xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.155 allow imgsz and batch resume changes (#4366)

Browse Source 
Co-authored-by: Mostafa Nemati <58460889+monemati@users.noreply.github.com>
Co-authored-by: Eduard Voiculescu <eduardvoiculescu95@gmail.com>
This commit is contained in:
Glenn Jocher
2023-08-15 22:02:23 +02:00
committed by GitHub
parent 60cad0c592
commit 9a0555eca4
15 changed files with 84 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ultralytics/data/build.py
View File

@ -120,7 +120,7 @@ def check_source(source):
screenshot = source.lower() == 'screen'
if is_url and is_file:
source = check_file(source) # download
elif isinstance(source, tuple(LOADERS)):
elif isinstance(source, LOADERS):
in_memory = True
elif isinstance(source, (list, tuple)):
source = autocast_list(source) # convert all list elements to PIL or np arrays

29
ultralytics/data/loaders.py
View File

@ -98,7 +98,7 @@ class LoadStreams:
def close(self):
"""Close stream loader and release resources."""
self.running = False # stop flag for Thread
for i, thread in enumerate(self.threads):
for thread in self.threads:
if thread.is_alive():
thread.join(timeout=5) # Add timeout
for cap in self.caps: # Iterate through the stored VideoCapture objects
@ -210,7 +210,6 @@ class LoadImages:
self.vid_stride = vid_stride # video frame-rate stride
self.bs = 1
if any(videos):
self.orientation = None # rotation degrees
self._new_video(videos[0]) # new video
else:
self.cap = None
@ -263,20 +262,6 @@ class LoadImages:
self.frame = 0
self.cap = cv2.VideoCapture(path)
self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT) / self.vid_stride)
if hasattr(cv2, 'CAP_PROP_ORIENTATION_META'): # cv2<4.6.0 compatibility
self.orientation = int(self.cap.get(cv2.CAP_PROP_ORIENTATION_META)) # rotation degrees
# Disable auto-orientation due to known issues in https://github.com/ultralytics/yolov5/issues/8493
# self.cap.set(cv2.CAP_PROP_ORIENTATION_AUTO, 0)
def _cv2_rotate(self, im):
"""Rotate a cv2 video manually."""
if self.orientation == 0:
return cv2.rotate(im, cv2.ROTATE_90_CLOCKWISE)
elif self.orientation == 180:
return cv2.rotate(im, cv2.ROTATE_90_COUNTERCLOCKWISE)
elif self.orientation == 90:
return cv2.rotate(im, cv2.ROTATE_180)
return im
def __len__(self):
"""Returns the number of files in the object."""
@ -385,10 +370,10 @@ def autocast_list(source):
return files
LOADERS = [LoadStreams, LoadPilAndNumpy, LoadImages, LoadScreenshots]
LOADERS = LoadStreams, LoadPilAndNumpy, LoadImages, LoadScreenshots # tuple
def get_best_youtube_url(url, use_pafy=True):
def get_best_youtube_url(url, use_pafy=False):
"""
Retrieves the URL of the best quality MP4 video stream from a given YouTube video.
@ -411,9 +396,11 @@ def get_best_youtube_url(url, use_pafy=True):
import yt_dlp
with yt_dlp.YoutubeDL({'quiet': True}) as ydl:
info_dict = ydl.extract_info(url, download=False) # extract info
for f in info_dict.get('formats', None):
if f['vcodec'] != 'none' and f['acodec'] == 'none' and f['ext'] == 'mp4' and f.get('width') > 1280:
return f.get('url', None)
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')
if __name__ == '__main__':

22
ultralytics/data/utils.py
View File

@ -142,16 +142,12 @@ def polygon2mask(imgsz, polygons, color=1, downsample_ratio=1):
downsample_ratio (int): downsample ratio
"""
mask = np.zeros(imgsz, dtype=np.uint8)
polygons = np.asarray(polygons)
polygons = polygons.astype(np.int32)
shape = polygons.shape
polygons = polygons.reshape(shape[0], -1, 2)
polygons = np.asarray(polygons, dtype=np.int32)
polygons = polygons.reshape((polygons.shape[0], -1, 2))
cv2.fillPoly(mask, polygons, color=color)
nh, nw = (imgsz[0] // downsample_ratio, imgsz[1] // downsample_ratio)
# NOTE: fillPoly firstly then resize is trying the keep the same way
# of loss calculation when mask-ratio=1.
mask = cv2.resize(mask, (nw, nh))
return mask
# NOTE: fillPoly first then resize is trying to keep the same way of loss calculation when mask-ratio=1.
return cv2.resize(mask, (nw, nh))
def polygons2masks(imgsz, polygons, color, downsample_ratio=1):
@ -162,11 +158,7 @@ def polygons2masks(imgsz, polygons, color, downsample_ratio=1):
color (int): color
downsample_ratio (int): downsample ratio
"""
masks = []
for si in range(len(polygons)):
mask = polygon2mask(imgsz, [polygons[si].reshape(-1)], color, downsample_ratio)
masks.append(mask)
return np.array(masks)
return np.array([polygon2mask(imgsz, [x.reshape(-1)], color, downsample_ratio) for x in polygons])
def polygons2masks_overlap(imgsz, segments, downsample_ratio=1):
@ -421,7 +413,7 @@ class HUBDatasetStats:
else:
raise ValueError('Undefined dataset task.')
zipped = zip(labels['cls'], coordinates)
return [[int(c), *(round(float(x), 4) for x in points)] for c, points in zipped]
return [[int(c[0]), *(round(float(x), 4) for x in points)] for c, points in zipped]
for split in 'train', 'val', 'test':
if self.data.get(split) is None:
@ -563,7 +555,7 @@ def zip_directory(dir, use_zipfile_library=True):
def autosplit(path=DATASETS_DIR / 'coco8/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
"""
Autosplit a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.
Automatically split a dataset into train/val/test splits and save the resulting splits into autosplit_*.txt files.
Args:
path (Path, optional): Path to images directory. Defaults to DATASETS_DIR / 'coco8/images'.