def create(name, pretrained, channels, classes, autoshape):
"""Creates a specified YOLOv3 model
Arguments:
name (str): name of model, i.e. 'yolov3'
pretrained (bool): load pretrained weights into the model
channels (int): number of input channels
classes (int): number of model classes
Returns:
pytorch model
"""
try:
cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
model = Model(cfg, channels, classes)
if pretrained:
fname = f'{name}.pt' # checkpoint filename
attempt_download(fname) # download if not found locally
ckpt = torch.load(fname, map_location=torch.device('cpu')) # load
msd = model.state_dict() # model state_dict
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter
model.load_state_dict(csd, strict=False) # load
if len(ckpt['model'].names) == classes:
model.names = ckpt['model'].names # set class names attribute
if autoshape:
model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
device = select_device('0' if torch.cuda.is_available() else 'cpu') # default to GPU if available
return model.to(device)
except Exception as e:
help_url = 'https://github.com/ultralytics/yolov5/issues/36'
s = 'Cache maybe be out of date, try force_reload=True. See %s for help.' % help_url
raise Exception(s) from e
def custom(path_or_model='path/to/model.pt', autoshape=True, verbose=True):
"""YOLOv5-custom model https://github.com/ultralytics/yolov5
Arguments (3 options):
path_or_model (str): 'path/to/model.pt'
path_or_model (dict): torch.load('path/to/model.pt')
path_or_model (nn.Module): torch.load('path/to/model.pt')['model']
Returns:
pytorch model
"""
set_logging(verbose=verbose)
model = torch.load(path_or_model) if isinstance(
path_or_model, str) else path_or_model # load checkpoint
if isinstance(model, dict):
model = model['ema' if model.get('ema') else 'model'] # load model
hub_model = Model(model.yaml).to(next(model.parameters()).device) # create
hub_model.load_state_dict(model.float().state_dict()) # load state_dict
hub_model.names = model.names # class names
if autoshape:
hub_model = hub_model.autoshape(
) # for file/URI/PIL/cv2/np inputs and NMS
device = select_device('0' if torch.cuda.is_available() else
'cpu') # default to GPU if available
return hub_model.to(device)
def test_2():
from models.yolo import Model
device = 'cuda:0'
model_path = '/home/lintao/jobs/logo/yolov5-4.0/yolov5s.pt'
# model = torch.load(model_path)['model'].float()
model = Model(
'/home/lintao/jobs/logo/yolov5-4.0/models/yolov5s.yaml').eval()
model.to(device)
model.model[-1].export = True
x = torch.ones((1, 3, 640, 640)).float().cuda()
y = model(x)
save_path = model_path.replace('.pt', '.onnx') # filename
torch_2_onnx(model,
x,
input_names=['images'],
output_names=['classes'],
save_path=save_path)
def create(name,
pretrained=True,
channels=3,
classes=80,
autoshape=True,
verbose=True):
"""Creates a specified YOLOv5 model
Arguments:
name (str): name of model, i.e. 'yolov5s'
pretrained (bool): load pretrained weights into the model
channels (int): number of input channels
classes (int): number of model classes
autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
verbose (bool): print all information to screen
Returns:
YOLOv5 pytorch model
"""
set_logging(verbose=verbose)
fname = Path(name).with_suffix('.pt') # checkpoint filename
try:
if pretrained and channels == 3 and classes == 80:
model = attempt_load(
fname,
map_location=torch.device('cpu')) # download/load FP32 model
else:
cfg = list((Path(__file__).parent /
'models').rglob(f'{name}.yaml'))[0] # model.yaml path
model = Model(cfg, channels, classes) # create model
if pretrained:
attempt_download(fname) # download if not found locally
ckpt = torch.load(fname,
map_location=torch.device('cpu')) # load
msd = model.state_dict() # model state_dict
csd = ckpt['model'].float().state_dict(
) # checkpoint state_dict as FP32
csd = {
k: v
for k, v in csd.items() if msd[k].shape == v.shape
} # filter
model.load_state_dict(csd, strict=False) # load
if len(ckpt['model'].names) == classes:
model.names = ckpt[
'model'].names # set class names attribute
if autoshape:
model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
device = select_device('0' if torch.cuda.is_available() else
'cpu') # default to GPU if available
return model.to(device)
except Exception as e:
help_url = 'https://github.com/ultralytics/yolov5/issues/36'
s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url
raise Exception(s) from e
def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
"""Creates a specified YOLOv5 model
Arguments:
name (str): name of model, i.e. 'yolov5s'
pretrained (bool): load pretrained weights into the model
channels (int): number of input channels
classes (int): number of model classes
autoshape (bool): apply YOLOv5 .autoshape() wrapper to model
verbose (bool): print all information to screen
device (str, torch.device, None): device to use for model parameters
Returns:
YOLOv5 pytorch model
"""
from pathlib import Path
from models.common import AutoShape
from models.experimental import attempt_load
from models.yolo import Model
from utils.downloads import attempt_download
from utils.general import check_requirements, intersect_dicts, set_logging
from utils.torch_utils import select_device
file = Path(__file__).resolve()
check_requirements(exclude=('tensorboard', 'thop', 'opencv-python'))
set_logging(verbose=verbose)
save_dir = Path('') if str(name).endswith('.pt') else file.parent
path = (save_dir / name).with_suffix('.pt') # checkpoint path
try:
device = select_device(('0' if torch.cuda.is_available() else 'cpu') if device is None else device)
if pretrained and channels == 3 and classes == 80:
model = attempt_load(path, map_location=device) # download/load FP32 model
else:
cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
model = Model(cfg, channels, classes) # create model
if pretrained:
ckpt = torch.load(attempt_download(path), map_location=device) # load
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
csd = intersect_dicts(csd, model.state_dict(), exclude=['anchors']) # intersect
model.load_state_dict(csd, strict=False) # load
if len(ckpt['model'].names) == classes:
model.names = ckpt['model'].names # set class names attribute
if autoshape:
model = AutoShape(model) # for file/URI/PIL/cv2/np inputs and NMS
return model.to(device)
except Exception as e:
help_url = 'https://github.com/ultralytics/yolov5/issues/36'
s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url
raise Exception(s) from e
def _create(name, pretrained=True, channels=3, classes=80, autoshape=True, verbose=True, device=None):
"""Creates a specified YOLOv3 model
Arguments:
name (str): name of model, i.e. 'yolov3'
pretrained (bool): load pretrained weights into the model
channels (int): number of input channels
classes (int): number of model classes
autoshape (bool): apply YOLOv3 .autoshape() wrapper to model
verbose (bool): print all information to screen
device (str, torch.device, None): device to use for model parameters
Returns:
YOLOv3 pytorch model
"""
from pathlib import Path
from models.yolo import Model, attempt_load
from utils.general import check_requirements, set_logging
from utils.google_utils import attempt_download
from utils.torch_utils import select_device
check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('tensorboard', 'pycocotools', 'thop'))
set_logging(verbose=verbose)
fname = Path(name).with_suffix('.pt') # checkpoint filename
try:
if pretrained and channels == 3 and classes == 80:
model = attempt_load(fname, map_location=torch.device('cpu')) # download/load FP32 model
else:
cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0] # model.yaml path
model = Model(cfg, channels, classes) # create model
if pretrained:
ckpt = torch.load(attempt_download(fname), map_location=torch.device('cpu')) # load
msd = model.state_dict() # model state_dict
csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32
csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape} # filter
model.load_state_dict(csd, strict=False) # load
if len(ckpt['model'].names) == classes:
model.names = ckpt['model'].names # set class names attribute
if autoshape:
