lmomoy / lf-yolo Goto Github PK

Hi, when I run python detect.py --source data/images --weights LF-YOLO.pt --conf 0.25, I find there is no LF-YOLO.pt and I use yolov3.pt instead, but I get an error: RuntimeError: The size of tensor a (80) must match the size of tensor b (44) at non-singleton dimension 3. Could you help me? Thank you!

hello，When I was running your code, there was a problem with the version of OpenCV。My opencv is 4.5.2, but He reminded me opencv-python>=4.1.2

requirements: opencv-python>=4.1.2 not found and is required by YOLOv3, attempting auto-update...
ERROR: Invalid requirement: "'opencv-python"
Traceback (most recent call last):
File "d:\Studies\bhdx\CODE\LF-YOLO-master\utils\general.py", line 110, in check_requirements
pkg.require(r)
File "D:\Studies\Anaconda3\envs\pytorch\lib\site-packages\pkg_resources_init_.py", line 891, in require
needed = self.resolve(parse_requirements(requirements))
File "D:\Studies\Anaconda3\envs\pytorch\lib\site-packages\pkg_resources_init_.py", line 777, in resolve
raise DistributionNotFound(req, requirers)
pkg_resources.DistributionNotFound: The 'opencv-python>=4.1.2' distribution was not found and is required by the application

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "d:/Studies/bhdx/CODE/LF-YOLO-master/train.py", line 511, in
check_requirements()
File "d:\Studies\bhdx\CODE\LF-YOLO-master\utils\general.py", line 114, in check_requirements
print(subprocess.check_output(f"pip install '{e.req}'", shell=True).decode())
File "D:\Studies\Anaconda3\envs\pytorch\lib\subprocess.py", line 415, in check_output
return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
File "D:\Studies\Anaconda3\envs\pytorch\lib\subprocess.py", line 516, in run
raise CalledProcessError(retcode, process.args,
subprocess.CalledProcessError: Command 'pip install 'opencv-python>=4.1.2'' returned non-zero exit status 1.

Do you have this problem？

May I ask if this model has pre-trained weights?

Hi, when I run python detect.py --source data/images --weights LF-YOLO.pt --conf 0.25, I find there is no LF-YOLO.pt and I use yolov3.pt instead, but I get an error: RuntimeError: The size of tensor a (80) must match the size of tensor b (44) at naon-singleton dimension 3. Could you help me? Thank you!

can you share the weld defect image dataset ? Thank you !