Skip to content

Commit

Permalink
support ffmpeg stream for inference_realesrgan_video (#308)
Browse files Browse the repository at this point in the history 
* support ffmpeg stream for inference_realesrgan_video

* fix code format

Co-authored-by: yanzewu <[email protected]>
  • Loading branch information
@ToTheBeginning
ToTheBeginning and yanzewu authored Apr 26, 2022
1 parent 827fae3 commit cdc14b7
Show file tree
Hide file tree
Showing 2 changed files with 209 additions and 85 deletions.
7 changes: 6 additions & 1 deletion docs/anime_video_model.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,12 @@ The following are some demos (best view in the full screen mode).
# download model
wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P realesrgan/weights
# inference
python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2
python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --stream
```
```console
Usage:
--stream with this option, the enhanced frames are sent directly to a ffmpeg stream,
avoiding storing large (usually tens of GB) intermediate results.
```

### NCNN Executable File
Expand Down
287 changes: 203 additions & 84 deletions inference_realesrgan_video.py
View file
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
import argparse
import cv2
import glob
import mimetypes
import numpy as np
import os
import queue
import shutil
Expand All @@ -13,6 +15,192 @@
from realesrgan.archs.srvgg_arch import SRVGGNetCompact


def get_frames(args, extract_frames=False):
# input can be a video file / a folder of frames / an image
is_video = False
if mimetypes.guess_type(args.input)[0].startswith('video'): # is a video file
is_video = True
video_name = os.path.splitext(os.path.basename(args.input))[0]
if extract_frames:
frame_folder = os.path.join('tmp_frames', video_name)
os.makedirs(frame_folder, exist_ok=True)
# use ffmpeg to extract frames
os.system(f'ffmpeg -i {args.input} -qscale:v 1 -qmin 1 -qmax 1 -vsync 0 {frame_folder}/frame%08d.png')
# get image path list
paths = sorted(glob.glob(os.path.join(frame_folder, '*')))
else:
paths = []
# get input video fps
if args.fps is None:
import ffmpeg
probe = ffmpeg.probe(args.input)
video_streams = [stream for stream in probe['streams'] if stream['codec_type'] == 'video']
args.fps = eval(video_streams[0]['avg_frame_rate'])
elif mimetypes.guess_type(args.input)[0].startswith('image'): # is an image file
paths = [args.input]
else:
paths = sorted(glob.glob(os.path.join(args.input, '*')))
assert len(paths) > 0, 'the input folder is empty'

if args.fps is None:
args.fps = 24

return is_video, paths


def inference_stream(args, upsampler, face_enhancer):
try:
import ffmpeg
except ImportError:
import pip
pip.main(['install', '--user', 'ffmpeg-python'])
import ffmpeg

is_video, paths = get_frames(args, extract_frames=False)
video_name = os.path.splitext(os.path.basename(args.input))[0]
video_save_path = os.path.join(args.output, f'{video_name}_{args.suffix}.mp4')

# decoder
if is_video:
# get height and width
probe = ffmpeg.probe(args.input)
video_streams = [stream for stream in probe['streams'] if stream['codec_type'] == 'video']
width = video_streams[0]['width']
height = video_streams[0]['height']

# set up frame decoder
decoder = (
ffmpeg.input(args.input).output('pipe:', format='rawvideo', pix_fmt='rgb24', loglevel='warning').run_async(
pipe_stdin=True, pipe_stdout=True, cmd=args.ffmpeg_bin))
else:
from PIL import Image
tmp_img = Image.open(paths[0])
width, height = tmp_img.size
idx = 0

out_width, out_height = int(width * args.outscale), int(height * args.outscale)
if out_height > 2160:
print('You are generating video that is larger than 4K, which will be very slow due to IO speed.',
'We highly recommend to decrease the outscale(aka, -s).')
