yolov5跳帧检测
yolov5视频跳帧检测
如何实现从这样
到这样跳十帧检测一次？
我感觉应该调整datasets文件里的LoadStreams但是调了update之类的，半天没有效果
detect文件我也尝试在for path, img, im0s, vid_cap in dataset里加语句也没有效果
相关datasets代码如下：
class LoadStreams: # multiple IP or RTSP cameras
def __init__(self, sources='streams.txt', img_size=640, stride=32):
#self.skip_frames = skip_frames # 跳帧间隔
#self.frame_counter = 0 # 帧计数器
self.mode = 'stream'
self.img_size = img_size
self.stride = stride
if os.path.isfile(sources):
with open(sources, 'r') 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
for i, s in enumerate(sources): # index, source
# Start thread to read frames from video stream
print(f'{i + 1}/{n}: {s}... ', end='')
if 'youtube.com/' in s or 'youtu.be/' in s: # if source is YouTube video
check_requirements(('pafy', 'youtube_dl'))
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
cap = cv2.VideoCapture(s)
assert cap.isOpened(), f'Failed to open {s}'
w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
self.fps[i] = max(cap.get(cv2.CAP_PROP_FPS) % 100, 0) or 30.0 # 30 FPS fallback
self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback
_, self.imgs[i] = cap.read() # guarantee first frame
self.threads[i] = Thread(target=self.update, args=([i, cap]), daemon=True)
print(f" success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
self.threads[i].start()
print('') # newline
# check for common shapes
s = np.stack([letterbox(x, self.img_size, stride=self.stride)[0].shape for x in self.imgs], 0) # shapes
self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
if not self.rect:
print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
def update(self, i, cap):
# 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()
self.imgs[i] = im if success else self.imgs[i] * 0
time.sleep(1 / self.fps[i]) # wait time
"""
while cap.isOpened() and n < f:
n += 1
cap.grab()
self.frame_counter += 1 # 帧计数器递增
if self.frame_counter % self.skip_frames == 0: # 跳帧检测
success, im = cap.retrieve()
self.imgs[i] = im if success else self.imgs[i] * 0
time.sleep(1 / self.fps[i]) # 等待时间
"""
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, auto=self.rect, stride=self.stride)[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
def img2label_paths(img_paths):
# Define label paths as a function of image paths
sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings
return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]
class LoadImagesAndLabels(Dataset): # for training/testing
def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
self.img_size = img_size
self.augment = augment
self.hyp = hyp
self.image_weights = image_weights
self.rect = False if image_weights else rect
self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
self.mosaic_border = [-img_size // 2, -img_size // 2]
self.stride = stride
self.path = path
self.albumentations = Albumentations() if augment else None
try:
f = [] # image files
for p in path if isinstance(path, list) else [path]:
p = Path(p) # os-agnostic
if p.is_dir(): # dir
f += glob.glob(str(p / '**' / '*.*'), recursive=True)
# f = list(p.rglob('**/*.*')) # pathlib
elif p.is_file(): # file
with open(p, 'r') as t:
t = t.read().strip().splitlines()
parent = str(p.parent) + os.sep
f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path
# f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
else:
raise Exception(f'{prefix}{p} does not exist')
self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in img_formats])
# self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats]) # pathlib
assert self.img_files, f'{prefix}No images found'
except Exception as e:
raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {help_url}')
# Check cache
self.label_files = img2label_paths(self.img_files) # labels
cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
try:
cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict
assert cache['version'] == 0.4 and cache['hash'] == get_hash(self.label_files + self.img_files)
except:
cache, exists = self.cache_labels(cache_path, prefix), False # cache
# Display cache
nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupted, total
if exists:
d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
tqdm(None, desc=prefix + d, total=n, initial=n) # display cache results
if cache['msgs']:
logging.info('\n'.join(cache['msgs'])) # display warnings
assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {help_url}'
# Read cache
[cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
labels, shapes, self.segments = zip(*cache.values())
self.labels = list(labels)
self.shapes = np.array(shapes, dtype=np.float64)
self.img_files = list(cache.keys()) # update
self.label_files = img2label_paths(cache.keys()) # update
if single_cls:
for x in self.labels:
x[:, 0] = 0
n = len(shapes) # number of images
bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index
nb = bi[-1] + 1 # number of batches
self.batch = bi # batch index of image
self.n = n
self.indices = range(n)
# Rectangular Training
if self.rect:
# Sort by aspect ratio
s = self.shapes # wh
ar = s[:, 1] / s[:, 0] # aspect ratio
irect = ar.argsort()
self.img_files = [self.img_files[i] for i in irect]
self.label_files = [self.label_files[i] for i in irect]
self.labels = [self.labels[i] for i in irect]
self.shapes = s[irect] # wh
ar = ar[irect]
# Set training image shapes
shapes = [[1, 1]] * nb
for i in range(nb):
ari = ar[bi == i]
mini, maxi = ari.min(), ari.max()
if maxi < 1:
shapes[i] = [maxi, 1]
elif mini > 1:
shapes[i] = [1, 1 / mini]
self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride
# Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
self.imgs = [None] * n
if cache_images:
gb = 0 # Gigabytes of cached images
self.img_hw0, self.img_hw = [None] * n, [None] * n
results = ThreadPool(num_threads).imap(lambda x: load_image(*x), zip(repeat(self), range(n)))
pbar = tqdm(enumerate(results), total=n)
for i, x in pbar:
self.imgs[i], self.img_hw0[i], self.img_hw[i] = x # img, hw_original, hw_resized = load_image(self, i)
gb += self.imgs[i].nbytes
pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB)'
pbar.close()
def cache_labels(self, path=Path('./labels.cache'), prefix=''):
# Cache dataset labels, check images and read shapes
x = {} # dict
nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels..."
