YOLO_tiny
This implementation of YOLO with TensorFlow.
Installation
-
Clone YOLO_tiny repository
$ git clone https://github.com/leeyoshinari/YOLO_tiny.git $ cd YOLO_tiny
-
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_tiny, and put weight file into
data/output
.Or you can also download my training weights file YOLO_tiny.
-
Modify configuration into
yolo/config.py
. -
Training
$ python train.py
-
Test
$ python test.py
Training on Your Own Dataset
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 image for training, write this part of the image filename intotrain.txt
, the remaining part of the image filename written intest.txt
. Then put theImages
,Labels
,train.txt
andtest.txt
intodata/dataset
. 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()
.
Requirements
- Tensorflow
- OpenCV