def mainFunc(args):
# Set the main function flag
print("Main Function Start...")
# Check the GPU device
print("Number of available GPUs: {}".format(torch.cuda.device_count()))
# Check whether using the distributed runing for the network
is_distributed = initDistributed(args)
master = True
if is_distributed and os.environ["RANK"]:
master = int(
os.environ["RANK"]) == 0 # check whether this node is master node
# Configuration for device setting
set_logging()
if is_distributed:
device = torch.device('cuda:{}'.format(args.local_rank))
else:
device = select_device(args.device)
half = device.type != 'cpu' # half precision only supported on CUDA
# Load the configuration
config = loadConfig(args.config)
# CuDNN related setting
if torch.cuda.is_available():
cudnn.benchmark = config.DEVICE.CUDNN.BENCHMARK
cudnn.deterministic = config.DEVICE.CUDNN.DETERMINISTIC
cudnn.enabled = config.DEVICE.CUDNN.ENABLED
# Configurations for dirctories
save_img, save_dir, source, yolov5_weights, view_img, save_txt, imgsz = \
False, Path(args.save_dir), args.source, args.weights, args.view_img, args.save_txt, args.img_size
webcam = source.isnumeric() or source.startswith(
('rtsp://', 'rtmp://', 'http://')) or source.endswith('.txt')
if save_dir == Path('runs/detect'): # if default
os.makedirs('runs/detect', exist_ok=True) # make base
save_dir = Path(increment_dir(save_dir / 'exp',
args.name)) # increment run
os.makedirs(save_dir / 'labels' if save_txt else save_dir,
exist_ok=True) # make new dir
# Load yolov5 model for human detection
model_yolov5 = attempt_load(config.MODEL.PRETRAINED.YOLOV5,
map_location=device)
imgsz = check_img_size(imgsz,
s=model_yolov5.stride.max()) # check img_size
if half:
model_yolov5.half() # to FP16
# Second-stage classifier
classify = False
if classify:
model_classifier = load_classifier(name='resnet101', n=2) # initialize
model_classifier.load_state_dict(
torch.load('weights/resnet101.pt',
map_location=device)['model']) # load weights
model_classifier.to(device).eval()
# Load resnet model for human keypoints estimation
model_resnet = eval('pose_models.' + config.MODEL.NAME.RESNET +
'.get_pose_net')(config, is_train=False)
if config.EVAL.RESNET.MODEL_FILE:
print('=> loading model from {}'.format(config.EVAL.RESNET.MODEL_FILE))
model_resnet.load_state_dict(torch.load(config.EVAL.RESNET.MODEL_FILE),
strict=False)
else:
print('expected model defined in config at EVAL.RESNET.MODEL_FILE')
model_resnet.to(device)
model_resnet.eval()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = True
dataset = LoadStreams(source, img_size=imgsz)
else:
save_img = True
dataset = LoadImages(source, img_size=imgsz)
pose_transform = transforms.Compose(
[ # input transformation for 2d human pose estimation
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
# Get names and colors
names = model_yolov5.module.names if hasattr(
model_yolov5, 'module') else model_yolov5.names
colors = [[random.randint(0, 255) for _ in range(3)]
for _ in range(len(names))]
# Construt filters for filtering 2D/3D human keypoints
# filters_2d = constructFilters((1,16,2), freq=25, mincutoff=1, beta=0.01) # for test
# filters_3d = constructFilters((1,16,3), freq=25, mincutoff=1, beta=0.01)
# Run the yolov5 and resnet for 2d human pose estimation
# with torch.no_grad():
# Run inference
t0 = time.time()
img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
_ = model_yolov5(img.half() if half else img
) if device.type != 'cpu' else None # run once
# Process every video frame
for path, img, im0s, vid_cap in 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_synchronized()
pred_boxes = model_yolov5(img, augment=args.augment)[0]
# Apply NMS
pred_boxes = non_max_suppression(pred_boxes,
args.conf_thres,
args.iou_thres,
classes=args.classes,
agnostic=args.agnostic_nms)
t2 = time_synchronized()
# Can not find people and move to next frame
if pred_boxes[0] is None:
# show the frame with no human detected
cv2.namedWindow("2D Human Pose Estimation", cv2.WINDOW_NORMAL)
cv2.imshow("2D Human Pose Estimation", im0s[0].copy())
# wait manual operations
# with kb.Listener(on_press=on_press) as listener:
# listener.join()
# return
# if kb.is_pressed('t'):
# return
print("No Human Detected and Move on.")
print("-" * 30)
continue
# Print time (inference + NMS)
detect_time = t2 - t1
detect_fps = 1.0 / detect_time
print("Human Detection Time: {}, Human Detection FPS: {}".format(
detect_time, detect_fps))
# Apply Classifier
if classify: # false
pred_boxes = apply_classifier(pred_boxes, model_classifier, img,
im0s)
# Estimate 2d human pose(multiple person)
centers = []
scales = []
for id, boxes in enumerate(pred_boxes):
if boxes is not None and len(boxes):
boxes[:, :4] = scale_coords(img.shape[2:], boxes[:, :4],
im0s[id].copy().shape).round()
# convert tensor to list format
boxes = np.delete(boxes.cpu().numpy(), [-2, -1], axis=1).tolist()
for l in range(len(boxes)):
boxes[l] = [tuple(boxes[l][0:2]), tuple(boxes[l][2:4])]
# convert box to center and scale
for box in boxes:
center, scale = box_to_center_scale(box, imgsz, imgsz)
centers.append(center)
scales.append(scale)
t3 = time_synchronized()
pred_pose_2d = get_pose_estimation_prediction(config,
model_resnet,
im0s[0],
centers,
scales,
transform=pose_transform,
device=device)
t4 = time_synchronized()
# Print time (2d human pose estimation)
estimate_time = t4 - t3
estimate_fps = 1.0 / estimate_time
print("Pose Estimation Time: {}, Pose Estimation FPS: {}".format(
estimate_time, estimate_fps))
# Filter the predicted 2d human pose(multiple person)
t5 = time_synchronized()
# if False: # for test
if config.EVAL.RESNET.USE_FILTERS_2D:
# construct filters for every keypoints of every person in 2D
filters_2d = constructFilters(pred_pose_2d.shape,
freq=1,
mincutoff=1,
beta=0.01)
print("Shape of filters_2d: ({}, {}, {})".format(
len(filters_2d), len(filters_2d[0]),
len(filters_2d[0][0]))) # for test
for per in range(pred_pose_2d.shape[0]):
for kp in range(pred_pose_2d.shape[1]):
for coord in range(pred_pose_2d.shape[2]):
pred_pose_2d[per][kp][coord] = filters_2d[per][kp][
coord](pred_pose_2d[per][kp][coord])
t6 = time_synchronized()
# Print time (filter 2d human pose)
filter_time_2d = t6 - t5
filter_fps_2d = 1.0 / filter_time_2d
print("Filter 2D Pose Time: {}, Filter 2D Pose FPS: {}".format(
filter_time_2d, filter_fps_2d))
# Process detections and estimations in 2D
for i, box in enumerate(pred_boxes):
if webcam: # batch_size >= 1
p, s, im0 = Path(path[i]), '%g: ' % i, im0s[i].copy()
else:
p, s, im0 = Path(path), '', im0s
save_path = str(save_dir / p.name)
txt_path = str(save_dir / 'labels' / p.stem) + (
'_%g' % dataset.frame if dataset.mode == 'video' else '')
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1,
0]] # normalization gain whwh
if box is not None and len(box):
# Rescale boxes from img_size to im0 size
box[:, :4] = scale_coords(img.shape[2:], box[:, :4],
im0.shape).round()
# Print results
for c in box[:, -1].unique():
n = (box[:, -1] == c).sum() # detections per class
s += '%g %ss, ' % (n, names[int(c)]) # add to string
# Write results
for *xyxy, conf, cls in reversed(box):
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 args.save_conf else (
cls, *xywh) # label format
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * len(line) + '\n') % line)
# Add bbox to image
if save_img or view_img:
label = '%s %.2f' % (names[int(cls)], conf)
plot_one_box(xyxy,
im0,
label=label,
color=colors[int(cls)],
line_thickness=3)
# Draw joint keypoints, number orders and human skeletons for every detected people in 2D
for person in pred_pose_2d:
# draw the human keypoints
for idx, coord in enumerate(person):
x_coord, y_coord = int(coord[0]), int(coord[1])
cv2.circle(im0, (x_coord, y_coord), 1, (0, 0, 255), 5)
cv2.putText(im0, str(idx), (x_coord, y_coord),
cv2.FONT_HERSHEY_SIMPLEX, 0.6,
(255, 255, 255), 2, cv2.LINE_AA)
# draw the human skeletons in PACIFIC mode
for skeleton in PACIFIC_SKELETON_INDEXES:
cv2.line(im0, (int(person[skeleton[0]][0]),
int(person[skeleton[0]][1])),
(int(person[skeleton[1]][0]),
int(person[skeleton[1]][1])), skeleton[2], 2)
# Print time (inference + NMS + estimation)
print('%sDone. (%.3fs)' % (s, t4 - t1))
# Stream results
if view_img:
detect_text = "Detect FPS:{0:0>5.2f}/{1:0>6.2f}ms".format(
detect_fps, detect_time * 1000)
estimate_text = "Estimate FPS:{0:0>5.2f}/{1:0>6.2f}ms".format(
estimate_fps, estimate_time * 1000)
cv2.putText(im0, detect_text, (10, 30),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2,
cv2.LINE_AA)
cv2.putText(im0, estimate_text, (10, 60),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 255), 2,
cv2.LINE_AA)
cv2.namedWindow("2D Human Pose Estimation", cv2.WINDOW_NORMAL)
cv2.imshow("2D Human Pose Estimation", im0)
if cv2.waitKey(1) & 0xFF == ord('q'): # q to quit
return
# goto .mainFunc
# Save results (image with detections)
if save_img:
if dataset.mode == 'images':
cv2.imwrite(save_path, im0)
else:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release(
) # release previous video writer
fourcc = 'mp4v' # output video codec
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))
vid_writer = cv2.VideoWriter(
save_path, cv2.VideoWriter_fourcc(*fourcc), fps,
(w, h))
vid_writer.write(im0)
# Print time (inference + NMS + estimation + 2d filtering)
all_process_time = t6 - t1
all_process_fps = 1.0 / all_process_time
print("All Process Time: {}, All Process FPS: {}".format(
all_process_time, all_process_fps))
print("-" * 30)
# Goto label
# label .mainFunc
# Print saving results
if save_txt or save_img:
print('Results saved to %s' % save_dir)
# Release video reader and writer, then destory all opencv windows
dataset.vid_cap.release()
vid_writer.release()
cv2.destroyAllWindows()
print('Present 2D Human Pose Inference Done. Total Time:(%.3f seconds)' %
(time.time() - t0))
def detect(save_img=False):
out, source, weights, view_img, save_txt, imgsz = \
opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
webcam = source.isnumeric() or source.startswith(
'rtsp') or source.startswith('http') or source.endswith('.txt')
# Initialize
set_logging()
device = select_device(opt.device)
if os.path.exists(out):
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(weights, map_location=device) # load FP32 model
imgsz = check_img_size(imgsz, s=model.stride.max()) # check img_size
if half:
model.half() # to FP16
# Second-stage classifier
classify = False
if classify:
modelc = load_classifier(name='resnet101', n=2) # initialize
modelc.load_state_dict(
torch.load('weights/resnet101.pt',
map_location=device)['model']) # load weights
modelc.to(device).eval()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = True
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz)
else:
save_img = True
dataset = LoadImages(source, img_size=imgsz)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
colors = [[random.randint(0, 255) for _ in range(3)]
for _ in range(len(names))]
# Run inference
t0 = time.time()
img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
_ = model(img.half() if half else img
) if device.type != 'cpu' else None # run once
for path, img, im0s, vid_cap in 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_synchronized()
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_synchronized()
# Apply Classifier
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# 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
save_path = str(Path(out) / Path(p).name)
txt_path = str(Path(out) / Path(p).stem) + (
'_%g' % dataset.frame if dataset.mode == 'video' else '')
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1,
0]] # normalization gain whwh
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 += '%g %ss, ' % (n, names[int(c)]) # 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
with open(txt_path + '.txt', 'a') as f:
f.write(('%g ' * 5 + '\n') %
(cls, *xywh)) # label format
if save_img or view_img: # Add bbox to image
label = '%s %.2f' % (names[int(cls)], conf)
plot_one_box(xyxy,
im0,
label=label,
color=colors[int(cls)],
line_thickness=3)
# Print time (inference + NMS)
print('%sDone. (%.3fs)' % (s, t2 - t1))
# Stream results
if view_img:
# cv2.imshow(p, im0)
cv2.imwrite("C:/Users/lenovo/Desktop/server/output/camera.jpg",
im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIterationq
# Save results (image with detections)
if save_img:
if dataset.mode == 'images':
cv2.imwrite(save_path, im0)
else:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release(
) # release previous video writer
fourcc = 'mp4v' # output video codec
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))
# vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*fourcc), fps, (w, h))
vid_writer = cv2.VideoWriter(
save_path,
cv2.VideoWriter_fourcc('X', '2', '6', '4'), fps,
(w, h))
vid_writer.write(im0)
if save_txt or save_img:
print('Results saved to %s' % Path(out))
if platform.system() == 'Darwin' and not opt.update: # MacOS
os.system('open ' + save_path)
print('Done. (%.3fs)' % (time.time() - t0))
def detect(save_img=False):
out, source, weights, view_img, save_txt, imgsz = \
opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
webcam = source.isnumeric() or source.startswith(
'rtsp') or source.startswith('http') or source.endswith('.txt')
# Initialize
set_logging()
device = select_device(opt.device)
if os.path.exists(out):
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(weights, map_location=device) # load FP32 model
imgsz = check_img_size(imgsz, s=model.stride.max()) # check img_size
if half:
model.half() # to FP16
# Second-stage classifier
classify = False
if classify:
modelc = load_classifier(name='resnet101', n=2) # initialize
modelc.load_state_dict(
torch.load('weights/resnet101.pt',
map_location=device)['model']) # load weights
modelc.to(device).eval()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = True
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz)
else:
save_img = True
dataset = LoadImages(source, img_size=imgsz)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
colors = [[random.randint(0, 255) for _ in range(3)]
for _ in range(len(names))]
# Find index corresponding to a person
idx_person = names.index("person")
# SORT: initialize the tracker
mot_tracker = sort_module.Sort(max_age=opt.max_age,
min_hits=opt.min_hits,
iou_threshold=opt.iou_threshold)
# Run inference
t0 = time.time()
img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
_ = model(img.half() if half else img
) if device.type != 'cpu' else None # run once
for path, img, im0s, vid_cap in 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_synchronized()
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_synchronized()
# Apply Classifier
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# 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
save_path = str(Path(out) / Path(p).name)
txt_path = str(Path(out) / Path(p).stem) + (
'_%g' % dataset.frame if dataset.mode == 'video' else '')
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1,
0]] # normalization gain whwh
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 += '%g %ss, ' % (n, names[int(c)]) # add to string
# SORT: number of people detected
idxs_ppl = (
det[:, -1] == idx_person
).nonzero(as_tuple=False).squeeze(
dim=1) # 1. List of indices with 'person' class detections
dets_ppl = det[idxs_ppl, :-1].to(
"cpu") # 2. Torch.tensor with 'person' detections
print('\n {} people were detected!'.format(len(idxs_ppl)))
# SORT: feed detections to the tracker
if len(dets_ppl) != 0:
trackers = mot_tracker.update(dets_ppl)
for d in trackers:
plot_one_box(d[:-1],
im0,
label='ID' + str(int(d[-1])),
color=colors[1],
line_thickness=1)
# Print time (inference + NMS)
print('%sDone. (%.3fs)' % (s, t2 - t1))
# Stream results
if view_img:
cv2.imshow(p, im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
# Save results (image with detections)
if save_img:
if dataset.mode == 'images':
cv2.imwrite(save_path, im0)
else:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release(
) # release previous video writer
fourcc = 'mp4v' # output video codec
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))
vid_writer = cv2.VideoWriter(
save_path, cv2.VideoWriter_fourcc(*fourcc), fps,
(w, h))
vid_writer.write(im0)
if save_txt or save_img:
print('Results saved to %s' % Path(out))
if platform.system() == 'Darwin' and not opt.update: # MacOS
os.system('open ' + save_path)
print('Done. (%.3fs)' % (time.time() - t0))
def detect(save_img=False):
out, source, weights, view_img, save_txt, imgsz = \
opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
webcam = source.isnumeric() or source.endswith(
'.txt') or source.lower().startswith(
('rtsp://', 'rtmp://',
'http://')) or source.lower().startswith('intel')
# Initialize
set_logging()
device = select_device(opt.device)
folder_main = out.split('/')[0]
if os.path.exists(out):
shutil.rmtree(out) # delete output folder
folder_features = folder_main + '/features'
if os.path.exists(folder_features):
shutil.rmtree(folder_features) # delete features output folder
folder_crops = folder_main + '/image_crops'
if os.path.exists(folder_crops):
shutil.rmtree(folder_crops) # delete output folder with object crops
os.makedirs(out) # make new output folder
os.makedirs(folder_features) # make new output folder
os.makedirs(folder_crops) # make new output folder
half = device.type != 'cpu' # half precision only supported on CUDA
# Load model
model = torch.load(weights[0],
map_location=device)['model'].float() # load to FP32
model.to(device).eval()
imgsz = check_img_size(imgsz, s=model.stride.max()) # check img_size
if half:
model.half() # to FP16
# Second-stage classifier
classify = False
if classify:
modelc = load_classifier(name='resnet101', n=2) # initialize
modelc.load_state_dict(
torch.load('weights/resnet101.pt',
map_location=device)['model']) # load weights
modelc.to(device).eval()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = True
cudnn.benchmark = True # set True to speed up constant image size inference
if source.lower().startswith('intel'):
dataset = LoadRealSense2()
save_img = True
else:
dataset = LoadStreams(source, img_size=imgsz)
else:
save_img = True
dataset = LoadImages(source, img_size=imgsz)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
colors = [[random.randint(0, 255) for _ in range(3)]
for _ in range(len(names))]
# frames per second
# TODO if use intel or if use given footage
fps = 30 # dataset.cap.get(cv2.CAP_PROP_FPS)
critical_time_frames = opt.time * fps
# COUNTER: initialization
counter = VoteCounter(critical_time_frames, fps)
print('CRITICAL TIME IS ', opt.time, 'sec, or ', counter.critical_time,
' frames')
# Find index corresponding to a person
idx_person = names.index("person")
# Deep SORT: initialize the tracker
cfg = get_config()
cfg.merge_from_file(opt.config_deepsort)
deepsort = DeepSort(cfg.DEEPSORT.REID_CKPT,
max_dist=cfg.DEEPSORT.MAX_DIST,
min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP,
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)
# AlphaPose: initialization
# args_p = update_config(opt.config_alphapose)
# cfg_p = update_config(args_p.ALPHAPOSE.cfg)
#
# args_p.ALPHAPOSE.tracking = args_p.ALPHAPOSE.pose_track or args_p.ALPHAPOSE.pose_flow
#
# demo = SingleImageAlphaPose(args_p.ALPHAPOSE, cfg_p, device)
# output_pose = opt.output.split('/')[0] + '/pose'
# if not os.path.exists(output_pose):
# os.mkdir(output_pose)
# Run inference
t0 = time.time()
img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
_ = model(img.half() if half else img
) if device.type != 'cpu' else None # run once
for path, img, im0s, vid_cap in 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_synchronized()
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_synchronized()
# TODO => COUNTER: draw queueing ROI
# compute urn centoid (1st frame only) and plot a bounding box around it
# if dataset.frame == 1:
# counter.read_urn_coordinates(opt.urn, im0s, opt.radius)
# counter.plot_urn_bbox(im0s)
# Apply Classifier
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# Process detections
