-
This is run on the following setup.
Darknet V3 "Jazz" v3.0-177-gfa2353b1
CUDA runtime version 12010 (v12.1), driver version 12060 (v12.6)
cuDNN version 12020 (v8.9.6), use of half-size floats is …
-
Investigate what would be needed to support batch inference.
See: https://github.com/AlexeyAB/darknet/issues/7541
And: https://github.com/AlexeyAB/darknet/pull/7915
-
I don't know where to leave this, but in case it is useful I've written a C++ class to access libdarknet.so. I've published it using the MIT license so anyone can use it, even in commercial apps. At…
-
I want to save the boundig box objects as images.
The issue #2157 shows how to do this. I implemented and it works for **images**. However, I want to do the same for real-time object detection. For t…
-
Dear Stephane,
First, thank you very much for your work on darknet, darkhelp and darkmark.
These are fantastic tools.
I encounter a compilation error `error: ‘exchange’ is not a member of ‘std’…
-
If something doesn’t work for you, then show 2 screenshots:
1. screenshots of your issue
2. screenshots with such information
```
./darknet detector test cfg/coco.data cfg/yolov4.cfg yolov4.weight…
-
Hello, AlexeyAB!
in darkenet.h:
LIB_API detection *get_network_boxes(network *net, int w, int h, float thresh, float hier, int *map, int relative, int *num, int letter);
I am coufused, what does th…
-
In Keras we can return predictions for a single batch of samples.
Bellow is the commented section of the predict_on_batch function on keras/engine/training.py.
There is something like this implement…
-
-
Hello,
i am new to yolov4 and I have the following problem. I trained my yolov4 tiny network to detect faces and it runs on a jetson nano. I am using the following code to run the detection over my z…