December 10, 2019

488 words 3 mins read



A Keras implementation of YOLOv3 (Tensorflow backend)

repo name qqwweee/keras-yolo3
repo link
language Python
size (curr.) 148 kB
stars (curr.) 5304
created 2018-04-03
license MIT License




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.
python yolov3.cfg yolov3.weights model_data/yolo.h5
python [OPTIONS...] --image, for image detection mode, OR
python [video_path] [output_path (optional)]

For Tiny YOLOv3, just do in a similar way, just specify model path and anchor path with --model model_file and --anchors anchor_file.


Use –help to see usage of

usage: [-h] [--model MODEL] [--anchors ANCHORS]
                     [--classes CLASSES] [--gpu_num GPU_NUM] [--image]
                     [--input] [--output]

positional arguments:
  --input        Video input path
  --output       Video output path

optional arguments:
  -h, --help         show this help message and exit
  --model MODEL      path to model weight file, default model_data/yolo.h5
  --anchors ANCHORS  path to anchor definitions, default
  --classes CLASSES  path to class definitions, default
  --gpu_num GPU_NUM  Number of GPU to use, default 1
  --image            Image detection mode, will ignore all positional arguments

  1. MultiGPU usage: use --gpu_num N to use N GPUs. It is passed to the Keras multi_gpu_model().


  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
    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 -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 and start training.
    Use your trained weights or checkpoint weights with command line option --model model_file when using Remember to modify class path or anchor path, with --classes class_file and --anchors anchor_file.

If you want to use original pretrained weights for YOLOv3:
1. wget
2. rename it as darknet53.weights
3. python -w darknet53.cfg darknet53.weights model_data/darknet53_weights.h5
4. use model_data/darknet53_weights.h5 in

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 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.

comments powered by Disqus