for i, det in enumerate(pred): # detections per image
if webcam: # batch_size >= 1
if source.lower().startswith('intel'):
p, s, im0, frame = path, '%g: ' % i, im0s[i].copy(
), dataset.count
else:
p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
else:
p, s, im0 = path, '', im0s
save_path = str(Path(out) / Path(p).name)
print(save_path)
txt_path = str(Path(out) / Path(p).stem) + (
'_%g' % dataset.frame if dataset.mode == 'video' else '')
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1,
0]] # normalization gain whwh
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 += '%g %ss, ' % (n, names[int(c)]) # add to string
# Deep SORT: person class only
idxs_ppl = (
det[:, -1] == idx_person
).nonzero(as_tuple=False).squeeze(
dim=1) # 1. List of indices with 'person' class detections
dets_ppl = det[idxs_ppl, :
-1] # 2. Torch.tensor with 'person' detections
print('\n {} people were detected!'.format(len(idxs_ppl)))
# Deep SORT: convert data into a proper format
xywhs = xyxy2xywh(dets_ppl[:, :-1]).to("cpu")
confs = dets_ppl[:, 4].to("cpu")
# Deep SORT: feed detections to the tracker
if len(dets_ppl) != 0:
trackers, features = deepsort.update(xywhs, confs, im0)
# tracks inside a critical sphere
trackers_inside = []
for i, d in enumerate(trackers):
plot_one_box(d[:-1],
im0,
label='ID' + str(int(d[-1])),
color=colors[1],
line_thickness=1)
# TODO: queue COUNTER
# d_include = counter.centroid_distance(d, im0, colors[1], dataset.frame)
# if d_include:
# trackers_inside.append(d)
# ALPHAPOSE: show skeletons for bounding boxes inside the critical sphere
# if len(trackers_inside) > 0:
# pose = demo.process('frame_'+str(dataset.frame), im0, trackers_inside)
# im0 = demo.vis(im0, pose)
# demo.writeJson([pose], output_pose, form=args_p.ALPHAPOSE.format, for_eval=args_p.ALPHAPOSE.eval)
#
# counter.save_features_and_crops(im0, dataset.frame, trackers_inside, features, folder_main)
cv2.putText(im0, 'Voted ' + str(len(counter.voters_count)),
(50, 50), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0, 0, 255),
2)
print('NUM VOTERS', len(counter.voters))
print(list(counter.voters.keys()))
# COUNTER
if len(counter.voters) > 0:
counter.save_voter_trajectory(dataset.frame, folder_main)
# Print time (inference + NMS)
print('%sDone. (%.3fs)' % (s, t2 - t1))
# Stream results
if view_img:
cv2.imshow(p, im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
# Save results (image with detections)
if save_img:
if dataset.mode == 'images':
cv2.imwrite(save_path, im0)
else:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release(
) # release previous video writer
fourcc = 'mp4v' # output video codec
if type(vid_cap
) is dict: # estimate distance_in_meters
# TODO hard code
w, h, fps = 640, 480, 6
else:
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))
vid_writer = cv2.VideoWriter(
save_path, cv2.VideoWriter_fourcc(*fourcc), fps,
(w, h))
vid_writer.write(im0)
if save_txt or save_img:
print('Results saved to %s' % Path(out))
if platform.system() == 'Darwin' and not opt.update: # MacOS
os.system('open ' + save_path)
print('Done. (%.3fs)' % (time.time() - t0))
def detect(opt, save_img=False):
out, source, weights, view_img, save_txt, imgsz = \
opt.output, opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
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(cfg.DEEPSORT.REID_CKPT,
max_dist=cfg.DEEPSORT.MAX_DIST,
min_confidence=cfg.DEEPSORT.MIN_CONFIDENCE,
nms_max_overlap=cfg.DEEPSORT.NMS_MAX_OVERLAP,
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)
if os.path.exists(out):
shutil.rmtree(out) # delete output folder
os.makedirs(out) # make new output folder
half = device.type != 'cpu' # half precision only supported on CUDA
# Read Yaml
with open(opt.data) as f:
data_dict = yaml.load(f, Loader=yaml.FullLoader)
names = data_dict['names']
print(names)
# Load model
#google_utils.attempt_download(weights)
model = torch.load(weights,
map_location=device)['model'].float() # load to FP32
#model = torch.save(torch.load(weights, map_location=device), weights) # update model if SourceChangeWarning
# model.fuse()
model.to(device).eval()
if half:
model.half() # to FP16
# Second-stage classifier
classify = False
if classify:
modelc = torch_utils.load_classifier(name='resnet101',
n=2) # initialize
modelc.load_state_dict(
torch.load('weights/resnet101.pt',
map_location=device)['model']) # load weights
modelc.to(device).eval()
# Set Dataloader
vid_path, vid_writer = None, None
if webcam:
view_img = True
cudnn.benchmark = True # set True to speed up constant image size inference
dataset = LoadStreams(source, img_size=imgsz)
else:
save_img = True
dataset = LoadImages(source, img_size=imgsz)
# Get names and colors
names = model.module.names if hasattr(model, 'module') else model.names
colors = [[random.randint(0, 255) for _ in range(3)]
for _ in range(len(names))]
# Run inference
t_fps = time_synchronized()
frame_fps = 0
img = torch.zeros((1, 3, imgsz, imgsz), device=device) # init img
_ = model(img.half() if half else img
) if device.type != 'cpu' else None # run once
for path, img, im0s, vid_cap in 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_synchronized()
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_synchronized()
# Apply Classifier
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# 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
save_path = str(Path(out) / Path(p).name)
txt_path = str(Path(out) / Path(p).stem) + (
'_%g' % dataset.frame if dataset.mode == 'video' else '')
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1,
0]] # normalization gain whwh
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
#print(det[:, -1].unique())
for c in det[:, -1].unique():
n = (det[:, -1] == c).sum() # detections per class
s += '%g %ss, ' % (n, names[int(c)]) # add to string
bbox_xywh = []
confs = []
#clses = []
# Write results
for *xyxy, conf, cls in det:
img_h, img_w, _ = im0.shape # get image shape
x_c, y_c, bbox_w, bbox_h = bbox_rel(img_w, img_h, *xyxy)
obj = [x_c, y_c, bbox_w, bbox_h]
bbox_xywh.append(obj)
confs.append([conf.item()])
#clses.append([cls.item()])
#outputs, clses2 = deepsort.update((torch.Tensor(bbox_xywh)), (torch.Tensor(confs)), (torch.Tensor(clses)), im0)
#outputs = deepsort.update((torch.Tensor(bbox_xywh)), (torch.Tensor(confs)), im0)
if save_img or view_img: # Add bbox to image
label = '%s %.2f' % (names[int(cls)], conf)
plot_one_box(xyxy,
im0,
label=label,
color=colors[int(cls)],
line_thickness=3)
xywhs = torch.Tensor(bbox_xywh)
confss = torch.Tensor(confs)
# Pass detections to deepsort
outputs = deepsort.update(xywhs, confss, im0)
# draw boxes for visualization
if len(outputs) > 0:
bbox_tlwh = []
bbox_xyxy = outputs[:, :4]
identities = outputs[:, -1]
ori_im = draw_boxes(im0, bbox_xyxy, identities)
# Print time (inference + NMS)
#print('%sDone. (%.3fs)' % (s, t2 - t1))
print('%sDone.' % s)
# Stream results
if view_img:
cv2.imshow(p, im0)
if cv2.waitKey(1) == ord('q'): # q to quit
raise StopIteration
# Save results (image with detections)
if save_img:
if dataset.mode == 'images':
cv2.imwrite(save_path, im0)
else:
if vid_path != save_path: # new video
vid_path = save_path
if isinstance(vid_writer, cv2.VideoWriter):
vid_writer.release(
) # release previous video writer
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))
vid_writer = cv2.VideoWriter(
save_path, cv2.VideoWriter_fourcc(*opt.fourcc),
fps, (w, h))
vid_writer.write(im0)
frame_fps += 1
if ((time_synchronized() - t_fps) >= 1):
print('\n')
print('FPS=%.2f' % (frame_fps))
t_fps = time_synchronized()
frame_fps = 0
#print('FPS=%.2f' % (1/(time_synchronized() - t1)))
if save_txt or save_img:
print('Results saved to %s' % os.getcwd() + os.sep + out)
if platform == 'darwin': # MacOS
os.system('open ' + save_path)