search

jzbontar / mc-cnn

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches
BSD 2-Clause "Simplified" License
707 stars 232 forks source link

UnicodeDecodeError: 'utf-8' codec can't decode byte 0x99 in position 22: invalid start byte #53

Open blueevangelion opened 6 years ago

blueevangelion commented 6 years ago

I had Compute the Matching Cost and be able to run with pretrained network. I downloaded Middlebury dataset use ./download_middlebury.sh command. I compile MiddEval3-SDK and installed ImageMagick. I got the following error while i try to run preprocess_mb.py

Adirondack Traceback (most recent call last): File "preprocess_mb.py", line 166, in disp0, scale0 = load_pfm(os.path.join(base2_imperfect, 'disp0.pfm'), True) File "preprocess_mb.py", line 34, in load_pfm header = file.readline().rstrip() File "/usr/lib/python3.5/codecs.py", line 321, in decode (result, consumed) = self._buffer_decode(data, self.errors, final) UnicodeDecodeError: 'utf-8' codec can't decode byte 0x99 in position 22: invalid start byte

Opencv version:3.4.0 python version:3.5

pannyl commented 5 years ago

Hello, I have the same problem. Could you please tell me how to solved it ?