I am currently using a custom trained yolov5 model to run object detection inference on live youtube videos, the problem is that the videos are streamed at 30 FPS , I actually don't want to process each frame for object detection and just process every nth frame.
I looked at the LoadStreams() class in the official yolov5 repo but I am not able to change the captured frame to be every 10th frame
class LoadStreams:
# YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP streams`
def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True):
self.mode = 'stream'
self.img_size = img_size
self.stride = stride
if os.path.isfile(sources):
with open(sources) as f:
sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
else:
sources = [sources]
n = len(sources)
self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
self.sources = [clean_str(x) for x in sources] # clean source names for later
self.auto = auto
for i, s in enumerate(sources): # index, source
# Start thread to read frames from video stream
st = f'{i + 1}/{n}: {s}... '
if urlparse(s).hostname in ('www.youtube.com', 'youtube.com', 'youtu.be'): # if source is YouTube video
check_requirements(('pafy', 'youtube_dl==2020.12.2'))
import pafy
s = pafy.new(s).getbest(preftype="mp4").url # YouTube URL
s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam
if s == 0:
assert not is_colab(), '--source 0 webcam unsupported on Colab. Rerun command in a local environment.'
assert not is_kaggle(), '--source 0 webcam unsupported on Kaggle. Rerun command in a local environment.'
cap = cv2.VideoCapture(s)
assert cap.isOpened(), f'{st}Failed to open {s}'
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = cap.get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan
self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback
self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback
_, self.imgs[i] = cap.read() # guarantee first frame
self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
self.threads[i].start()
LOGGER.info('') # newline
# check for common shapes
s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs])
self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
if not self.rect:
LOGGER.warning('WARNING: Stream shapes differ. For optimal performance supply similarly-shaped streams.')
def update(self, i, cap, stream):
# Read stream `i` frames in daemon thread
n, f, read = 0, self.frames[i], 1 # frame number, frame array, inference every 'read' frame
while cap.isOpened() and n < f:
n += 1
# _, self.imgs[index] = cap.read()
cap.grab()
if n % read == 0:
success, im = cap.retrieve()
if success:
self.imgs[i] = im
else:
LOGGER.warning('WARNING: Video stream unresponsive, please check your IP camera connection.')
self.imgs[i] = np.zeros_like(self.imgs[i])
cap.open(stream) # re-open stream if signal was lost
time.sleep(0.0) # wait time
def __iter__(self):
self.count = -1
return self
def __next__(self):
self.count += 1
if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'): # q to quit
cv2.destroyAllWindows()
raise StopIteration
# Letterbox
img0 = self.imgs.copy()
img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0]
# Stack
img = np.stack(img, 0)
# Convert
img = img[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW
img = np.ascontiguousarray(img)
return self.sources, img, img0, None, ''
def __len__(self):
return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years
