def display(self,
pprint=False,
show=False,
save=False,
crop=False,
render=False,
save_dir=Path('')):
crops = []
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
if pred.shape[0]:
for c in pred[:, -1].unique():
n = (pred[:, -1] == c).sum() # detections per class
s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
if show or save or render or crop:
annotator = Annotator(im, example=str(self.names))
for *box, conf, cls in reversed(
pred): # xyxy, confidence, class
label = f'{self.names[int(cls)]} {conf:.2f}'
if crop:
file = save_dir / 'crops' / self.names[int(
cls)] / self.files[i] if save else None
crops.append({
'box':
box,
'conf':
conf,
'cls':
cls,
'label':
label,
'im':
save_one_box(box, im, file=file, save=save)
})
else: # all others
annotator.box_label(box, label, color=colors(cls))
im = annotator.im
else:
s += '(no detections)'
im = Image.fromarray(im.astype(np.uint8)) if isinstance(
im, np.ndarray) else im # from np
if pprint:
LOGGER.info(s.rstrip(', '))
if show:
im.show(self.files[i]) # show
if save:
f = self.files[i]
im.save(save_dir / f) # save
if i == self.n - 1:
LOGGER.info(
f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}"
)
if render:
self.imgs[i] = np.asarray(im)
if crop:
if save:
LOGGER.info(f'Saved results to {save_dir}\n')
return crops
def run(
weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
data=ROOT / 'data/coco128.yaml', # dataset.yaml path
imgsz=(640, 640), # inference size (height, width)
conf_thres=0.25, # confidence threshold
iou_thres=0.45, # NMS IOU threshold
max_det=1000, # maximum detections per image
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
view_img=False, # show results
save_txt=False, # save results to *.txt
save_conf=False, # save confidences in --save-txt labels
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos
classes=None, # filter by class: --class 0, or --class 0 2 3
agnostic_nms=False, # class-agnostic NMS
augment=False, # augmented inference
visualize=False, # visualize features
update=False, # update all models
project=ROOT / 'runs/detect', # save results to project/name
name='exp', # save results to project/name
exist_ok=False, # existing project/name ok, do not increment
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
dnn=False, # use OpenCV DNN for ONNX inference
):
source = str(source)
save_img = not nosave and not source.endswith(
'.txt') # save inference images
is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
is_url = source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
webcam = source.isnumeric() or source.endswith('.txt') or (is_url
and not is_file)
if is_url and is_file:
source = check_file(source) # download
# Directories
save_dir = increment_path(Path(project) / name,
exist_ok=exist_ok) # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(
parents=True, exist_ok=True) # make dir
# Load model
device = select_device(device)
model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data)
stride, names, pt, jit, onnx, engine = model.stride, model.names, model.pt, model.jit, model.onnx, model.engine
imgsz = check_img_size(imgsz, s=stride) # check image size
# Half
half &= (
pt or jit or onnx or engine
) and device.type != 'cpu' # FP16 supported on limited backends with CUDA
if pt or jit:
model.model.half() if half else model.model.float()
# Dataloader
if webcam:
view_img = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Run inference
model.warmup(imgsz=(1 if pt else bs, 3, *imgsz), half=half) # warmup
dt, seen = [0.0, 0.0, 0.0], 0
for path, im, im0s, vid_cap, s in dataset:
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half else im.float() # uint8 to fp16/32
im /= 255 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
im = im[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path).stem,
mkdir=True) if visualize else False
pred = model(im, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
pred = non_max_suppression(pred,
conf_thres,
iou_thres,
classes,
agnostic_nms,
max_det=max_det)
dt[2] += time_sync() - t3
# Second-stage classifier (optional)
# pred = utils.general.apply_classifier(pred, classifier_model, im, im0s)
# Process predictions
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
