This implementation of YOLO.
-
Clone YOLO_v1 repository
$ git clone https://github.com/leeyoshinari/YOLO_v1.git $ cd YOLO_v1
-
Download Pascal VOC2007 dataset, and put the dataset into
data/Pascal_voc
.if you download other dataset, you also need to modify file paths.
-
Download weights file YOLO_small, and put weight file into
data/output
Or you can also download my training weights file YOLO_v1.
-
Modify configuration into
yolo/config.py
-
Training
$ python train.py
-
Test
$ python test.py
To train the model on your own dataset, you should need to modefy:
-
Put all the images into the
Images
folder, put all the labels into theLabels
folder. Select a part of the images for training, write this part of the images filename intotrain.txt
, the remaining part of the images filename written intest.txt
. Then put theImages
,Labels
,train.txt
andtest.txt
intodata/data_set
. Put weight file indata/output
-
config.py
modify the CLASSES -
train.py
replacefrom utils.pascal_voc import pascal_voc
withfrom utils.preprocess import preprocess
, and replacepascal = pascal_voc()
withpascal = preprocess()
.
- Tensorflow
- OpenCV