search

neuralmagic / sparseml

Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Apache License 2.0
2.07k stars 148 forks source link

Cannot get bounding box #787

Closed soohwanlim closed 2 years ago

soohwanlim commented 2 years ago

Describe the bug Cannot get bounding box I tried yolov5 webcam by two methods. The first is the default setting, the second is using branches and quantized weights.

python detect.py --source 0 python detect.py --weight ./runs/train/prunedquantized/weight/best.pt --source 0

I was able to get the webcam image, but in both cases I couldn't find the bounding box.

can i get some advice?

(Recently, when I ran the webcam on original YoloV5(https://github.com/ultralytics/yolov5), the bounding box was well drawn.)

Environment Include all relevant environment information:

  1. OS [e.g. Ubuntu 18.04]: 20.04
  2. Python version [e.g. 3.7]: 3.8 (Conda)
  3. SparseML version or commit hash [e.g. 0.1.0, f7245c8]:
  4. ML framework version(s) [e.g. torch 1.7.1]: torch 1.9.0 + cu111
  5. Other Python package versions [e.g. SparseZoo, DeepSparse, numpy, ONNX]:
  6. Other relevant environment information [e.g. hardware, CUDA version]:

To Reproduce Exact steps to reproduce the behavior:

Errors If applicable, add a full print-out of any errors or exceptions that are raised or include screenshots to help explain your problem.

Additional context Add any other context about the problem here. Also include any relevant files.

KSGulin commented 2 years ago

Hey @OSMasterSoohwan, thanks for reporting this issue. This is indeed a bug with the detect script and a fix is up at neuralmagic/yolov5#45