Closed JinEui-Kim closed 1 year ago
Would you mind sharing the testing image with me?
I found the reason why this problem occured. The image was 16bit image, so the image pixel value has range of 0~65535. hint was the first error
TypeError: can't convert np.ndarray of type numpy.uint16
therefore, i change the imread parameter (delete the FLAG)
img = cv2.imread(img_file, cv2.IMREAD_UNCHANGED)
->
img = cv2.imread(img_file)
then img pixel value has range of 0~255, and inference is no problem.
I find better way to inference 16-bit image, so i pull request to your repository.
the first error i met is above. so i changed the code (/lib/common/imutils.py - line 60)
Then I infered png image that size is (3840,2160) extracted from mp4 video, but i got error.
here is my environment ubuntu 20.04.5 LTS Ryzen 5900x NVIDIA RTX A6000 48GB CUDA 11.6 and other libraries installed following your installation script. did i miss something?