Open qwertyuiop-123456789 opened 4 years ago
In DarkHelp (a C++ wrapper for libdarknet.so) I have a --json
or -j
switch that makes it output a JSON structure. It contains everything there is to know about what has been detected. Maybe this would be useful to you? See here: https://www.ccoderun.ca/DarkHelp/api/ShellScripting.html
Output looks like this for every image:
{
"image": [
{
"count": 1,
"duration": "178 milliseconds",
"filename": "cujo.jpg",
"original_height": 293,
"original_width": 269,
"prediction": [
{
"all_probabilities": [
{
"class": 0,
"name": "dog",
"probability": 0.9390020966529846
}
],
"best_class": 0,
"best_probability": 0.9390020966529846,
"name": "dog 94%",
"original_point": {
"x": 0.4825710654258728,
"y": 0.33033615350723267
},
"original_size": {
"height": 0.48039382696151733,
"width": 0.6355597376823425
},
"rect": {
"height": 141,
"width": 171,
"x": 44,
"y": 26
}
}
],
"resized_height": 293,
"resized_width": 269
}
],
...
I've got them saved in txt file through this command. Is that what you need?
!./darknet detector demo obj.data yolov3-tiny-costum.cfg yolov3-tiny_last.weights -dont_show -ext_output video.mp4 -out_filename video.avi >video.txt
Hi. i want to get output text of video detection's annotation list in each video frame or image from Darknet. Is there any solution to this problem inside Darknet?