 major, 2 minor) and 143 code smells.

Security

FaceForensics has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

FaceForensics code analysis shows 0 unresolved vulnerabilities.

There are 4 security hotspots that need review.

License

FaceForensics has a Non-SPDX License.

Non-SPDX licenses can be open source with a non SPDX compliant license, or non open source licenses, and you need to review them closely before use.

Reuse

FaceForensics releases are not available. You will need to build from source code and install.

FaceForensics has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions are not available. Examples and code snippets are available.

FaceForensics saves you 3838 person hours of effort in developing the same functionality from scratch.

It has 8181 lines of code, 636 functions and 63 files.

It has high code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed FaceForensics and discovered the below as its top functions. This is intended to give you an instant insight into FaceForensics implemented functionality, and help decide if they suit your requirements.

Generate models
Convert a CUDA model
Convert frames to data
Train a CUDA model on the given data path
Process the arguments
Check the equality of a value
Checks if the item type is a valid media type
Get argument list
Parse transpose value
Main entry point
Performs the final process for each bin
Sort images by face - similarity
Sort images by face - cnn dissimilarity
Group faces by face - similarity similarity
Sort images by face similarity
Group images into reference histogram
Sort images by histogram dissimilarity
Scale image
Create a compressed compressed method
Creates a model
Extract all the sequences from the video
Group images by face similarity
Test the full image network
Set the resolution of the device
Finalize and rename the images
Run process

Get all kandi verified functions for this library.

FaceForensics Key Features

No Key Features are available at this moment for FaceForensics.

FaceForensics Examples and Code Snippets

Domain General Face Forgery Detection by Learning to Weight,Installation,Dataset

Python

Lines of Code : 43

License : No License

Copy

├── faceforensics++
  └──manipulated_sequences
    ├──Deepfakes
      └──c23
        └──mtcnn
          ├──000_003
            ├──000_003_0000.png
            ├──000_003_0001.png
            ├──...
          ├──001_870
          └── ...
      └──c40

Patch Forensics,Training

Python

Lines of Code : 16

License : No License

Copy

python train.py --gpu_ids 0 --seed 0 --loadSize 299 --fineSize 299 \
        --name example_train_run --save_epoch_freq 200 \
        --real_im_path dataset/faces/celebahq/real-tfr-1024-resized128 \
        --fake_im_path dataset/faces/celebahq/pgan-

MesoNet

Python

Lines of Code : 6

License : No License

Copy

faceforensics++_models_subset/
  - face_detection/
    - Meso
      - Meso4_deepfake.pkl
    - xception
      - all_c23.p

Community Discussions

Trending Discussions on FaceForensics

How to use a customized dataset for training with PyTorch/few-shot-vid2vid

QUESTION

How to use a customized dataset for training with PyTorch/few-shot-vid2vid

Asked 2020-Mar-03 at 01:13

I’d like to use my own dataset created from the FaceForensics footage with few-show-vid2vid. So I generated image sequences with ffmpeg and keypoints with dlib. When I try to start the training script, I get the following error. What exactly is the problem? The provided small dataset was working for me.

...

ANSWER

Answered 2020-Mar-03 at 01:13

for i in range(67):

This is incorrect, you should be using range(68) for 68 face landmarks. You can verify this with python -c "for i in range(67): print(i)" which will only count from 0 to 66 (67 total numbers). python -c "for i in range(68): print(i)" will count from 0 to 67 (68 items) and get the whole face landmark set.

Source https://stackoverflow.com/questions/60373136

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install FaceForensics

You can download it from GitHub.
You can use FaceForensics like any standard Python library. You will need to make sure that you have a development environment consisting of a Python distribution including header files, a compiler, pip, and git installed. Make sure that your pip, setuptools, and wheel are up to date. When using pip it is generally recommended to install packages in a virtual environment to avoid changes to the system.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: