HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.0.239 Ultralytics Actions and hub-sdk adoption (#7431)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-01-10 03:16:08 +01:00 • committed by GitHub
parent e795277391
commit fe27db2f6e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
139 changed files with 6870 additions and 5125 deletions
Download patch file Download diff file Expand all files Collapse all files

137
ultralytics/data/loaders.py
View file

@ -23,6 +23,7 @@ from ultralytics.utils.checks import check_requirements
@dataclass
class SourceTypes:
"""Class to represent various types of input sources for predictions."""
webcam: bool = False
screenshot: bool = False
from_img: bool = False
@ -59,12 +60,12 @@ class LoadStreams:
__len__: Return the length of the sources object.
"""
def __init__(self, sources='file.streams', imgsz=640, vid_stride=1, buffer=False):
def __init__(self, sources="file.streams", imgsz=640, vid_stride=1, buffer=False):
"""Initialize instance variables and check for consistent input stream shapes."""
torch.backends.cudnn.benchmark = True # faster for fixed-size inference
self.buffer = buffer # buffer input streams
self.running = True # running flag for Thread
self.mode = 'stream'
self.mode = "stream"
self.imgsz = imgsz
self.vid_stride = vid_stride # video frame-rate stride
@ -79,33 +80,36 @@ class LoadStreams:
self.sources = [ops.clean_str(x) for x in sources] # clean source names for later
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
st = f"{i + 1}/{n}: {s}... "
if urlparse(s).hostname in ("www.youtube.com", "youtube.com", "youtu.be"): # if source is YouTube video
# YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/LNwODJXcvt4'
s = get_best_youtube_url(s)
s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam
if s == 0 and (is_colab() or is_kaggle()):
raise NotImplementedError("'source=0' webcam not supported in Colab and Kaggle notebooks. "
"Try running 'source=0' in a local environment.")
raise NotImplementedError(
"'source=0' webcam not supported in Colab and Kaggle notebooks. "
"Try running 'source=0' in a local environment."
)
self.caps[i] = cv2.VideoCapture(s) # store video capture object
if not self.caps[i].isOpened():
raise ConnectionError(f'{st}Failed to open {s}')
raise ConnectionError(f"{st}Failed to open {s}")
w = int(self.caps[i].get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(self.caps[i].get(cv2.CAP_PROP_FRAME_HEIGHT))
fps = self.caps[i].get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan
self.frames[i] = max(int(self.caps[i].get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float(
'inf') # infinite stream fallback
"inf"
) # infinite stream fallback
self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback
success, im = self.caps[i].read() # guarantee first frame
if not success or im is None:
raise ConnectionError(f'{st}Failed to read images from {s}')
raise ConnectionError(f"{st}Failed to read images from {s}")
self.imgs[i].append(im)
self.shape[i] = im.shape
self.threads[i] = Thread(target=self.update, args=([i, self.caps[i], s]), daemon=True)
LOGGER.info(f'{st}Success ✅ ({self.frames[i]} frames of shape {w}x{h} at {self.fps[i]:.2f} FPS)')
LOGGER.info(f"{st}Success ✅ ({self.frames[i]} frames of shape {w}x{h} at {self.fps[i]:.2f} FPS)")
self.threads[i].start()
LOGGER.info('') # newline
LOGGER.info("") # newline
# Check for common shapes
self.bs = self.__len__()
@ -121,7 +125,7 @@ class LoadStreams:
success, im = cap.retrieve()
if not success:
im = np.zeros(self.shape[i], dtype=np.uint8)
LOGGER.warning('WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.')
LOGGER.warning("WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.")
cap.open(stream) # re-open stream if signal was lost
if self.buffer:
self.imgs[i].append(im)
@ -140,7 +144,7 @@ class LoadStreams:
try:
cap.release() # release video capture
except Exception as e:
LOGGER.warning(f'WARNING ⚠️ Could not release VideoCapture object: {e}')
LOGGER.warning(f"WARNING ⚠️ Could not release VideoCapture object: {e}")
cv2.destroyAllWindows()
def __iter__(self):
@ -154,16 +158,15 @@ class LoadStreams:
images = []
for i, x in enumerate(self.imgs):
# Wait until a frame is available in each buffer
while not x:
if not self.threads[i].is_alive() or cv2.waitKey(1) == ord('q'): # q to quit
if not self.threads[i].is_alive() or cv2.waitKey(1) == ord("q"): # q to quit
self.close()
raise StopIteration
time.sleep(1 / min(self.fps))
x = self.imgs[i]
if not x:
LOGGER.warning(f'WARNING ⚠️ Waiting for stream {i}')
LOGGER.warning(f"WARNING ⚠️ Waiting for stream {i}")
# Get and remove the first frame from imgs buffer
if self.buffer:
@ -174,7 +177,7 @@ class LoadStreams:
images.append(x.pop(-1) if x else np.zeros(self.shape[i], dtype=np.uint8))
x.clear()
return self.sources, images, None, ''
return self.sources, images, None, ""
def __len__(self):
"""Return the length of the sources object."""
@ -209,7 +212,7 @@ class LoadScreenshots:
def __init__(self, source, imgsz=640):
"""Source = [screen_number left top width height] (pixels)."""
check_requirements('mss')
check_requirements("mss")
import mss # noqa
source, *params = source.split()
@ -221,18 +224,18 @@ class LoadScreenshots:
elif len(params) == 5:
self.screen, left, top, width, height = (int(x) for x in params)
self.imgsz = imgsz
self.mode = 'stream'
self.mode = "stream"
self.frame = 0
self.sct = mss.mss()
self.bs = 1
# Parse monitor shape
monitor = self.sct.monitors[self.screen]
self.top = monitor['top'] if top is None else (monitor['top'] + top)
self.left = monitor['left'] if left is None else (monitor['left'] + left)
self.width = width or monitor['width']
self.height = height or monitor['height']
self.monitor = {'left': self.left, 'top': self.top, 'width': self.width, 'height': self.height}
self.top = monitor["top"] if top is None else (monitor["top"] + top)
self.left = monitor["left"] if left is None else (monitor["left"] + left)
self.width = width or monitor["width"]
self.height = height or monitor["height"]
self.monitor = {"left": self.left, "top": self.top, "width": self.width, "height": self.height}
def __iter__(self):
"""Returns an iterator of the object."""
@ -241,7 +244,7 @@ class LoadScreenshots:
def __next__(self):
"""mss screen capture: get raw pixels from the screen as np array."""
im0 = np.asarray(self.sct.grab(self.monitor))[:, :, :3] # BGRA to BGR
s = f'screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: '
s = f"screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: "
self.frame += 1
return [str(self.screen)], [im0], None, s # screen, img, vid_cap, string
@ -274,32 +277,32 @@ class LoadImages:
def __init__(self, path, imgsz=640, vid_stride=1):
"""Initialize the Dataloader and raise FileNotFoundError if file not found."""
