search

armaanpriyadarshan / Training-a-Custom-TensorFlow-2.X-Object-Detector

Learn how to train a TensorFlow Custom Object Detector with TensorFlow-GPU
83 stars 47 forks source link

Error in testing model when running TF-image-od.py #9

Closed abdulmanann closed 3 years ago

abdulmanann commented 4 years ago

I'm facing this issue when running TF-image-od.py for testing my model. The error is the same as that stated on readme of this repo. I'm using google colab. When I run the following command !python TF-image-od.py I get this error. Loading model...Done! Took 13.8348548412323 seconds Running inference for images/test/test.jpg... Done Traceback (most recent call last): File "TF-image-od.py", line 136, in <module> cv2.imshow('Object Detector', image_with_detections) cv2.error: OpenCV(4.4.0) /tmp/pip-req-build-svkjd8wa/opencv/modules/highgui/src/window.cpp:651: error: (-2:Unspecified error) The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage' I've installed opencv-python using pip and then rerun the program but still get the same error.

mahamatnoumai commented 4 years ago

@abdulmanan275 is opencv installed? if Yes pls check the path nd setup correctly. then it may work for u.

The function is not implemented. Rebuild the library with Windows, GTK+ 2.x or Cocoa support. If you are on Ubuntu or Debian, install libgtk2.0-dev and pkg-config, then re-run cmake or configure script in function 'cvShowImage' read the messages correctly

armaanpriyadarshan commented 4 years ago

Yes, @mahamatnoumai I believe that's the issue, Make sure you have installed opencv with pip install opencv-python.