p, im0, frame = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # im.jpg
txt_path = str(save_dir / 'labels' / p.stem) + (
'' if dataset.mode == 'image' else f'_{frame}') # im.txt
s += '%gx%g ' % im.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1,
0]] # normalization gain whwh
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0,
line_width=line_thickness,
example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.shape[2:], det[:, :4],
im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
# Write results
for *xyxy, conf, cls in reversed(det):
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) /
gn).view(-1).tolist() # normalized xywh
line = (cls, *xywh,
conf) if save_conf else (cls,
*xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line)).rstrip() % line + '\n')
if save_img or save_crop or view_img: # Add bbox to image
c = int(cls) # integer class
label = None if hide_labels else (
names[c]
if hide_conf else f'{names[c]} {conf:.2f}')
annotator.box_label(xyxy, label, color=colors(c, True))
if save_crop:
save_one_box(xyxy,
imc,
file=save_dir / 'crops' / names[c] /
f'{p.stem}.jpg',
BGR=True)
# Stream results
im0 = annotator.result()
if view_img:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_img:
if dataset.mode == 'image':
cv2.imwrite(save_path, im0)
else: # 'video' or 'stream'
if vid_path[i] != save_path: # new video
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].release(
) # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = str(Path(save_path).with_suffix(
'.mp4')) # force *.mp4 suffix on results videos
vid_writer[i] = cv2.VideoWriter(
save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps,
(w, h))
vid_writer[i].write(im0)
# Print time (inference-only)
LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(
f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}'
% t)
if save_txt or save_img:
s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
def rtsp_to_mongodb():
with open("/home/asyed/airflow/dags/parameters.json") as f:
parms = json.load(f)
agnostic_nms = parms["agnostic_nms"]
augment = parms["augment"]
classes = parms["classes"]
conf_thres = parms["conf_thres"]
config_deepsort = parms["config_deepsort"]
deep_sort_model = parms["deep_sort_model"]
device = parms["device"]
dnn = False
evaluate = parms["evaluate"]
exist_ok = parms["exist_ok"]
fourcc = parms["fourcc"]
half = False
print(device)
imgsz = parms["imgsz"]
iou_thres = parms["iou_thres"]
max_det = parms["max_det"]
name = parms["name"]
# save_vid = parms["save_vid"]
#show_vid = parms["show_vid"]
source = parms["source"]
visualize = parms["visualize"]
yolo_model = parms["yolo_model"]
webcam = parms["webcam"]
save_txt = parms["save_txt"]
homography = np.array(parms["homography"])
url = "mongodb://localhost:27017"
client = MongoClient(url)
db = client.trajectory_database
today_date = date.today().strftime("%m-%d-%y")
new = "file_image_coordinates_" + today_date
collection = db[new]
cfg = get_config()
cfg.merge_from_file(config_deepsort)
deepsort = DeepSort(deep_sort_model,
max_dist=cfg.DEEPSORT.MAX_DIST,
max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
max_age=cfg.DEEPSORT.MAX_AGE,
n_init=cfg.DEEPSORT.N_INIT,
nn_budget=cfg.DEEPSORT.NN_BUDGET,
use_cuda=True)
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# The MOT16 evaluation runs multiple inference streams in parallel, each one writing to
# its own .txt file. Hence, in that case, the output folder is not restored
# make new output folder
# Load model
device = select_device(device)
model = DetectMultiBackend(yolo_model, device=device, dnn=dnn)
stride, names, pt, jit, _ = model.stride, model.names, model.pt, model.jit, model.onnx
imgsz = check_img_size(imgsz, s=stride) # check image size
# Half
half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
if pt:
model.model.half() if half else model.model.float()
# Set Dataloader
vid_path, vid_writer = None, None
# Check if environment supports image displays
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source,
img_size=imgsz,
stride=stride,
auto=pt and not jit)
bs = len(dataset) # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
if pt and device.type != 'cpu':
model(
torch.zeros(1, 3, *imgsz).to(device).type_as(
next(model.model.parameters()))) # warmup