parent = None
if isinstance(path, str) and Path(path).suffix == '.txt': # *.txt file with img/vid/dir on each line
if isinstance(path, str) and Path(path).suffix == ".txt": # *.txt file with img/vid/dir on each line
parent = Path(path).parent
path = Path(path).read_text().splitlines() # list of sources
files = []
for p in sorted(path) if isinstance(path, (list, tuple)) else [path]:
a = str(Path(p).absolute()) # do not use .resolve() https://github.com/ultralytics/ultralytics/issues/2912
if '*' in a:
if "*" in a:
files.extend(sorted(glob.glob(a, recursive=True))) # glob
elif os.path.isdir(a):
files.extend(sorted(glob.glob(os.path.join(a, '*.*')))) # dir
files.extend(sorted(glob.glob(os.path.join(a, "*.*")))) # dir
elif os.path.isfile(a):
files.append(a) # files (absolute or relative to CWD)
elif parent and (parent / p).is_file():
files.append(str((parent / p).absolute())) # files (relative to *.txt file parent)
else:
raise FileNotFoundError(f'{p} does not exist')
raise FileNotFoundError(f"{p} does not exist")
images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
images = [x for x in files if x.split(".")[-1].lower() in IMG_FORMATS]
videos = [x for x in files if x.split(".")[-1].lower() in VID_FORMATS]
ni, nv = len(images), len(videos)
self.imgsz = imgsz
self.files = images + videos
self.nf = ni + nv # number of files
self.video_flag = [False] * ni + [True] * nv
self.mode = 'image'
self.mode = "image"
self.vid_stride = vid_stride # video frame-rate stride
self.bs = 1
if any(videos):
@ -307,8 +310,10 @@ class LoadImages:
else:
self.cap = None
if self.nf == 0:
raise FileNotFoundError(f'No images or videos found in {p}. '
f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}')
raise FileNotFoundError(
f"No images or videos found in {p}. "
f"Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}"
)
def __iter__(self):
"""Returns an iterator object for VideoStream or ImageFolder."""
@ -323,7 +328,7 @@ class LoadImages:
if self.video_flag[self.count]:
# Read video
self.mode = 'video'
self.mode = "video"
for _ in range(self.vid_stride):
self.cap.grab()
success, im0 = self.cap.retrieve()
@ -338,15 +343,15 @@ class LoadImages:
self.frame += 1
# im0 = self._cv2_rotate(im0) # for use if cv2 autorotation is False
s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
s = f"video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: "
else:
# Read image
self.count += 1
im0 = cv2.imread(path) # BGR
if im0 is None:
raise FileNotFoundError(f'Image Not Found {path}')
s = f'image {self.count}/{self.nf} {path}: '
raise FileNotFoundError(f"Image Not Found {path}")
s = f"image {self.count}/{self.nf} {path}: "
return [path], [im0], self.cap, s
@ -385,20 +390,20 @@ class LoadPilAndNumpy:
"""Initialize PIL and Numpy Dataloader."""
if not isinstance(im0, list):
im0 = [im0]
self.paths = [getattr(im, 'filename', f'image{i}.jpg') for i, im in enumerate(im0)]
self.paths = [getattr(im, "filename", f"image{i}.jpg") for i, im in enumerate(im0)]
self.im0 = [self._single_check(im) for im in im0]
self.imgsz = imgsz
self.mode = 'image'
self.mode = "image"
# Generate fake paths
self.bs = len(self.im0)
@staticmethod
def _single_check(im):
"""Validate and format an image to numpy array."""
assert isinstance(im, (Image.Image, np.ndarray)), f'Expected PIL/np.ndarray image type, but got {type(im)}'
assert isinstance(im, (Image.Image, np.ndarray)), f"Expected PIL/np.ndarray image type, but got {type(im)}"
if isinstance(im, Image.Image):
if im.mode != 'RGB':
im = im.convert('RGB')
if im.mode != "RGB":
im = im.convert("RGB")
im = np.asarray(im)[:, :, ::-1]
im = np.ascontiguousarray(im) # contiguous
return im
@ -412,7 +417,7 @@ class LoadPilAndNumpy:
if self.count == 1: # loop only once as it's batch inference
raise StopIteration
self.count += 1
return self.paths, self.im0, None, ''
return self.paths, self.im0, None, ""
def __iter__(self):
"""Enables iteration for class LoadPilAndNumpy."""
