Home

Awesome

YOLOv2 in PyTorch

NOTE: This project is no longer maintained and may not compatible with the newest pytorch (after 0.4.0).

This is a PyTorch implementation of YOLOv2. This project is mainly based on darkflow and darknet.

I used a Cython extension for postprocessing and multiprocessing.Pool for image preprocessing. Testing an image in VOC2007 costs about 13~20ms.

For details about YOLO and YOLOv2 please refer to their project page and the paper: YOLO9000: Better, Faster, Stronger by Joseph Redmon and Ali Farhadi.

NOTE 1: This is still an experimental project. VOC07 test mAP is about 0.71 (trained on VOC07+12 trainval, reported by @cory8249). See issue1 and issue23 for more details about training.

NOTE 2: I recommend to write your own dataloader using torch.utils.data.Dataset since multiprocessing.Pool.imap won't stop even there is no enough memory space. An example of dataloader for VOCDataset: issue71.

NOTE 3: Upgrade to PyTorch 0.4: https://github.com/longcw/yolo2-pytorch/issues/59

Installation and demo

  1. Clone this repository

    git clone git@github.com:longcw/yolo2-pytorch.git
    
  2. Build the reorg layer (tf.extract_image_patches)

    cd yolo2-pytorch
    ./make.sh
    
  3. Download the trained model yolo-voc.weights.h5 (link updated) and set the model path in demo.py

  4. Run demo python demo.py.

Training YOLOv2

You can train YOLO2 on any dataset. Here we train it on VOC2007/2012.

  1. Download the training, validation, test data and VOCdevkit

    wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tar
    wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tar
    wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar
    
  2. Extract all of these tars into one directory named VOCdevkit

    tar xvf VOCtrainval_06-Nov-2007.tar
    tar xvf VOCtest_06-Nov-2007.tar
    tar xvf VOCdevkit_08-Jun-2007.tar
    
  3. It should have this basic structure

    $VOCdevkit/                           # development kit
    $VOCdevkit/VOCcode/                   # VOC utility code
    $VOCdevkit/VOC2007                    # image sets, annotations, etc.
    # ... and several other directories ...
    
  4. Since the program loading the data in yolo2-pytorch/data by default, you can set the data path as following.

    cd yolo2-pytorch
    mkdir data
    cd data
    ln -s $VOCdevkit VOCdevkit2007
    
  5. Download the pretrained darknet19 model (link updated) and set the path in yolo2-pytorch/cfgs/exps/darknet19_exp1.py.

  6. (optional) Training with TensorBoard.

    To use the TensorBoard, set use_tensorboard = True in yolo2-pytorch/cfgs/config.py and install TensorboardX (https://github.com/lanpa/tensorboard-pytorch). Tensorboard log will be saved in training/runs.

  7. Run the training program: python train.py.

Evaluation

Set the path of the trained_model in yolo2-pytorch/cfgs/config.py.

cd faster_rcnn_pytorch
mkdir output
python test.py

Training on your own data

The forward pass requires that you supply 4 arguments to the network:

License: MIT license (MIT)