Shape : (1, 3, 448, 448)
Range : [-1.0, 1.0]
- category : [0,19]
- probablity : [0.0,1.0]
- position : x, y, w, h [0,1]
Automatically downloads the onnx and prototxt files on the first run. It is necessary to be connected to the Internet while downloading.
For the sample image,
$ python3 yolov1-tiny.py
If you want to specify the input image, put the image path after the --input
option.
You can use --savepath
option to change the name of the output file to save.
$ python3 yolov1-tiny.py --input IMAGE_PATH --savepath SAVE_IMAGE_PATH
By adding the --video
option, you can input the video.
If you pass 0
as an argument to VIDEO_PATH, you can use the webcam input instead of the video file.
$ python3 yolov1-tiny.py --video VIDEO_PATH
- YOLO: Real-Time Object Detection
- convert between pytorch, caffe prototxt/weights and darknet cfg/weights
Darknet
CaffeModel