YOLO v4 environment building

I follow the steps with video to build the yolo v4 environment. P.S. video is Chinese. video link

But when I want to test the result, there is a error I dont know how to solve.

the error:

CUDA-version: 11050 (11050), cuDNN: 8.3.0, GPU count: 1
OpenCV version: 4.1.0
0 : compute_capability = 610, cudnn_half = 0, GPU: NVIDIA GeForce MX250
net.optimized_memory = 0
mini_batch = 1, batch = 8, time_steps = 1, train = 0
layer filters size/strd(dil) input output
0 Create CUDA-stream - 0
Could not load library cudnn_cnn_infer64_8.dll. Error code 126
Please make sure cudnn_cnn_infer64_8.dll is in your library path!

Plz help me, thanks

[Error image][2]

Solution

You can try the following thing. Download the cuda zip file and locate it. Copy all these files:


    cudnn_adv_infer64_8.dll
    cudnn_adv_train64_8.dll
    cudnn_cnn_infer64_8.dll
    cudnn_cnn_train64_8.dll
    cudnn_ops_infer64_8.dll
    cudnn_ops_train64_8.dll

And paste them in your nvidia gpu computing toolkit>cuda>bin

Alternatively, if you've already have these files move them to the folder. You might encounter new errors of the same type for other dll fes. Do the same with those.

I had the same issue and solved it that way.