# global framess_im2
dt, seen = [0.0, 0.0, 0.0, 0.0], 0
# arr = None
past = []
for frame_idx, (path, img, im0s, vid_cap, s) in enumerate(dataset):
t1 = time_sync()
img = torch.from_numpy(img).to(device)
# print("raw_frame",img.shape)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
t2 = time_sync()
dt[0] += t2 - t1
pred = model(img, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
pred = non_max_suppression(pred,
conf_thres,
iou_thres,
classes,
agnostic_nms,
max_det=max_det)
dt[2] += time_sync() - t3
# Process detections
# dets_per_img = []
for i, det in enumerate(pred): # detections per image
seen += 1
if webcam: # batch_size >= 1
p, im0, _ = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, _ = path, im0s.copy(), getattr(dataset, 'frame', 0)
annotator = Annotator(im0, line_width=2, pil=not ascii)
if det is not None and len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4],
im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
xywhs = xyxy2xywh(det[:, 0:4])
confs = det[:, 4]
clss = det[:, 5]
# pass detections to deepsort
t4 = time_sync()
outputs = deepsort.update(xywhs.cpu(), confs.cpu(),
clss.cpu(), im0)
t5 = time_sync()
dt[3] += t5 - t4
if len(outputs) > 0:
for j, (output, conf) in enumerate(zip(outputs,
confs)):
bboxes = output[0:4]
id = output[4]
cls = output[5]
c = int(cls) # integer class
label = f'{id} {names[c]} {conf:.2f}'
annotator.box_label(bboxes,
label,
color=colors(c, True))
if save_txt:
# to MOT format
bbox_left = output[0]
bbox_top = output[1]
bbox_w = output[2] - output[0]
bbox_h = output[3] - output[1]
# bbox_left = bbox_left + bbox_h
bbox_top = bbox_top + bbox_h
agent_data = {
'frame': int(frame_idx + 1),
'agent_id': int(id),
"labels": str(names[c]),
"x": int(bbox_left),
"y": int(bbox_top)
}
print("agent", agent_data)
collection.insert_one(agent_data)
#db.object_detection.insert_one(agent_data)
#db.pedestrian_detection_15_june.insert_one(agent_data)
#db.test_21_july.insert_one(agent_data)
LOGGER.info(
f'{s}Done. YOLO:({t3 - t2:.3f}s), DeepSort:({t5 - t4:.3f}s)'
)
else:
deepsort.increment_ages()
LOGGER.info('No detections')
im0 = annotator.result()
def detect(opt):
memory = {}
counter = 0
out, source, yolo_model, deep_sort_model, show_vid, save_vid, save_txt, imgsz, evaluate, half, project, name, exist_ok= \
opt.output, opt.source, opt.yolo_model, opt.deep_sort_model, opt.show_vid, opt.save_vid, \
opt.save_txt, opt.imgsz, opt.evaluate, opt.half, opt.project, opt.name, opt.exist_ok
webcam = source == '0' or source.startswith('rtsp') or source.startswith(
'http') or source.endswith('.txt')
# initialize deepsort
cfg = get_config()
cfg.merge_from_file(opt.config_deepsort)
deepsort = DeepSort(deep_sort_model,
torch.device("cpu"),
max_dist=cfg.DEEPSORT.MAX_DIST,
max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
max_age=cfg.DEEPSORT.MAX_AGE,
n_init=cfg.DEEPSORT.N_INIT,
nn_budget=cfg.DEEPSORT.NN_BUDGET)
# Initialize
device = select_device(opt.device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# The MOT16 evaluation runs multiple inference streams in parallel, each one writing to
# its own .txt file. Hence, in that case, the output folder is not restored
if not evaluate:
if os.path.exists(out):
pass
shutil.rmtree(out) # delete output folder
os.makedirs(out) # make new output folder
# Directories
save_dir = increment_path(Path(project) / name,
exist_ok=exist_ok) # increment run
save_dir.mkdir(parents=True, exist_ok=True) # make dir
# Load model
device = select_device(device)
model = DetectMultiBackend(yolo_model, device=device, dnn=opt.dnn)
stride, names, pt, jit, _ = model.stride, model.names, model.pt, model.jit, model.onnx
imgsz = check_img_size(imgsz, s=stride) # check image size
# Half
half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
if pt:
model.model.half() if half else model.model.float()
# Set Dataloader
vid_path, vid_writer = None, None
# Check if environment supports image displays
if show_vid:
show_vid = check_imshow()
# Dataloader
if webcam:
show_vid = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source,
img_size=imgsz,
stride=stride,
auto=pt and not jit)
bs = len(dataset) # batch_size
else:
dataset = LoadImages(source,
img_size=imgsz,
stride=stride,
auto=pt and not jit)