# encoder
if is_video:
audio = ffmpeg.input(args.input).audio
encoder = (
ffmpeg.input(
'pipe:', format='rawvideo', pix_fmt='rgb24', s=f'{out_width}x{out_height}', framerate=args.fps).output(
audio, video_save_path, pix_fmt='yuv420p', vcodec='libx264', loglevel='info',
acodec='copy').overwrite_output().run_async(pipe_stdin=True, pipe_stdout=True, cmd=args.ffmpeg_bin))
else:
encoder = (
ffmpeg.input(
'pipe:', format='rawvideo', pix_fmt='rgb24', s=f'{out_width}x{out_height}',
framerate=args.fps).output(video_save_path, pix_fmt='yuv420p', vcodec='libx264',
loglevel='info').overwrite_output().run_async(
pipe_stdin=True, pipe_stdout=True, cmd=args.ffmpeg_bin))

while True:
if is_video:
img_bytes = decoder.stdout.read(width * height * 3) # 3 bytes for one pixel
if not img_bytes:
break
img = np.frombuffer(img_bytes, np.uint8).reshape([height, width, 3])
else:
if idx >= len(paths):
break
img = cv2.imread(paths[idx])
idx += 1

try:
if args.face_enhance:
_, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
else:
output, _ = upsampler.enhance(img, outscale=args.outscale)
except RuntimeError as error:
print('Error', error)
print('If you encounter CUDA out of memory, try to set --tile with a smaller number.')
else:
output = output.astype(np.uint8).tobytes()
encoder.stdin.write(output)

torch.cuda.synchronize()

if is_video:
decoder.stdin.close()
decoder.wait()
encoder.stdin.close()
encoder.wait()


def inference_frames(args, upsampler, face_enhancer):
is_video, paths = get_frames(args, extract_frames=True)
video_name = os.path.splitext(os.path.basename(args.input))[0]

# for saving restored frames
save_frame_folder = os.path.join(args.output, video_name, 'frames_tmpout')
os.makedirs(save_frame_folder, exist_ok=True)

timer = AvgTimer()
timer.start()
pbar = tqdm(total=len(paths), unit='frame', desc='inference')
# set up prefetch reader
reader = PrefetchReader(paths, num_prefetch_queue=4)
reader.start()

que = queue.Queue()
consumers = [IOConsumer(args, que, f'IO_{i}') for i in range(args.consumer)]
for consumer in consumers:
consumer.start()

for idx, (path, img) in enumerate(zip(paths, reader)):
imgname, extension = os.path.splitext(os.path.basename(path))
if len(img.shape) == 3 and img.shape[2] == 4:
img_mode = 'RGBA'
else:
img_mode = None

try:
if args.face_enhance:
_, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
else:
output, _ = upsampler.enhance(img, outscale=args.outscale)
except RuntimeError as error:
print('Error', error)
print('If you encounter CUDA out of memory, try to set --tile with a smaller number.')

else:
if args.ext == 'auto':
extension = extension[1:]
else:
extension = args.ext
if img_mode == 'RGBA': # RGBA images should be saved in png format
extension = 'png'
save_path = os.path.join(save_frame_folder, f'{imgname}_out.{extension}')

que.put({'output': output, 'save_path': save_path})

pbar.update(1)
torch.cuda.synchronize()
timer.record()
avg_fps = 1. / (timer.get_avg_time() + 1e-7)
pbar.set_description(f'idx {idx}, fps {avg_fps:.2f}')

for _ in range(args.consumer):
que.put('quit')
for consumer in consumers:
consumer.join()
pbar.close()

# merge frames to video
video_save_path = os.path.join(args.output, f'{video_name}_{args.suffix}.mp4')
os.system(f'ffmpeg -r {args.fps} -i {save_frame_folder}/frame%08d_out.{extension} -i {args.input}'
f' -map 0:v:0 -map 1:a:0 -c:a copy -c:v libx264 -r {args.fps} -pix_fmt yuv420p {video_save_path}')
# delete tmp file
shutil.rmtree(save_frame_folder)
frame_folder = os.path.join('tmp_frames', video_name)
if os.path.isdir(frame_folder):
shutil.rmtree(frame_folder)


def main():
"""Inference demo for Real-ESRGAN.
It mainly for restoring anime videos.
Expand All @@ -39,6 +227,8 @@ def main():
'--fp32', action='store_true', help='Use fp32 precision during inference. Default: fp16 (half precision).')
parser.add_argument('--fps', type=float, default=None, help='FPS of the output video')
parser.add_argument('--consumer', type=int, default=4, help='Number of IO consumers')
parser.add_argument('--stream', action='store_true')
parser.add_argument('--ffmpeg_bin', type=str, default='ffmpeg', help='The path to ffmpeg')

parser.add_argument(
'--alpha_upsampler',
Expand All @@ -52,6 +242,8 @@ def main():
help='Image extension. Options: auto | jpg | png, auto means using the same extension as inputs')
args = parser.parse_args()

args.input = args.input.rstrip('/').rstrip('\\')

# ---------------------- determine models according to model names ---------------------- #
args.model_name = args.model_name.split('.pth')[0]
if args.model_name in ['RealESRGAN_x4plus', 'RealESRNet_x4plus']: # x4 RRDBNet model
Expand Down Expand Up @@ -84,6 +276,11 @@ def main():
pre_pad=args.pre_pad,
half=not args.fp32)

if 'anime' in args.model_name and args.face_enhance:
print('face_enhance is not supported in anime models, we turned this option off for you. '
'if you insist on turning it on, please manually comment the relevant lines of code.')