model = model.autoshape() # for file/URI/PIL/cv2/np inputs and NMS
device = select_device('0' if torch.cuda.is_available() else 'cpu') if device is None else torch.device(device)
return model.to(device)
except Exception as e:
help_url = 'https://github.com/ultralytics/yolov5/issues/36'
s = 'Cache may be out of date, try `force_reload=True`. See %s for help.' % help_url
raise Exception(s) from e
# Load PyTorch model
# ckpt = torch.load(opt.weights, map_location=lambda storage, loc: storage.cuda())['model'].float()
with open('./models/configs/yolo3d_5m.yaml') as f:
cfg = yaml.load(f, Loader=yaml.FullLoader)
cfg.update(opt.__dict__)
print(cfg)
model = Model(cfg)
model.eval()
checkpointer = model_utils.CheckPointer(model, device=device)
checkpointer.load(opt.weights, load_solver=False)
# model.to(device)
if half:
model.half() # to FP16
img = img.half()
else:
model.to(torch.float32)
model.to(device)
# _print_weights_(model)
_ = model(img) # dry run
model.model[-1].export = True # set Detect() layer export=True
# TorchScript export
try:
print('\nStarting TorchScript export with torch %s...' %
torch.__version__)
f = opt.weights.replace('.pt', '.torchscript.pt') # filename
ts = torch.jit.trace(model, img)
ts.save(f)
print('TorchScript export success, saved as %s' % f)
except Exception as e:
print('TorchScript export failure: %s' % e)
def detect():
weights, imgsz, output = opt.checkpoint, opt.img_size, opt.output_video
# Initialize
device = torch_utils.select_device(opt.device)
half = device.type != 'cpu' # half precision only supported on CUDA
with open(opt.project) as f:
data_dict = yaml.load(f, Loader=yaml.FullLoader)
names = data_dict['names']
dest_object = data_dict[
'dest_object'] if 'dest_object' in data_dict else names
if 'name_map' in data_dict:
name_map = data_dict['name_map']
else:
name_map = defaultdict()
for x in dest_object:
name_map[x] = x
draw_names = set()
for k, v in name_map.items():
draw_names.add(v)
draw_names = list(draw_names)
colors = get_all_colors(len(draw_names))
model = Model(data_dict).to(device)
model.load_state_dict(torch.load(weights, map_location=device))
model.to(device).eval()
if half:
model.half()
if opt.video_type == 'camera':
rtsp = 'rtsp://*****:*****@' + opt.input_video + ':554/h264/chCH/sub/av_stream'
cap = cv2.VideoCapture(rtsp)
elif opt.video_type == 'video':
cap = cv2.VideoCapture(opt.input_video)
else:
print('Input video type ERROR!')
return
fps = int(cap.get(cv2.CAP_PROP_FPS))
width = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
print(fps, width, height)
fourcc = cv2.VideoWriter_fourcc('m', 'p', '4', 'v')
outstream = cv2.VideoWriter(output, fourcc, fps, (width, height))
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
while (cap.isOpened()):
ret, im0s = cap.read()
if ret:
pred = forward_one(model, im0s, imgsz, device, half, opt)
for i, det in enumerate(pred): # detections per image
if det is not None and len(det):
for *xyxy, conf, cls in det:
if names[int(cls)] in dest_object:
draw_str = name_map[names[int(cls)]]
color = colors[draw_names.index(draw_str)]
label = '%s %.2f' % (draw_str, conf)
xmin, ymin, xmax, ymax = xyxy
cv2.rectangle(im0s, (xmin, ymin), (xmax, ymax),
color=color,
thickness=1)
cv2.putText(im0s, label, (xmin, ymax),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, color,
1)
if opt.need_view:
cv2.imshow('real-time', im0s)
key = cv2.waitKey(delay=1)
if key == ord('q'):
break
else:
outstream.write(im0s)
cv2.destroyAllWindows()
print('Done. (%.3fs)' % (time.time() - t0))
def detect():
source, weights, view_img, save_txt, imgsz = \
opt.input_images, opt.checkpoint, 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
device = torch_utils.select_device(opt.device)
if os.path.exists(opt.output_images):
shutil.rmtree(opt.output_images) # delete output folder
os.makedirs(opt.output_images) # make new output folder
half = device.type != 'cpu' # half precision only supported on CUDA
with open(opt.project) as f:
data_dict = yaml.load(f, Loader=yaml.FullLoader)
model = Model(data_dict).to(device)
model.load_state_dict(torch.load(weights, map_location=device))