bs = 1 # batch_size
vid_path, vid_writer = [None] * bs, [None] * bs
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
# extract what is in between the last '/' and last '.'
txt_file_name = source.split('/')[-1].split('.')[0]
txt_path = str(Path(save_dir)) + '/' + txt_file_name + '.txt'
if pt and device.type != 'cpu':
model(
torch.zeros(1, 3, *imgsz).to(device).type_as(
next(model.model.parameters()))) # warmup
dt, seen = [0.0, 0.0, 0.0, 0.0], 0
regionid = set()
for frame_idx, (path, img, im0s, vid_cap, s) in enumerate(dataset):
t1 = time_sync()
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path).stem,
mkdir=True) if opt.visualize else False
pred = model(img, augment=opt.augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# Apply NMS
pred = non_max_suppression(pred,
opt.conf_thres,
opt.iou_thres,
opt.classes,
opt.agnostic_nms,
max_det=opt.max_det)
dt[2] += time_sync() - t3
# Process detections
for i, det in enumerate(pred): # detections per image
seen += 1
if webcam: # batch_size >= 1
p, im0, _ = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, _ = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # im.jpg, vid.mp4, ...
s += '%gx%g ' % img.shape[2:] # print string
annotator = Annotator(im0,
line_width=2,
font='Arial.ttf',
pil=not ascii)
if det is not None and len(det):
tboxes = []
indexIDs = []
previous = memory.copy()
memory = {}
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4],
im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
xywhs = xyxy2xywh(det[:, 0:4])
confs = det[:, 4]
clss = det[:, 5]
# pass detections to deepsort
t4 = time_sync()
outputs = deepsort.update(xywhs.cpu(), confs.cpu(), clss.cpu(),
im0)
t5 = time_sync()
dt[3] += t5 - t4
# draw boxes for visualization
if len(outputs) > 0:
for j, (output, conf) in enumerate(zip(outputs, confs)):
bboxes = output[0:4]
id = output[4]
cls = output[5]
roi = [(0, 0), (640, 0), (640, 380), (0, 380)]
(x, y) = (int(bboxes[0]), int(bboxes[1]))
(w, h) = (int(bboxes[2]), int(bboxes[3]))
inside = cv2.pointPolygonTest(np.array(roi), (x, h),
False)
if inside > 0:
regionid.add(id)
c = int(cls) # integer class
label = f' {names[c]} {conf:.2f}'
cv2.putText(im0, "count =" + str(len(regionid)),
(20, 50), 0, 1, (100, 200, 0), 2)
annotator.box_label(bboxes,
label,
color=colors(c, True))
if save_txt:
# to MOT format
bbox_left = output[0]
bbox_top = output[1]
bbox_w = output[2] - output[0]
bbox_h = output[3] - output[1]
# Write MOT compliant results to file
with open(txt_path, 'a') as f:
f.write(('%g ' * 10 + '\n') % (
frame_idx + 1,
id,
bbox_left, # MOT format
bbox_top,
bbox_w,
bbox_h,
-1,
-1,
-1,
-1))
LOGGER.info(
f'{s}Done. YOLO:({t3 - t2:.3f}s), DeepSort:({t5 - t4:.3f}s)'
)
LOGGER.info(f'counter = {len(regionid)}')
else:
deepsort.increment_ages()
LOGGER.info('No detections')
# Stream results
im0 = annotator.result()
if show_vid:
cv2.imshow(str(p), im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
# Save results (image with detections)
if save_vid:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release() # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
vid_writer = cv2.VideoWriter(
save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps,
(w, h))
vid_writer.write(im0)
# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(
f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS, %.1fms deep sort update \
per image at shape {(1, 3, *imgsz)}' % t)
if save_txt or save_vid:
print('Results saved to %s' % save_path)
if platform == 'darwin': # MacOS
os.system('open ' + save_path)
def detect(opt):
