There's no bounding box when I tested darknet pre-trained model (NO-DETECTION RESULT)

[soboroa]

Looking for the solution for my problem. I used code ./darknet.exe detector test cfg/coco.data yolov3.cfg yolov3.weights data/dog.jpg in cmd (used alexeyAB yolov3.weights). The dog.jpg appeard but the bounding box was not.

CUDA-version: 11010 (11040), cuDNN: 8.2.1, CUDNN_HALF=1, GPU count: 1 CUDNN_HALF=1 OpenCV version: 4.5.4 0 : compute_capability = 750, cudnn_half = 1, GPU: NVIDIA GeForce MX450 net.optimized_memory = 0 mini_batch = 1, batch = 16, time_steps = 1, train = 0

*results showed like this ↓

[yolo] params: iou loss: mse (2), iou_norm: 0.75, obj_norm: 1.00, cls_norm: 1.00, delta_norm: 1.00, scale_x_y: 1.00 106 - receptive field: 965 x 965 Total BFLOPS 65.879 avg_outputs = 532444 Allocate additional workspace_size = 18.88 MB Loading weights from yolov3.weights... seen 64, trained: 32013 K-images (500 Kilo-batches_64) Done! Loaded 107 layers from weights-file Detection layer: 82 - type = 28 Detection layer: 94 - type = 28 Detection layer: 106 - type = 28 data/dog.jpg: Predicted in 1590.054000 milli-seconds.

Please give me some advice. Thank you.

+) I changed opencv version to 3.2.0 and tried other weights file(everything on the pjreddie), tagging -thresh 0 -ext_output, CUDNN_HALF=0, other example images, and found predictions.jpg... There was NO bounding box and my code results didnt show me the percentage of detection.

[teh-monad]

(used alexeyAB yolov3.weights)

Then use alexey cfg file.