riya-maan
commented
5 years ago Updated sk-video. It works fine then.
Closed riya-maan closed 5 years ago
riya-maan
commented
5 years ago Updated sk-video. It works fine then.
On running extract_mouth_batch.py I'm getting following error:
Using TensorFlow backend. Processing: datasets/s1/prwq3s.mpg Traceback (most recent call last): File "scripts/extract_mouth_batch.py", line 47, in
video = Video(vtype='face', face_predictor_path=FACE_PREDICTOR_PATH).from_video(filepath)
File "/Users/riyamaan/Desktop/LipNet/lipnet/lipreading/videos.py", line 120, in from_video
frames = self.get_video_frames(path)
File "/Users/riyamaan/Desktop/LipNet/lipnet/lipreading/videos.py", line 196, in get_video_frames
frames = np.array([frame for frame in videogen])
File "/Users/riyamaan/Desktop/LipNet/lipnet/lipreading/videos.py", line 196, in
frames = np.array([frame for frame in videogen])
File "/Users/riyamaan/anaconda3/lib/python3.6/site-packages/skvideo/io/io.py", line 251, in vreader
reader = FFmpegReader(fname, inputdict=inputdict, outputdict=outputdict, verbosity=verbosity)
File "/Users/riyamaan/anaconda3/lib/python3.6/site-packages/skvideo/io/ffmpeg.py", line 194, in init
self.inputframenum = np.int(check_output(probecmd).split('\n')[0])
TypeError: a bytes-like object is required, not 'str'
How to resolve it?