out, source, yolo_model, deep_sort_model, show_vid, save_vid, save_txt, imgsz, evaluate, half, \
project, exist_ok, update, save_crop = \
opt.output, opt.source, opt.yolo_model, opt.deep_sort_model, opt.show_vid, opt.save_vid, \
opt.save_txt, opt.imgsz, opt.evaluate, opt.half, opt.project, opt.exist_ok, opt.update, opt.save_crop
webcam = source == '0' or source.startswith(
'rtsp') or source.startswith('http') or source.endswith('.txt')
# Initialize
device = select_device(opt.device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# The MOT16 evaluation runs multiple inference streams in parallel, each one writing to
# its own .txt file. Hence, in that case, the output folder is not restored
if not evaluate:
if os.path.exists(out):
pass
shutil.rmtree(out) # delete output folder
os.makedirs(out) # make new output folder
# Directories
if type(yolo_model) is str: # single yolo model
exp_name = yolo_model.split(".")[0]
elif type(yolo_model) is list and len(yolo_model) == 1: # single models after --yolo_model
exp_name = yolo_model[0].split(".")[0]
else: # multiple models after --yolo_model
exp_name = "ensemble"
exp_name = exp_name + "_" + deep_sort_model.split('/')[-1].split('.')[0]
save_dir = increment_path(Path(project) / exp_name, exist_ok=exist_ok) # increment run if project name exists
(save_dir / 'tracks' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir
# Load model
model = DetectMultiBackend(yolo_model, device=device, dnn=opt.dnn)
stride, names, pt = model.stride, model.names, model.pt
imgsz = check_img_size(imgsz, s=stride) # check image size
# Half
half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
if pt:
model.model.half() if half else model.model.float()
# Set Dataloader
vid_path, vid_writer = None, None
# Check if environment supports image displays
if show_vid:
show_vid = check_imshow()
# Dataloader
if webcam:
show_vid = check_imshow()
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt)
nr_sources = len(dataset)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt)
nr_sources = 1
vid_path, vid_writer, txt_path = [None] * nr_sources, [None] * nr_sources, [None] * nr_sources
# initialize deepsort
cfg = get_config()
cfg.merge_from_file(opt.config_deepsort)
# Create as many trackers as there are video sources
deepsort_list = []
for i in range(nr_sources):
deepsort_list.append(
DeepSort(
deep_sort_model,
device,
max_dist=cfg.DEEPSORT.MAX_DIST,
max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET,
)
)
outputs = [None] * nr_sources
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
# Run tracking
model.warmup(imgsz=(1 if pt else nr_sources, 3, *imgsz)) # warmup
dt, seen = [0.0, 0.0, 0.0, 0.0], 0
for frame_idx, (path, im, im0s, vid_cap, s) in enumerate(dataset):
t1 = time_sync()
im = torch.from_numpy(im).to(device)
im = im.half() if half else im.float() # uint8 to fp16/32
im /= 255.0 # 0 - 255 to 0.0 - 1.0
if len(im.shape) == 3:
im = im[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
visualize = increment_path(save_dir / Path(path[0]).stem, mkdir=True) if opt.visualize else False
pred = model(im, augment=opt.augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
# Apply NMS
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms, max_det=opt.max_det)
dt[2] += time_sync() - t3
# Process detections
for i, det in enumerate(pred): # detections per image
seen += 1
if webcam: # nr_sources >= 1
p, im0, _ = path[i], im0s[i].copy(), dataset.count
p = Path(p) # to Path
s += f'{i}: '
txt_file_name = p.name
save_path = str(save_dir / p.name) # im.jpg, vid.mp4, ...