model.names = data_dict['names']
# Load model
#google_utils.attempt_download(weights)
#model = torch.load(weights, map_location=device)['model'].float() # load to FP32
#model = torch.load(weights, map_location=device).float() # load to FP32
# 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
# 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))]
colors = get_all_colors(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:
for f in os.listdir(source):
t1 = time.time()
path = os.path.join(source, f)
im0s = cv2.imread(path)
img = letterbox(im0s, new_shape=imgsz)[0]
img = img[:, :, ::-1].transpose(2, 0, 1)
img = np.ascontiguousarray(img)
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 = torch_utils.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 = torch_utils.time_synchronized()
# Process detections
for i, det in enumerate(pred): # detections per image
p, s, im0 = path, '', im0s
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 det:
label = '%s %.2f' % (names[int(cls)], conf)
xmin, ymin, xmax, ymax = xyxy
color = colors[int(cls)]
cv2.rectangle(im0, (xmin, ymin), (xmax, ymax), color=color, thickness=2)
cv2.putText(im0, label, (xmin, ymax), cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 1)
cv2.imwrite(os.path.join(opt.output_images, f), im0)
print('%s Done. (%.3fs)' % (path, time.time() - t1))
print('Done. (%.3fs)' % (time.time() - t0))
def test(data,
weights=None,
batch_size=16,
imgsz=640,
conf_thres=0.001,
iou_thres=0.6, # for NMS
save_json=False,
single_cls=False,
augment=False,
verbose=False,
model=None,
dataloader=None,
fast=False):
# Initialize/load model and set device
if model is None:
training = False
device = torch_utils.select_device(opt.device, batch_size=batch_size)
half = device.type != 'cpu' # half precision only supported on CUDA
# Remove previous
for f in glob.glob('test_batch*.jpg'):
os.remove(f)
# Load model
google_utils.attempt_download(weights)
# model = torch.load(weights, map_location=device)['state_dict'].float() # load to FP32
model = Model(model_cfg='/home/ai/yulu/yolov5/models/yolov5s.yaml')
if os.path.exists(opt.weights):
ckpt = torch.load(opt.weights, map_location=device)
state_dict = {key: ckpt['state_dict'][key] for key in model.state_dict().keys()}
model.load_state_dict(state_dict)
# torch_utils.model_info(model)
model.fuse()
model.to(device)
if half:
model.half() # to FP16
# Multi-GPU disabled, incompatible with .half()
# if device.type != 'cpu' and torch.cuda.device_count() > 1:
# model = nn.DataParallel(model)
else: # called by train.py
training = True
device = next(model.parameters()).device # get model device
# half disabled https://github.com/ultralytics/yolov5/issues/99
half = False # device.type != 'cpu' and torch.cuda.device_count() == 1
if half:
model.half() # to FP16
# Configure
model.eval()
with open(data) as f:
data = yaml.load(f, Loader=yaml.FullLoader) # model dict
nc = 1 if single_cls else int(data['nc']) # number of classes
iouv = torch.linspace(0.5, 0.95, 10).to(device) # iou vector for [email protected]:0.95
# iouv = iouv[0].view(1) # comment for [email protected]:0.95
niou = iouv.numel()
# Dataloader
if dataloader is None: # not training
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
fast |= conf_thres > 0.001 # enable fast mode
path = data['test'] if opt.task == 'test' else data['val'] # path to val/test images
dataset = LoadImagesAndLabels(path,
imgsz,
batch_size,
rect=True, # rectangular inference
single_cls=opt.single_cls, # single class mode
pad=0.5) # padding
batch_size = min(batch_size, len(dataset))
nw = min([os.cpu_count(), batch_size if batch_size > 1 else 0, 8]) # number of workers
dataloader = DataLoader(dataset,
batch_size=batch_size,
num_workers=nw,
pin_memory=True,
collate_fn=dataset.collate_fn)
seen = 0
# names = model.names if hasattr(model, 'names') else model.module.names
coco91class = coco80_to_coco91_class()
s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Targets', 'P', 'R', '[email protected]', '[email protected]:.95')
p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0.
