Hi,

i am trying to get an minimal example to run using my rtsp camera. Every time the code stops with the following error:

File "mini.py", line 139, in YOLO detections = darknet.detect_image(netMain, metaMain, darknet_image, thresh=0.25) # Detection occurs at this line and return detections, for customize we can change the threshold. File "/home/cctv/darknet/darknet.py", line 174, in detect_image do_nms_sort(detections, num, len(class_names), nms) TypeError: object of type 'METADATA' has no len()
Do you know how to solve this or have a glue what I am doing wrong?

Thanks for your help

Phil

Hi,
I was following your example on youtube to try the demo. But I get this error when I run this video demo

[yolo] params: iou loss: ciou (4), iou_norm: 0.07, cls_norm: 1.00, scale_x_y: 1.05
nms_kind: greedynms (1), beta = 0.600000
Total BFLOPS 128.459
avg_outputs = 1068395
 Allocate additional workspace_size = 0.01 MB
 Try to load weights: ./yolov4.weights
Loading weights from ./yolov4.weights...
 seen 64, trained: 32032 K-images (500 Kilo-batches_64)
CUDA status Error: file: D:/Development_work/darknet/src/convolutional_kernels.cu : cuda_convert_f32_to_f16() : line: 138 : build time: Aug 23 2020 - 07:56:31

*CUDA Error: no kernel image is available for execution on the device*

*CUDA Error: no kernel image is available for execution on the device: No error*

PS D:\Development_work\darknet\build\darknet\x64> nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2020 NVIDIA Corporation
Built on Wed_Jul_22_19:09:35_Pacific_Daylight_Time_2020
Cuda compilation tools, release 11.0, V11.0.221
Build cuda_11.0_bu.relgpu_drvr445TC445_37.28845127_0

Opencv: 4.4.0
Darknet: latest
CUDA: 11.0.
CUDNN: cudnn-11.0-windows-x64-v8.0.2.39

I am getting this error
module 'darknet' has no attribute 'load_net_custom'

I ran darknet_video_mod.py and got the detection effect I wanted, but could you please tell me how to show the detected category as Chinese? I tried to use PILLOW display, but each frame only shows one detection box and the above Chinese category.How to change the code?Thanks！

Hi there,
I was wondering how do you estimate the distance for various locations in the image? As the number of pixels at different locations would correspond to different physical distances e.g, if the person is near to the camera then 75 pixels might correspond to 2m but if the person is away from the camera then 75 pixels might correspond to 4m in the same image. Have you integrated this information into your calculations?