else:
p, im0, _ = path, im0s.copy(), getattr(dataset, 'frame', 0)
p = Path(p) # to Path
# video file
if source.endswith(VID_FORMATS):
txt_file_name = p.stem
save_path = str(save_dir / p.name) # im.jpg, vid.mp4, ...
# folder with imgs
else:
txt_file_name = p.parent.name # get folder name containing current img
save_path = str(save_dir / p.parent.name) # im.jpg, vid.mp4, ...
txt_path = str(save_dir / 'tracks' / txt_file_name) # im.txt
s += '%gx%g ' % im.shape[2:] # print string
imc = im0.copy() if save_crop else im0 # for save_crop
annotator = Annotator(im0, line_width=2, pil=not ascii)
if det is not None and len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
xywhs = xyxy2xywh(det[:, 0:4])
confs = det[:, 4]
clss = det[:, 5]
# pass detections to deepsort
t4 = time_sync()
outputs[i] = deepsort_list[i].update(xywhs.cpu(), confs.cpu(), clss.cpu(), im0)
t5 = time_sync()
dt[3] += t5 - t4
# draw boxes for visualization
if len(outputs[i]) > 0:
for j, (output, conf) in enumerate(zip(outputs[i], confs)):
bboxes = output[0:4]
id = output[4]
cls = output[5]
if save_txt:
# to MOT format
bbox_left = output[0]
bbox_top = output[1]
bbox_w = output[2] - output[0]
bbox_h = output[3] - output[1]
# Write MOT compliant results to file
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * 10 + '\n') % (frame_idx + 1, id, bbox_left, # MOT format
bbox_top, bbox_w, bbox_h, -1, -1, -1, i))
if save_vid or save_crop or show_vid: # Add bbox to image
c = int(cls) # integer class
label = f'{id} {names[c]} {conf:.2f}'
annotator.box_label(bboxes, label, color=colors(c, True))
if save_crop:
txt_file_name = txt_file_name if (isinstance(path, list) and len(path) > 1) else ''
save_one_box(bboxes, imc, file=save_dir / 'crops' / txt_file_name / names[c] / f'{id}' / f'{p.stem}.jpg', BGR=True)
LOGGER.info(f'{s}Done. YOLO:({t3 - t2:.3f}s), DeepSort:({t5 - t4:.3f}s)')
else:
deepsort_list[i].increment_ages()
LOGGER.info('No detections')
# Stream results
im0 = annotator.result()
if show_vid:
cv2.imshow(str(p), im0)
cv2.waitKey(1) # 1 millisecond
# Save results (image with detections)
if save_vid:
if vid_path[i] != save_path: # new video
vid_path[i] = save_path
if isinstance(vid_writer[i], cv2.VideoWriter):
vid_writer[i].release() # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos
vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer[i].write(im0)
# Print results
t = tuple(x / seen * 1E3 for x in dt) # speeds per image
LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS, %.1fms deep sort update \
per image at shape {(1, 3, *imgsz)}' % t)
if save_txt or save_vid:
s = f"\n{len(list(save_dir.glob('tracks/*.txt')))} tracks saved to {save_dir / 'tracks'}" if save_txt else ''
LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(yolo_model) # update model (to fix SourceChangeWarning)
def detect(opt):
out, source, yolo_weights, deep_sort_weights, show_vid, save_vid, save_txt, imgsz, evaluate = \
opt.output, opt.source, opt.yolo_weights, opt.deep_sort_weights, opt.show_vid, opt.save_vid, \
opt.save_txt, opt.img_size, opt.evaluate
webcam = source == '0' or source.startswith(
'rtsp') or source.startswith('http') or source.endswith('.txt')
# initialize deepsort
cfg = get_config()
cfg.merge_from_file(opt.config_deepsort)
attempt_download(deep_sort_weights, repo='mikel-brostrom/Yolov5_DeepSort_Pytorch')