loss = torch.zeros(3, device=device)
jdict, stats, ap, ap_class = [], [], [], []
for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
img = 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
targets = targets.to(device)
nb, _, height, width = img.shape # batch size, channels, height, width
whwh = torch.Tensor([width, height, width, height]).to(device)
# Disable gradients
with torch.no_grad():
# Run model
t = torch_utils.time_synchronized()
inf_out, train_out = model(img, augment=augment) # inference and training outputs
t0 += torch_utils.time_synchronized() - t
# Compute loss
if training: # if model has loss hyperparameters
loss += compute_loss([x.float() for x in train_out], targets, model)[1][:3] # GIoU, obj, cls
# Run NMS
t = torch_utils.time_synchronized()
output = non_max_suppression(inf_out, conf_thres=conf_thres, iou_thres=iou_thres, fast=fast) # ??????????????
t1 += torch_utils.time_synchronized() - t
# Statistics per image
for si, pred in enumerate(output):
labels = targets[targets[:, 0] == si, 1:]
nl = len(labels)
tcls = labels[:, 0].tolist() if nl else [] # target class
seen += 1
if pred is None:
if nl:
stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
continue
# Append to text file
# with open('test.txt', 'a') as file:
# [file.write('%11.5g' * 7 % tuple(x) + '\n') for x in pred]
# Clip boxes to image bounds
clip_coords(pred, (height, width))
# Append to pycocotools JSON dictionary
if save_json:
# [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
image_id = int(Path(paths[si]).stem.split('_')[-1])
box = pred[:, :4].clone() # xyxy
scale_coords(img[si].shape[1:], box, shapes[si][0], shapes[si][1]) # to original shape
box = xyxy2xywh(box) # xywh
box[:, :2] -= box[:, 2:] / 2 # xy center to top-left corner
for p, b in zip(pred.tolist(), box.tolist()):
jdict.append({'image_id': image_id,
'category_id': coco91class[int(p[5])],
'bbox': [round(x, 3) for x in b],
'score': round(p[4], 5)})
# Assign all predictions as incorrect
correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
if nl:
detected = [] # target indices
tcls_tensor = labels[:, 0]
# target boxes
tbox = xywh2xyxy(labels[:, 1:5]) * whwh
# Per target class
for cls in torch.unique(tcls_tensor):
ti = (cls == tcls_tensor).nonzero().view(-1) # prediction indices
pi = (cls == pred[:, 5]).nonzero().view(-1) # target indices
# Search for detections
if pi.shape[0]:
# Prediction to target ious
ious, i = box_iou(pred[pi, :4], tbox[ti]).max(1) # best ious, indices
# Append detections
for j in (ious > iouv[0]).nonzero():
d = ti[i[j]] # detected target
if d not in detected:
detected.append(d)
correct[pi[j]] = ious[j] > iouv # iou_thres is 1xn
if len(detected) == nl: # all targets already located in image
break
# Append statistics (correct, conf, pcls, tcls)
stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))
# Plot images
if batch_i < 1:
f = 'test_batch%g_gt.jpg' % batch_i # filename
# plot_images(img, targets, paths, f, names) # ground truth
plot_images(img, targets, paths, f, 'yolov5s')
f = 'test_batch%g_pred.jpg' % batch_i
# plot_images(img, output_to_target(output, width, height), paths, f, names) # predictions
plot_images(img, output_to_target(output, width, height), paths, f, 'yolov5s')
# Compute statistics
stats = [np.concatenate(x, 0) for x in zip(*stats)] # to numpy
if len(stats):
p, r, ap, f1, ap_class = ap_per_class(*stats)
