TensorFlow 2.x implementation of YOLOv4
Project description
YOLOv4
A TensorFlow 2.0 implementation of YOLOv4: Optimal Speed and Accuracy of Object Detection
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
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
tf2_yolov4-0.1.0.tar.gz
(12.0 kB
view details)
Built Distribution
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 579163e701be53f167e6292693c3661462329d6bad3d2ac3ad638ca1634c69ed |
|
MD5 | 39c0042d0bb7c3c5a82aa19f5fb88120 |
|
BLAKE2b-256 | 794ba1d7891577c3065ad000952df7ddec97c8cf8199610c4ce37461f946cd1b |
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
Algorithm | Hash digest | |
---|---|---|
SHA256 | 377cdbc7f67c4ac581c07af336303b663c52594ecac185a0fffc44efdf229474 |
|
MD5 | 77ad3252ae61e81e8369e93da437067e |
|
BLAKE2b-256 | 6a6124a0aed949afc7715b767160abc241c7cd9e7ae9c34e4f8b42c1d6924e63 |