deepsort = DeepSort(cfg.DEEPSORT.REID_CKPT,
max_dist=cfg.DEEPSORT.MAX_DIST, min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
max_age=cfg.DEEPSORT.MAX_AGE, n_init=cfg.DEEPSORT.N_INIT, nn_budget=cfg.DEEPSORT.NN_BUDGET,
use_cuda=True)
# Initialize
device = select_device(opt.device)
# The MOT16 evaluation runs multiple inference streams in parallel, each one writing to
# its own .txt file. Hence, in that case, the output folder is not restored
if not evaluate:
if os.path.exists(out):
pass
shutil.rmtree(out) # delete output folder
os.makedirs(out) # make new output folder
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = attempt_load(yolo_weights, map_location=device) # load FP32 model
stride = int(model.stride.max()) # model stride
imgsz = check_img_size(imgsz, s=stride) # check img_size
names = model.module.names if hasattr(model, 'module') else model.names # get class names
if half:
model.half() # to FP16
# Set Dataloader
vid_path, vid_writer = None, None
# Check if environment supports image displays
if show_vid:
show_vid = check_imshow()
if webcam:
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz, stride=stride)
else:
dataset = LoadImages(source, img_size=imgsz, stride=stride)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
# Run inference
if device.type != 'cpu':
model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) # run once
t0 = time.time()
save_path = str(Path(out))
# extract what is in between the last '/' and last '.'
txt_file_name = source.split('/')[-1].split('.')[0]
txt_path = str(Path(out)) + '/' + txt_file_name + '.txt'
for frame_idx, (path, img, im0s, vid_cap) in enumerate(dataset):
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
# Inference
t1 = time_sync()
pred = model(img, augment=opt.augment)[0]
# Apply NMS
pred = non_max_suppression(
pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
t2 = time_sync()
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
else:
p, s, im0 = path, '', im0s
s += '%gx%g ' % img.shape[2:] # print string
save_path = str(Path(out) / Path(p).name)
annotator = Annotator(im0, line_width=2, pil=not ascii)
if det is not None and len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(
img.shape[2:], det[:, :4], im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
xywhs = xyxy2xywh(det[:, 0:4])
confs = det[:, 4]
clss = det[:, 5]
# pass detections to deepsort
outputs = deepsort.update(xywhs.cpu(), confs.cpu(), clss.cpu(), im0)
# draw boxes for visualization
if len(outputs) > 0:
for j, (output, conf) in enumerate(zip(outputs, confs)):
bboxes = output[0:4]
id = output[4]
cls = output[5]
c = int(cls) # integer class
label = f'{id} {names[c]} {conf:.2f}'
annotator.box_label(bboxes, label, color=colors(c, True))
if save_txt:
# to MOT format
bbox_left = output[0]
bbox_top = output[1]
bbox_w = output[2] - output[0]
bbox_h = output[3] - output[1]
# Write MOT compliant results to file
with open(txt_path, 'a') as f:
f.write(('%g ' * 10 + '\n') % (frame_idx, id, bbox_left,
bbox_top, bbox_w, bbox_h, -1, -1, -1, -1)) # label format
else:
deepsort.increment_ages()
# Print time (inference + NMS)
print('%sDone. (%.3fs)' % (s, t2 - t1))
# Stream results
im0 = annotator.result()
if show_vid:
cv2.imshow(p, im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
