This is implementation of YOLO v2 with TensorFlow.
Clone YOLO_v2 repository
$ git clone https://github.com/leeyoshinari/YOLO_v2.git $ cd YOLO_v2
Download Pascal VOC2007 dataset, and put the dataset into
If you download other dataset, you also need to modify file paths.
Download weights file yolo_weights for COCO, and put weight file into
Or you can also download my training weights file YOLO_v2 for VOC.
Modify configuration into
$ python train_val.py
$ python test_val.py
For more information to wiki.
Darknet-19 has 19 convolutional layers, it's faster than yolo_v2. If you use darknet-19, you need some modifications. It's easy to modify.
Please download Darknet-19 weights file for VOC from darknet-19.
Training on Your Own Dataset
To train the model on your own dataset, you should need to modify:
Put all the images into the
Imagesfolder, put all the labels into the
Labelsfolder. Select a part of the image for training, write this part of the image filenames into
train.txt, the remaining part of the image filenames written in
test.txt. Then put the
data/dataset. Put weight file in
config.py:modify the CLASSES.
from pascal_voc import Pascal_vocwith
from preprocess import Data_preprocess, and replace
pre_data = Pascal_voc()with
pre_data = Data_preprocess().