def main(args):
# Create output directory if needed
os.makedirs(args.output, exist_ok=True)
# Create pipeline steps
capture_video = CaptureVideo(
int(args.input) if args.input.isdigit() else args.input)
display_video = DisplayVideo("image") \
if args.display else None
save_image = SaveImage("image", args.output, image_ext=args.image_ext)
# Create image processing pipeline
pipeline = (capture_video | display_video | save_image)
# Iterate through pipeline
try:
for _ in tqdm(pipeline,
total=capture_video.frame_count
if capture_video.frame_count > 0 else None,
disable=not args.progress):
pass
except StopIteration:
return
except KeyboardInterrupt:
return
finally:
# Pipeline cleanup
capture_video.cleanup()
def main(args):
# Create pipeline steps
capture_video = CaptureVideo(
int(args.input) if args.input.isdigit() else args.input)
detect_faces = DetectFaces(prototxt=args.prototxt,
model=args.model,
confidence=args.confidence,
batch_size=args.batch_size)
save_faces = SaveFaces(args.output)
summary_file = os.path.join(args.output, args.out_summary)
save_summary = SaveSummary(summary_file)
annotate_image = AnnotateImage("annotated_image") \
if args.display or args.out_video else None
display_video = DisplayVideo("annotated_image") \
if args.display else None
save_video = SaveVideo("annotated_image", os.path.join(args.output, args.out_video), fps=capture_video.fps) \
if args.out_video else None
# Create image processing pipeline
pipeline = (capture_video | detect_faces | save_faces | annotate_image
| display_video | save_video | save_summary)
# Iterate through pipeline
progress = tqdm(total=capture_video.frame_count
if capture_video.frame_count > 0 else None,
disable=not args.progress)
try:
for _ in pipeline:
progress.update(1)
except StopIteration:
return
except KeyboardInterrupt:
return
finally:
progress.close()
# Pipeline cleanup
capture_video.cleanup()
if display_video:
display_video.cleanup()
if save_video:
save_video.cleanup()
print(f"[INFO] Saving summary to {summary_file}...")
save_summary.write()
def create_pipeline():
capture_video = CaptureVideo("demo.mp4")
mp.set_start_method("spawn", force=True)
predict = AsyncPredict(model_path=WEIGHTS_FILE,
load_model_fn=load_fcn,
num_cpus=CPUS,
queue_size=QUEUE_SIZE,
ordered=True)
# separate_background = SeparateBackground("vis_image")
separate_background = VirtualBackground("vis_image", BACKGROUND_IMAGE)
save_video = SaveVideo("vis_image", os.path.join(OUTPUT, OUT_VIDEO),
capture_video.fps * 0.5)
pipeline = (capture_video | predict | separate_background | save_video)
return iter(pipeline), (capture_video, predict, save_video)
def main(args):
import sys
# Create output directory if needed
os.makedirs(args.output, exist_ok=True)
# First create video capture
if args.input.isdigit():
capture_video = CaptureVideo(int(args.input))
elif os.path.isfile(args.input):
capture_video = CaptureVideo(args.input)
else:
print("Invalid Type put in!")
sys.exit(1)
if args.single_process:
predict = None
else:
mp.set_start_method("spawn", force=True)
predict = AsyncPredict(model_path=args.weights_file,
load_model_fn=load_fcn,
num_cpus=args.cpus,
queue_size=args.queue_size,
ordered=True)
separate_background = SeparateBackground("vis_image")
save_video = SaveVideo("vis_image",
os.path.join(args.output, args.out_video),
capture_video.fps if args.fps is None else args.fps)
pipeline = (capture_video | predict | separate_background | save_video)
try:
for _ in tqdm(pipeline,
total=capture_video.frame_count
if capture_video.frame_count > 0 else None,
disable=not args.progress):
pass
except StopIteration:
return
except KeyboardInterrupt:
return
finally:
# Clean up of file handles etc.
if isinstance(predict, CaptureVideo):
capture_video.cleanup()
if isinstance(predict, AsyncPredict):
predict.cleanup()
if save_video:
save_video.cleanup()
def main(args):
# Create output directory if needed
os.makedirs(args.output, exist_ok=True)
# Create pipeline steps
if args.input.isdigit():
capture_video = CaptureVideo(int(args.input))
elif os.path.isfile(args.input):
capture_video = CaptureVideo(args.input)
elif os.path.isdir(args.input):
capture_video = CaptureFrames(args.input)
cfg = detectron.setup_cfg(config_file=args.config_file,
weights_file=args.weights_file,
config_opts=args.config_opts,
confidence_threshold=args.confidence_threshold,
cpu=False if args.gpus > 0 else True)
if not args.single_process:
mp.set_start_method("spawn", force=True)
predict = AsyncPredict(cfg,
num_gpus=args.gpus,
num_cpus=args.cpus,
queue_size=args.queue_size,
ordered=True)
else:
predict = Predict(cfg)
track_pose = TrackPose(
link_len=args.track_link_len,
num=args.track_num,
mag=args.track_mag,
match=args.track_match,
orb_features=args.track_orb_features) if args.track_pose else None
if args.separate_background:
separate_background = SeparateBackground("vis_image")
annotate_video = None
else:
separate_background = None
metadata_name = cfg.DATASETS.TEST[0] if len(
cfg.DATASETS.TEST) else "__unused"
annotate_video = AnnotateVideo("vis_image",
metadata_name,
predictions=track_pose is None,
pose_flows=track_pose is not None)
display_video = DisplayVideo("vis_image") \
if args.display else None
save_video = SaveVideo("vis_image", os.path.join(args.output, args.out_video),
capture_video.fps if args.fps is None else args.fps) \
if args.out_video else None
# Create image processing pipeline
pipeline = (capture_video | predict | track_pose | separate_background
| annotate_video | display_video | save_video)
# Iterate through pipeline
try:
for _ in tqdm(pipeline,
total=capture_video.frame_count
if capture_video.frame_count > 0 else None,
disable=not args.progress):
pass
except StopIteration:
return
except KeyboardInterrupt:
return
finally:
# Pipeline cleanup
if isinstance(predict, CaptureVideo):
capture_video.cleanup()
if isinstance(predict, AsyncPredict):
predict.cleanup()
if display_video:
display_video.cleanup()
if save_video:
save_video.cleanup()