with Pool(num_threads) as pool:
pbar = tqdm(pool.imap_unordered(verify_image_label, zip(self.img_files, self.label_files, repeat(prefix))),
desc=desc, total=len(self.img_files))
for im_file, l, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
nm += nm_f
nf += nf_f
ne += ne_f
nc += nc_f
if im_file:
x[im_file] = [l, shape, segments]
if msg:
msgs.append(msg)
pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
pbar.close()
if msgs:
logging.info('\n'.join(msgs))
if nf == 0:
logging.info(f'{prefix}WARNING: No labels found in {path}. See {help_url}')
x['hash'] = get_hash(self.label_files + self.img_files)
x['results'] = nf, nm, ne, nc, len(self.img_files)
x['msgs'] = msgs # warnings
x['version'] = 0.4 # cache version
try:
np.save(path, x) # save cache for next time
path.with_suffix('.cache.npy').rename(path) # remove .npy suffix
logging.info(f'{prefix}New cache created: {path}')
except Exception as e:
logging.info(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}') # path not writeable
return x
def __len__(self):
return len(self.img_files)
# def __iter__(self):
# self.count = -1
# print('ran dataset iter')
# #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
# return self
def __getitem__(self, index):
index = self.indices[index] # linear, shuffled, or image_weights
hyp = self.hyp
mosaic = self.mosaic and random.random() < hyp['mosaic']
if mosaic:
# Load mosaic
img, labels = load_mosaic(self, index)
shapes = None
# MixUp augmentation
if random.random() < hyp['mixup']:
img, labels = mixup(img, labels, *load_mosaic(self, random.randint(0, self.n - 1)))
else:
# Load image
img, (h0, w0), (h, w) = load_image(self, index)
# Letterbox
shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
labels = self.labels[index].copy()
if labels.size: # normalized xywh to pixel xyxy format
labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
if self.augment:
img, labels = random_perspective(img, labels,
degrees=hyp['degrees'],
translate=hyp['translate'],
scale=hyp['scale'],
shear=hyp['shear'],
perspective=hyp['perspective'])
nl = len(labels) # number of labels
if nl:
labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)
if self.augment:
# Albumentations
img, labels = self.albumentations(img, labels)
# HSV color-space
augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
# Flip up-down
if random.random() < hyp['flipud']:
img = np.flipud(img)
if nl:
labels[:, 2] = 1 - labels[:, 2]
# Flip left-right
if random.random() < hyp['fliplr']:
img = np.fliplr(img)
if nl:
labels[:, 1] = 1 - labels[:, 1]
# Cutouts
# labels = cutout(img, labels, p=0.5)
labels_out = torch.zeros((nl, 6))
if nl:
labels_out[:, 1:] = torch.from_numpy(labels)
# Convert
img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
img = np.ascontiguousarray(img)
return torch.from_numpy(img), labels_out, self.img_files[index], shapes
@staticmethod
def collate_fn(batch):
img, label, path, shapes = zip(*batch) # transposed
for i, l in enumerate(label):
l[:, 0] = i # add target image index for build_targets()
return torch.stack(img, 0), torch.cat(label, 0), path, shapes
@staticmethod
def collate_fn4(batch):
img, label, path, shapes = zip(*batch) # transposed
n = len(shapes) // 4
img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
ho = torch.tensor([[0., 0, 0, 1, 0, 0]])
wo = torch.tensor([[0., 0, 1, 0, 0, 0]])
s = torch.tensor([[1, 1, .5, .5, .5, .5]]) # scale
for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW
i *= 4
if random.random() < 0.5:
im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2., mode='bilinear', align_corners=False)[
0].type(img[i].type())
l = label[i]
else:
im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
l = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
img4.append(im)
label4.append(l)
for i, l in enumerate(label4):
l[:, 0] = i # add target image index for build_targets()
return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4
def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False):
""" Return dataset statistics dictionary with images and instances counts per split per class
Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', verbose=True)
Usage2: from utils.datasets import *; dataset_stats('../datasets/coco128.zip', verbose=True)
Arguments
path: Path to data.yaml or data.zip (with data.yaml inside data.zip)
autodownload: Attempt to download dataset if not found locally
verbose: Print stats dictionary
"""
def round_labels(labels):
# Update labels to integer class and 6 decimal place floats
return [[int(c), *[round(x, 6) for x in points]] for c, *points in labels]
def unzip(path):
# Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
if str(path).endswith('.zip'): # path is data.zip
assert os.system(f'unzip -q {path} -d {path.parent}') == 0, f'Error unzipping {path}'
data_dir = path.with_suffix('') # dataset directory
return True, data_dir, list(data_dir.rglob('*.yaml'))[0] # zipped, data_dir, yaml_path
else: # path is data.yaml
return False, None, path
zipped, data_dir, yaml_path = unzip(Path(path))
with open(check_file(yaml_path)) as f:
data = yaml.safe_load(f) # data dict
if zipped:
data['path'] = data_dir # TODO: should this be dir.resolve()?