# Save results (image with detections)
if save_vid:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release() # release previous video writer
if vid_cap: # video
fps = vid_cap.get(cv2.CAP_PROP_FPS)
w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
else: # stream
fps, w, h = 30, im0.shape[1], im0.shape[0]
save_path += '.mp4'
vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
vid_writer.write(im0)
if save_txt or save_vid:
print('Results saved to %s' % os.getcwd() + os.sep + out)
if platform == 'darwin': # MacOS
os.system('open ' + save_path)
print('Done. (%.3fs)' % (time.time() - t0))
def my_gen():
# global framess_im2
dt, seen = [0.0, 0.0, 0.0, 0.0], 0
# arr = None
for frame_idx, (path, img, im0s, vid_cap, s) in enumerate(dataset):
t1 = time_sync()
img = torch.from_numpy(img).to(device)
# print("raw_frame",img.shape)
img = img.half() if half else img.float() # uint8 to fp16/32
img /= 255.0 # 0 - 255 to 0.0 - 1.0
if img.ndimension() == 3:
img = img.unsqueeze(0)
t2 = time_sync()
dt[0] += t2 - t1
pred = model(img, augment=augment, visualize=visualize)
t3 = time_sync()
dt[1] += t3 - t2
pred = non_max_suppression(pred,
conf_thres,
iou_thres,
classes,
agnostic_nms,
max_det=max_det)
dt[2] += time_sync() - t3
# Process detections
# dets_per_img = []
for i, det in enumerate(pred): # detections per image
seen += 1
if webcam: # batch_size >= 1
p, im0, _ = path[i], im0s[i].copy(), dataset.count
s += f'{i}: '
else:
p, im0, _ = path, im0s.copy(), getattr(dataset, 'frame', 0)
annotator = Annotator(im0, line_width=2, pil=not ascii)
if det is not None and len(det):
# Rescale boxes from img_size to im0 size
det[:, :4] = scale_coords(img.shape[2:], det[:, :4],
im0.shape).round()
# Print results
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
xywhs = xyxy2xywh(det[:, 0:4])
confs = det[:, 4]
clss = det[:, 5]
# pass detections to deepsort
t4 = time_sync()
outputs = deepsort.update(xywhs.cpu(), confs.cpu(), clss.cpu(),
im0)
t5 = time_sync()
dt[3] += t5 - t4
dets_per_img = []
if len(outputs) > 0:
for j, (output, conf) in enumerate(zip(outputs, confs)):
bboxes = output[0:4]
id = output[4]
cls = output[5]
c = int(cls) # integer class
label = f'{id} {names[c]} {conf:.2f}'
annotator.box_label(bboxes,
label,
color=colors(c, True))
if save_txt:
# to MOT format
bbox_left = output[0]
bbox_top = output[1]
bbox_w = output[2] - output[0]
bbox_h = output[3] - output[1]
# bbox_left = bbox_left + bbox_h
bbox_top = bbox_top + bbox_h
pts = np.array([[bbox_left, bbox_top, 1]])
arr_per = convert_bev(pts)
# print("arr_per_to", arr_per)
arr_per = np.append(id, arr_per)
# print("arr_per1_to", arr_per1)
dets_per_img.append(arr_per)
LOGGER.info(
f'{s}Done. YOLO:({t3 - t2:.3f}s), DeepSort:({t5 - t4:.3f}s)'
)
else:
deepsort.increment_ages()
arr_per = None
dets_per_img = [None, None]
LOGGER.info('No detections')
im0 = annotator.result()
if len(dets_per_img) > 1:
arr_per = np.stack(dets_per_img).tolist()
elif len(dets_per_img) == 1:
arr_per = np.array([dets_per_img[0]])
# print("not_stack",arr_per)
elif dets_per_img is None:
arr_per = None
if save_vid:
fps, w, h = 30, im0.shape[1], im0.shape[0]
cv2.putText(im0, str(frame_idx), (500, 460),
cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 255), 2,
cv2.LINE_AA)
framess = cv2.imencode(
'.jpg',
im0)[1].tobytes() # Remove this line for test camera
if arr_per is None:
yield framess
else:
yield framess, arr_per