args.face_enhance = False

if args.face_enhance: # Use GFPGAN for face enhancement
from gfpgan import GFPGANer
face_enhancer = GFPGANer(
Expand All @@ -92,93 +289,15 @@ def main():
arch='clean',
channel_multiplier=2,
bg_upsampler=upsampler)
os.makedirs(args.output, exist_ok=True)
# for saving restored frames
save_frame_folder = os.path.join(args.output, 'frames_tmpout')
os.makedirs(save_frame_folder, exist_ok=True)

# input can be a video file / a folder of frames / an image
if mimetypes.guess_type(args.input)[0].startswith('video'): # is a video file
video_name = os.path.splitext(os.path.basename(args.input))[0]
frame_folder = os.path.join('tmp_frames', video_name)
os.makedirs(frame_folder, exist_ok=True)
# use ffmpeg to extract frames
os.system(f'ffmpeg -i {args.input} -qscale:v 1 -qmin 1 -qmax 1 -vsync 0 {frame_folder}/frame%08d.png')
# get image path list
paths = sorted(glob.glob(os.path.join(frame_folder, '*')))
# get input video fps
if args.fps is None:

import ffmpeg
probe = ffmpeg.probe(args.input)
video_streams = [stream for stream in probe['streams'] if stream['codec_type'] == 'video']
args.fps = eval(video_streams[0]['avg_frame_rate'])
elif mimetypes.guess_type(args.input)[0].startswith('image'): # is an image file
paths = [args.input]
video_name = 'video'
else:
paths = sorted(glob.glob(os.path.join(args.input, '*')))
video_name = 'video'
face_enhancer = None

timer = AvgTimer()
timer.start()
pbar = tqdm(total=len(paths), unit='frame', desc='inference')
# set up prefetch reader
reader = PrefetchReader(paths, num_prefetch_queue=4)
reader.start()

que = queue.Queue()
consumers = [IOConsumer(args, que, f'IO_{i}') for i in range(args.consumer)]
for consumer in consumers:
consumer.start()

for idx, (path, img) in enumerate(zip(paths, reader)):
imgname, extension = os.path.splitext(os.path.basename(path))
if len(img.shape) == 3 and img.shape[2] == 4:
img_mode = 'RGBA'
else:
img_mode = None

try:
if args.face_enhance:
_, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
else:
output, _ = upsampler.enhance(img, outscale=args.outscale)
except RuntimeError as error:
print('Error', error)
print('If you encounter CUDA out of memory, try to set --tile with a smaller number.')

else:
if args.ext == 'auto':
extension = extension[1:]
else:
extension = args.ext
if img_mode == 'RGBA': # RGBA images should be saved in png format
extension = 'png'
save_path = os.path.join(save_frame_folder, f'{imgname}_out.{extension}')

que.put({'output': output, 'save_path': save_path})

pbar.update(1)
torch.cuda.synchronize()
timer.record()
avg_fps = 1. / (timer.get_avg_time() + 1e-7)
pbar.set_description(f'idx {idx}, fps {avg_fps:.2f}')

for _ in range(args.consumer):
que.put('quit')
for consumer in consumers:
consumer.join()
pbar.close()
os.makedirs(args.output, exist_ok=True)

# merge frames to video
video_save_path = os.path.join(args.output, f'{video_name}_{args.suffix}.mp4')
os.system(f'ffmpeg -r {args.fps} -i {save_frame_folder}/frame%08d_out.{extension} -i {args.input}'
f' -map 0:v:0 -map 1:a:0 -c:a copy -c:v libx264 -r {args.fps} -pix_fmt yuv420p {video_save_path}')
# delete tmp file
shutil.rmtree(save_frame_folder)
if os.path.isdir(frame_folder):
shutil.rmtree(frame_folder)
if args.stream:
inference_stream(args, upsampler, face_enhancer)
else:
inference_frames(args, upsampler, face_enhancer)


if __name__ == '__main__':
Expand Down

0 comments on commit cdc14b7

Please sign in to comment.