check_dataset(data, autodownload) # download dataset if missing
nc = data['nc'] # number of classes
stats = {'nc': nc, 'names': data['names']} # statistics dictionary
for split in 'train', 'val', 'test':
if data.get(split) is None:
stats[split] = None # i.e. no test set
continue
x = []
dataset = LoadImagesAndLabels(data[split], augment=False, rect=True) # load dataset
if split == 'train':
cache_path = Path(dataset.label_files[0]).parent.with_suffix('.cache') # *.cache path
for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics'):
x.append(np.bincount(label[:, 0].astype(int), minlength=nc))
x = np.array(x) # shape(128x80)
stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()},
'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()),
'per_class': (x > 0).sum(0).tolist()},
'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in
zip(dataset.img_files, dataset.labels)]}
# Save, print and return
with open(cache_path.with_suffix('.json'), 'w') as f:
json.dump(stats, f) # save stats *.json
if verbose:
print(json.dumps(stats, indent=2, sort_keys=False))
# print(yaml.dump([stats], sort_keys=False, default_flow_style=False))
return stats
答案由GPT-4Plus大模型(语音)与博主@晓码自在合作编写(思路逐步分析-->完美代码-->完整注释在最下方)：
根据您的描述,您想实现Yolov5在视频检测时,从原来的连续检测改为每10帧检测一次,即实现跳帧检测的效果。
解决思路如下:
- 查看detect.py文件
detect.py文件中包含了对视频检测的主要逻辑。其中有段代码如下:
python
for path, img, im0s, vid_cap in dataset:
... # 进行检测
这段在循环数据集,进行连续视频帧的检测。我们需要在这里实现跳帧逻辑。
- 在循环内部加跳帧判断
可以在循环内部添加一个计数变量,每检测完一帧加1。然后添加判断,当计数变量能被10整除时,表示已经检测完10帧,这一帧需要检测,否则跳过此帧:
python
count = 0
for path, img, im0s, vid_cap in dataset:
if count % 10 == 0: # 每10帧检测一次
... # 进行检测
count += 1
else:
continue # 跳过此帧
- 修改日志打印
由于现在不是每帧都在检测,所以日志中显示的检测进度不再准确。可以修改日志打印语句,使之显示实际检测的帧数:
python
# 原日志打印
print(f'video {vid}: stream {stream_id-1}/{len(datasets)} {count+1}/{nF} {fps:.3f}s')
# 修改后
print(f'video {vid}: stream {stream_id-1}/{len(datasets)} {count+1}~{count+10}/{nF} {fps:.3f}s')
打印`{count+1}~{count+10}/{nF}`表示检测了第count+1帧到count+10帧。
- 检查并修改其他依赖的变量
有的变量如last_percent等依赖于检测的帧数,也需要做相应修改,使之依赖实际检测的帧数。
实现Yolov5视频跳帧检测的完整代码及注释:
python
import cv2
from detect import detect
# 视频文件路径
source = 'test.mp4'
# 是否显示视频
show = False
# 跳帧间隔,每10帧检测一次
stride = 10
# 通过Opencv读取视频
vid = cv2.VideoCapture(source)
# 获取视频总帧数
n_frames = int(vid.get(cv2.CAP_PROP_FRAME_COUNT))
# 检测输出目录
det_dir = 'det/'
# 检测帧率
frame_rate = 0
for f in range(n_frames):
# 读取一帧
ret, frame = vid.read()
if ret:
# 每隔stride帧进行检测
if (f % stride == 0):
# 计时
start = time.time()
# 进行检测
detections = detect.run(source, det_dir, show)
# 更新检测帧率
frame_rate = time.time() - start
# 显示视频帧
if show:
cv2.imshow('video', frame)
if cv2.waitKey(1) == ord('q'):
break
else:
break
# 打印检测帧率
print(f'Frame rate: {frame_rate} fps')
# 释放资源
vid.release()
cv2.destroyAllWindows()
注释说明:
- 读取视频文件并获取总帧数
- 每隔stride帧调用detect()进行检测
- 进行检测时,计算并更新检测帧率
- 循环读取视频,直到结束
- 视频结束后,打印检测帧率
- 释放Opencv资源
这段代码实现了Yolov5在视频上进行跳帧检测并计算检测帧率的效果。通过调整stride可以实现不同的跳帧频率,满足实际需求。