p, r, ap50, ap = p[:, 0], r[:, 0], ap[:, 0], ap.mean(1) # [P, R, [email protected], [email protected]:0.95]
mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
nt = np.bincount(stats[3].astype(np.int64), minlength=nc) # number of targets per class
else:
nt = torch.zeros(1)
# Print results
pf = '%20s' + '%12.3g' * 6 # print format
print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
# Print results per class
if verbose and nc > 1 and len(stats):
for i, c in enumerate(ap_class):
print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
# Print speeds
t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size) # tuple
if not training:
print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)
# Save JSON
if save_json and map50 and len(jdict):
imgIds = [int(Path(x).stem.split('_')[-1]) for x in dataloader.dataset.img_files]
f = 'detections_val2017_%s_results.json' % \
(weights.split(os.sep)[-1].replace('.pt', '') if weights else '') # filename
print('\nCOCO mAP with pycocotools... saving %s...' % f)
with open(f, 'w') as file:
json.dump(jdict, file)
try:
from pycocotools.coco import COCO
from pycocotools.cocoeval import COCOeval
# https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
cocoGt = COCO(glob.glob('../coco/annotations/instances_val*.json')[0]) # initialize COCO ground truth api
cocoDt = cocoGt.loadRes(f) # initialize COCO pred api
cocoEval = COCOeval(cocoGt, cocoDt, 'bbox')
cocoEval.params.imgIds = imgIds # image IDs to evaluate
cocoEval.evaluate()
cocoEval.accumulate()
cocoEval.summarize()
map, map50 = cocoEval.stats[:2] # update results ([email protected]:0.95, [email protected])
except:
print('WARNING: pycocotools must be installed with numpy==1.17 to run correctly. '
'See https://github.com/cocodataset/cocoapi/issues/356')
# Return results
maps = np.zeros(nc) + map
for i, c in enumerate(ap_class):
maps[c] = ap[i]
return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
def train(hyp, opt, device, tb_writer=None, wandb=None):
logger.info(f'Hyperparameters {hyp}')
save_dir, epochs, batch_size, total_batch_size, weights, rank = \
Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
# Directories
wdir = save_dir / 'weights'
wdir.mkdir(parents=True, exist_ok=True) # make dir
last = wdir / 'last.pt'
best = wdir / 'best.pt'
results_file = save_dir / 'results.txt'
# Save run settings
with open(save_dir / 'hyp.yaml', 'w') as f:
yaml.dump(hyp, f, sort_keys=False)
with open(save_dir / 'opt.yaml', 'w') as f:
yaml.dump(vars(opt), f, sort_keys=False)
# Configure
plots = not opt.evolve # create plots
cuda = device.type != 'cpu'
init_seeds(2 + rank)
with open(opt.data) as f:
data_dict = yaml.load(f, Loader=yaml.FullLoader) # data dict
with torch_distributed_zero_first(rank):
check_dataset(data_dict) # check
train_path = data_dict['train']
test_path = data_dict['val']
nc, names = (1, ['item']) if opt.single_cls else (int(
data_dict['nc']), data_dict['names']) # number classes, names
assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (
len(names), nc, opt.data) # check
# Model
pretrained = weights.endswith('.pt')
if pretrained:
with torch_distributed_zero_first(rank):
attempt_download(weights) # download if not found locally
ckpt = torch.load(weights, map_location=device) # load checkpoint
if hyp.get('anchors'):
ckpt['model'].yaml['anchors'] = round(
hyp['anchors']) # force autoanchor
model = Model(opt.cfg or ckpt['model'].yaml, ch=3,
nc=nc).to(device) # create
