pingu_98/Wav2Lip
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Added additional inference options

Browse source
This commit is contained in:
prajwalkr 2020-09-04 20:17:04 +05:30
parent c77c82aee7
commit f043ec6f2c
2 changed files with 13 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
.gitignore vendored
View file

@ -11,3 +11,6 @@ filelists/*.txt
evaluation/test_filelists/lr*.txt evaluation/test_filelists/lr*.txt
*.pyc *.pyc
*.mkv *.mkv
*.gif
*.webm
*.mp3

10
inference.py
View file

@ -35,13 +35,17 @@ parser.add_argument('--resize_factor', default=1, type=int,
help='Reduce the resolution by this factor. Sometimes, best results are obtained at 480p or 720p') help='Reduce the resolution by this factor. Sometimes, best results are obtained at 480p or 720p')
parser.add_argument('--crop', nargs='+', type=int, default=[0, -1, 0, -1], parser.add_argument('--crop', nargs='+', type=int, default=[0, -1, 0, -1],
help='Crop video to a smaller region (top, bottom, left, right). Applied after resize_factor arg. ' help='Crop video to a smaller region (top, bottom, left, right). Applied after resize_factor and rotate arg. '
'Useful if multiple face present. -1 implies the value will be auto-inferred based on height, width') 'Useful if multiple face present. -1 implies the value will be auto-inferred based on height, width')
parser.add_argument('--box', nargs='+', type=int, default=[-1, -1, -1, -1], parser.add_argument('--box', nargs='+', type=int, default=[-1, -1, -1, -1],
help='Specify a constant bounding box for the face. Use only as a last resort if the face is not detected.' help='Specify a constant bounding box for the face. Use only as a last resort if the face is not detected.'
'Also, might work only if the face is not moving around much. Syntax: (top, bottom, left, right).') 'Also, might work only if the face is not moving around much. Syntax: (top, bottom, left, right).')
parser.add_argument('--rotate', default=False, action='store_true',
help='Sometimes videos taken from a phone can be flipped 90deg. If true, will flip video right by 90deg.'
'Use if you get a flipped result, despite feeding a normal looking video')
args = parser.parse_args() args = parser.parse_args()
args.img_size = 96 args.img_size = 96
@ -80,6 +84,7 @@ def face_detect(images):
pady1, pady2, padx1, padx2 = args.pads pady1, pady2, padx1, padx2 = args.pads
for rect, image in zip(predictions, images): for rect, image in zip(predictions, images):
if rect is None: if rect is None:
cv2.imwrite('temp/faulty_frame.jpg', image) # check this frame where the face was not detected.
raise ValueError('Face not detected! Ensure the video contains a face in all the frames.') raise ValueError('Face not detected! Ensure the video contains a face in all the frames.')
y1 = max(0, rect[1] - pady1) y1 = max(0, rect[1] - pady1)
@ -193,6 +198,9 @@ def main():
if args.resize_factor > 1: if args.resize_factor > 1:
frame = cv2.resize(frame, (frame.shape[1]//args.resize_factor, frame.shape[0]//args.resize_factor)) frame = cv2.resize(frame, (frame.shape[1]//args.resize_factor, frame.shape[0]//args.resize_factor))
if args.rotate:
frame = cv2.rotate(frame, cv2.cv2.ROTATE_90_CLOCKWISE)
y1, y2, x1, x2 = args.crop y1, y2, x1, x2 = args.crop
if x2 == -1: x2 = frame.shape[1] if x2 == -1: x2 = frame.shape[1]
if y2 == -1: y2 = frame.shape[0] if y2 == -1: y2 = frame.shape[0]