/keras-yolo3

A Keras implementation of YOLOv3 (Tensorflow backend)

Primary LanguagePythonMIT LicenseMIT

keras-yolo3

license

Introduction

A Keras implementation of YOLOv3 (Tensorflow backend) inspired by allanzelener/YAD2K.

Quick Start

  1. Download YOLOv3 weights from YOLO website.
  2. Convert the Darknet YOLO model to a Keras model.
  3. Run YOLO detection.
wget https://pjreddie.com/media/files/yolov3.weights
python convert.py yolov3.cfg yolov3.weights model_data/yolo.h5
python yolo.py   OR   python yolo_video.py [video_path] [output_path(optional)]

For Tiny YOLOv3, just do in a similar way. And modify model path and anchor path in yolo.py.

  1. MultiGPU usage is an optinal. Change the number of gpu and add gpu device id

Training

  1. Generate your own annotation file and class names file.
    One row for one image;
    Row format: image_file_path box1 box2 ... boxN;
    Box format: x_min,y_min,x_max,y_max,class_id (no space).
    For VOC dataset, try python voc_annotation.py
    Here is an example:

    path/to/img1.jpg 50,100,150,200,0 30,50,200,120,3
path/to/img2.jpg 120,300,250,600,2
...

  2. Make sure you have run python convert.py -w yolov3.cfg yolov3.weights model_data/yolo_weights.h5
    The file model_data/yolo_weights.h5 is used to load pretrained weights.

  3. Modify train.py and start training.
    python train.py
    Use your trained weights or checkpoint weights in yolo.py.
    Remember to modify class path or anchor path.

If you want to use original pretrained weights for YOLOv3:
1. wget https://pjreddie.com/media/files/darknet53.conv.74
2. rename it as darknet53.weights
3. python convert.py -w darknet53.cfg darknet53.weights model_data/darknet53_weights.h5
4. use model_data/darknet53_weights.h5 in train.py

Some issues to know

  1. The test environment is

    • Python 3.5.2
    • Keras 2.1.5
    • tensorflow 1.6.0

  2. Default anchors are used. If you use your own anchors, probably some changes are needed.

  3. The inference result is not totally the same as Darknet but the difference is small.

  4. The speed is slower than Darknet. Replacing PIL with opencv may help a little.

  5. Always load pretrained weights and freeze layers in the first stage of training. Or try Darknet training. It's OK if there is a mismatch warning.

  6. The training strategy is for reference only. Adjust it according to your dataset and your goal. And add further strategy if needed.

  7. For speeding up the training process with frozen layers train_bottleneck.py can be used. It will compute the bottleneck features of the frozen model first and then only trains the last layers. This makes training on CPU possible in a reasonable time. See this for more information on bottleneck features.