Skip to main content

TensorFlow 2.x implementation of YOLOv4

Project description

YOLOv4

A TensorFlow 2.0 implementation of YOLOv4: Optimal Speed and Accuracy of Object Detection

Python Versions Tensorflow Versions Code style: black Python package Open In Colab

This implementation runs (for now) inference with the original Darknet weights from AlexeyAB. See the roadmap section to see what's next.

Installation

To install this package, you can run:

pip install https://github.com/sicara/tf2-yolov4/archive/master.zip
pip install tensorflow
# Check that tf2_yolov4 is installed properly
python -c "from tf2_yolov4.model import YOLOv4; print(YOLOv4)"

Requirements:

  • MacOs >= 10.15 since tensorflow-addons is not available for older release of MacOs
  • Python >= 3.6
  • Compatible versions between TensorFlow and TensorFlow Addons: check the compatibility matrix

Examples in Colab

Pretrained weights

To load the Darknet weights trained on COCO, you have to:

  • get the weights (yolov4.weights) from AlexeyAB/darknet
  • run convert-darknet-weights PATH_TO/yolov4.weights

TF weights should be saved as yolov4.h5. For more information about the conversion script, run convert-darknet-weights --help.

Roadmap

  • Inference
    • CSPDarknet53 backbone with Mish activations
    • SPP Neck
    • YOLOv3 Head
    • Load Darknet Weights
    • Image loading and preprocessing
    • YOLOv3 box postprocessing
    • Handling non-square images
  • Training
    • Training loop with YOLOv3 loss
    • CIoU loss
    • Cross mini-Batch Normalization
    • Self-adversarial Training
    • Mosaic Data Augmentation
    • DropBlock
  • Enhancements
    • Automatic download of pretrained weights (like Keras applications)

References

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tf2_yolov4-0.1.0.tar.gz (12.0 kB view details)

Uploaded Source

Built Distribution

tf2_yolov4-0.1.0-py3-none-any.whl (17.1 kB view details)

Uploaded Python 3

File details

Details for the file tf2_yolov4-0.1.0.tar.gz.

File metadata

  • Download URL: tf2_yolov4-0.1.0.tar.gz
  • Upload date:
  • Size: 12.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.4.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.7

File hashes

Hashes for tf2_yolov4-0.1.0.tar.gz
Algorithm Hash digest
SHA256 579163e701be53f167e6292693c3661462329d6bad3d2ac3ad638ca1634c69ed
MD5 39c0042d0bb7c3c5a82aa19f5fb88120
BLAKE2b-256 794ba1d7891577c3065ad000952df7ddec97c8cf8199610c4ce37461f946cd1b

See more details on using hashes here.

Provenance

File details

Details for the file tf2_yolov4-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: tf2_yolov4-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 17.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.4.0 requests-toolbelt/0.9.1 tqdm/4.46.0 CPython/3.7.7

File hashes

Hashes for tf2_yolov4-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 377cdbc7f67c4ac581c07af336303b663c52594ecac185a0fffc44efdf229474
MD5 77ad3252ae61e81e8369e93da437067e
BLAKE2b-256 6a6124a0aed949afc7715b767160abc241c7cd9e7ae9c34e4f8b42c1d6924e63

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page