-
When I process a list of images and save results of detection to result.txt file, I find negative coordinates as follows:
`test/209.jpg: Predicted in 15.484000 milli-seconds.`
`ship: 74% (left_x: 2…
-
I'm having a question on the `detector test` command. When I run it, it works perfectly fine, but it takes quite some time per image. The prediction itself only takes on average 4.6 ms, but it takes a…
-
Improve API compatibility with other software (applications, libraries, ...)
1. Remove unnecessary API functions, which:
* isn't related to AI/Neural networks/Computer vision
* duplicate…
-
I trained a dataset using Darknet on gpu.
cas1 : I used the already available function "test_detector" and the result is correct --> 1 detection
cas2 : I used the already available Detector c…
-
I'm having some problem with webcam.
My webcam currently support three codec: MJPG/H264/YUYV
by default yolo use YUYU, which limit the resolution in 640x480
what can I do to change to another c…
-
I am training on the dataset to detect face and person at the same time. The 'person' dataset is from the VOC and COCO training dataset. The 'face' dataset is WIDERFACE dataset. So, there are 2 classe…
-
Hi,
how can I implement image tiling on darknet?
For example I have an image 3840x2160, and I want to tile it into 4 images of 1920x1080, or also in 8 tiles.
So I can run a net with small size and…
-
I have 2 classes: notouch and overpack - levels of tobacco in hookah bows. I have good accuracy, but the problem is that yolo displays most relevant class and it's probability. Is there any chance to …
-
Hi everyone,
I found a python example of the new OpenCV DetectionModel class by @YashasSamega (thanks for that), but does anyone have an implementation in C++?
![image](https://user-images.githu…
-
When running darknet with parameters to generate a JSON output, for example:
```
./darknet detector test .\data\dataj.data .\cfg\yolov3-tiny.cfg .\backup\yolov3-tiny_last.weights -ext_output -dont…