@ -441,14 +446,16 @@ class LoadTensor:
"""Initialize Tensor Dataloader."""
self.im0 = self._single_check(im0)
self.bs = self.im0.shape[0]
self.mode = 'image'
self.paths = [getattr(im, 'filename', f'image{i}.jpg') for i, im in enumerate(im0)]
self.mode = "image"
self.paths = [getattr(im, "filename", f"image{i}.jpg") for i, im in enumerate(im0)]
@staticmethod
def _single_check(im, stride=32):
"""Validate and format an image to torch.Tensor."""
s = f'WARNING ⚠️ torch.Tensor inputs should be BCHW i.e. shape(1, 3, 640, 640) ' \
f'divisible by stride {stride}. Input shape{tuple(im.shape)} is incompatible.'
s = (
f"WARNING ⚠️ torch.Tensor inputs should be BCHW i.e. shape(1, 3, 640, 640) "
f"divisible by stride {stride}. Input shape{tuple(im.shape)} is incompatible."
)
if len(im.shape) != 4:
if len(im.shape) != 3:
raise ValueError(s)
@ -457,8 +464,10 @@ class LoadTensor:
if im.shape[2] % stride or im.shape[3] % stride:
raise ValueError(s)
if im.max() > 1.0 + torch.finfo(im.dtype).eps: # torch.float32 eps is 1.2e-07
LOGGER.warning(f'WARNING ⚠️ torch.Tensor inputs should be normalized 0.0-1.0 but max value is {im.max()}. '
f'Dividing input by 255.')
LOGGER.warning(
f"WARNING ⚠️ torch.Tensor inputs should be normalized 0.0-1.0 but max value is {im.max()}. "
f"Dividing input by 255."
)
im = im.float() / 255.0
return im
@ -473,7 +482,7 @@ class LoadTensor:
if self.count == 1:
raise StopIteration
self.count += 1
return self.paths, self.im0, None, ''
return self.paths, self.im0, None, ""
def __len__(self):
"""Returns the batch size."""
@ -485,12 +494,14 @@ def autocast_list(source):
files = []
for im in source:
if isinstance(im, (str, Path)): # filename or uri
files.append(Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im))
files.append(Image.open(requests.get(im, stream=True).raw if str(im).startswith("http") else im))
elif isinstance(im, (Image.Image, np.ndarray)): # PIL or np Image
files.append(im)
else:
raise TypeError(f'type {type(im).__name__} is not a supported Ultralytics prediction source type. \n'
f'See https://docs.ultralytics.com/modes/predict for supported source types.')
raise TypeError(
f"type {type(im).__name__} is not a supported Ultralytics prediction source type. \n"
f"See https://docs.ultralytics.com/modes/predict for supported source types."
)
return files
@ -513,16 +524,18 @@ def get_best_youtube_url(url, use_pafy=True):
(str): The URL of the best quality MP4 video stream, or None if no suitable stream is found.
"""
if use_pafy:
check_requirements(('pafy', 'youtube_dl==2020.12.2'))
check_requirements(("pafy", "youtube_dl==2020.12.2"))
import pafy # noqa
return pafy.new(url).getbestvideo(preftype='mp4').url
return pafy.new(url).getbestvideo(preftype="mp4").url
else:
check_requirements('yt-dlp')
check_requirements("yt-dlp")
import yt_dlp
with yt_dlp.YoutubeDL({'quiet': True}) as ydl:
with yt_dlp.YoutubeDL({"quiet": True}) as ydl:
info_dict = ydl.extract_info(url, download=False) # extract info
for f in reversed(info_dict.get('formats', [])): # reversed because best is usually last
for f in reversed(info_dict.get("formats", [])): # reversed because best is usually last
# Find a format with video codec, no audio, *.mp4 extension at least 1920x1080 size
good_size = (f.get('width') or 0) >= 1920 or (f.get('height') or 0) >= 1080
if good_size and f['vcodec'] != 'none' and f['acodec'] == 'none' and f['ext'] == 'mp4':
return f.get('url')
good_size = (f.get("width") or 0) >= 1920 or (f.get("height") or 0) >= 1080
if good_size and f["vcodec"] != "none" and f["acodec"] == "none" and f["ext"] == "mp4":
return f.get("url")