Difference between revisions of "YOLO"
Jump to navigation
Jump to search
| Line 34: | Line 34: | ||
wget https://pjreddie.com/media/files/darknet53.conv.74 | wget https://pjreddie.com/media/files/darknet53.conv.74 | ||
| − | *Step 1: | + | '''*Step 1: Dataset''' |
*Download the images for the categories that you would like YOLO to detect. | *Download the images for the categories that you would like YOLO to detect. | ||
| − | *Step 2: Data Annotation | + | '''*Step 2: Data Annotation |
| − | *Download the YOLO annotation tool: | + | '''*Download the YOLO annotation tool: |
https://github.com/ManivannanMurugavel/Yolo-Annotation-Tool-New- | https://github.com/ManivannanMurugavel/Yolo-Annotation-Tool-New- | ||
*Enter the directory with the terminal: | *Enter the directory with the terminal: | ||
| Line 44: | Line 44: | ||
cd Yolo-Annotation-Tool-New- | cd Yolo-Annotation-Tool-New- | ||
python main.py | python main.py | ||
| − | * | + | *Write the path where you have placed the images of the first category of your dataset and click the button "Load" |
| + | *Select the category of those images in the combo box next that "Choose Class". | ||
*Create the bounding boxes in each one of the images in this category by first, clicking on the image and then clicking on the button Next | *Create the bounding boxes in each one of the images in this category by first, clicking on the image and then clicking on the button Next | ||
| − | *When you are done with all the images of that category | + | *When you are done with all the images of that category, write the path of the next category and press the Load button. |
| + | *Select the category of those images in the combo box next that "Choose Class". | ||
| + | *Create the bounding boxes for all the images of this category. | ||
| + | *Do the same for the rest of categories. | ||
| + | *Whenever you are done, go to the terminal and close the tool by typing CTRL+C | ||
| + | *The tool should have created one text file that contains the objects coordinates for each one of the images of your dataset. | ||
| + | *Now we need to split the images of the dataset into two sets: train and test. | ||
| + | *We will do that, by typing in the terminal: | ||
| + | python process.py | ||
| + | *By default this is done in a 90%/10% ratio, but it can be changed in the script. | ||
| + | *This script will generate the train.txt and test.txt files that we need to copy into the Darknet folder. | ||
| + | * | ||
| Line 54: | Line 66: | ||
| + | |||
| + | |||
| + | |||
| + | |||
| + | *More information: | ||
| + | *[https://medium.com/@manivannan_data/how-to-train-yolov3-to-detect-custom-objects-ccbcafeb13d2] | ||
| + | *[https://medium.com/@manivannan_data/how-to-train-yolov2-to-detect-custom-objects-9010df784f36] | ||
| + | *[https://medium.com/@manivannan_data/yolo-annotation-tool-new-18c7847a2186] | ||
=== Guide === | === Guide === | ||
*https://pjreddie.com/darknet/yolo/ | *https://pjreddie.com/darknet/yolo/ | ||
*Terminal basic tutorial: https://maker.pro/linux/tutorial/basic-linux-commands-for-beginners | *Terminal basic tutorial: https://maker.pro/linux/tutorial/basic-linux-commands-for-beginners | ||
Revision as of 22:22, 15 July 2019
Installation
- Fist, we install OpenCV:
- OpenCV Installation
- Then, we need to install our modified version of Darknet:
- Darknet Installation
- Go to the directory and download the YOLO weights:
cd darknet wget https://pjreddie.com/media/files/yolov3.weights
Using YOLO
- Using YOLO with Darknet (GPU + OpenCV). Tested on Ubuntu 16.04
Using YOLO with an image
- Go to the directory and run the detector for images:
cd darknet ./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
Using YOLO with a video
- Go to the directory and run the detector for videos:
cd darknet ./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights data/ny720p2.mp4
- Run the detector (webcam):
./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights
Training your own Dataset
- Download the convolutional weights from the darknet53 model that are pre-trained on Imagenet and place them in the Darknet folder:
wget https://pjreddie.com/media/files/darknet53.conv.74
*Step 1: Dataset
- Download the images for the categories that you would like YOLO to detect.
*Step 2: Data Annotation *Download the YOLO annotation tool:
https://github.com/ManivannanMurugavel/Yolo-Annotation-Tool-New-
- Enter the directory with the terminal:
cd Downloads cd Yolo-Annotation-Tool-New- python main.py
- Write the path where you have placed the images of the first category of your dataset and click the button "Load"
- Select the category of those images in the combo box next that "Choose Class".
- Create the bounding boxes in each one of the images in this category by first, clicking on the image and then clicking on the button Next
- When you are done with all the images of that category, write the path of the next category and press the Load button.
- Select the category of those images in the combo box next that "Choose Class".
- Create the bounding boxes for all the images of this category.
- Do the same for the rest of categories.
- Whenever you are done, go to the terminal and close the tool by typing CTRL+C
- The tool should have created one text file that contains the objects coordinates for each one of the images of your dataset.
- Now we need to split the images of the dataset into two sets: train and test.
- We will do that, by typing in the terminal:
python process.py
- By default this is done in a 90%/10% ratio, but it can be changed in the script.
- This script will generate the train.txt and test.txt files that we need to copy into the Darknet folder.
- We need to create 3 files:
- myDataset.data
Guide
- https://pjreddie.com/darknet/yolo/
- Terminal basic tutorial: https://maker.pro/linux/tutorial/basic-linux-commands-for-beginners