exclude = ['anchor'] if opt.cfg or hyp.get('anchors') else [
] # exclude keys
state_dict = ckpt['model'].float().state_dict() # to FP32
state_dict = intersect_dicts(state_dict,
model.state_dict(),
exclude=exclude) # intersect
model.load_state_dict(state_dict, strict=False) # load
logger.info(
'Transferred %g/%g items from %s' %
(len(state_dict), len(model.state_dict()), weights)) # report
else:
model = Model(opt.cfg, ch=3, nc=nc).to(device) # create
# replace the original model to a quantized model
if opt.quantization:
print(model)
model = model.cpu()
print("opt.cfg => {}".format(opt.cfg))
if opt.cfg.split("/")[-1].split(".")[-2] == "yolov3-tiny":
print("model: yolov3-tiny")
layer_layer_count = 12
else:
layer_layer_count = 100000
# quantize model
model = tflite.replace(model=model,
quantization_bits=opt.quantization_bits,
scale_bits=opt.scale_bits,
bias_bits=opt.bias_bits,
layer_layer_count=layer_layer_count)
model = model.to(device)
# Freeze
freeze = [] # parameter names to freeze (full or partial)
for k, v in model.named_parameters():
v.requires_grad = True # train all layers
if any(x in k for x in freeze):
print('freezing %s' % k)
v.requires_grad = False
# Optimizer
nbs = 64 # nominal batch size
accumulate = max(round(nbs / total_batch_size),
1) # accumulate loss before optimizing
hyp['weight_decay'] *= total_batch_size * accumulate / nbs # scale weight_decay
pg0, pg1, pg2 = [], [], [] # optimizer parameter groups
for k, v in model.named_modules():
if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
pg2.append(v.bias) # biases
if isinstance(v, nn.BatchNorm2d):
pg0.append(v.weight) # no decay
elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
pg1.append(v.weight) # apply decay
if opt.adam:
optimizer = optim.Adam(pg0,
lr=hyp['lr0'],
betas=(hyp['momentum'],
0.999)) # adjust beta1 to momentum
else:
optimizer = optim.SGD(pg0,
lr=hyp['lr0'],
momentum=hyp['momentum'],
nesterov=True)
optimizer.add_param_group({
'params': pg1,
'weight_decay': hyp['weight_decay']
}) # add pg1 with weight_decay
optimizer.add_param_group({'params': pg2}) # add pg2 (biases)
logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' %
(len(pg2), len(pg1), len(pg0)))
del pg0, pg1, pg2
# Scheduler https://arxiv.org/pdf/1812.01187.pdf
# https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
lf = lambda x: ((1 + math.cos(x * math.pi / epochs)) / 2) * (1 - hyp[
'lrf']) + hyp['lrf'] # cosine
scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
# plot_lr_scheduler(optimizer, scheduler, epochs)
# Logging
if wandb and wandb.run is None:
opt.hyp = hyp # add hyperparameters
wandb_run = wandb.init(
config=opt,
resume="allow",
project='YOLOv3'
if opt.project == 'runs/train' else Path(opt.project).stem,
name=save_dir.stem,
id=ckpt.get('wandb_id') if 'ckpt' in locals() else None)
loggers = {'wandb': wandb} # loggers dict
# Resume
start_epoch, best_fitness = 0, 0.0
if pretrained:
# Optimizer
if ckpt['optimizer'] is not None:
optimizer.load_state_dict(ckpt['optimizer'])
best_fitness = ckpt['best_fitness']
# Results
if ckpt.get('training_results') is not None:
with open(results_file, 'w') as file:
file.write(ckpt['training_results']) # write results.txt
# Epochs
start_epoch = ckpt['epoch'] + 1
if opt.resume:
assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (
weights, epochs)
if epochs < start_epoch:
logger.info(
'%s has been trained for %g epochs. Fine-tuning for %g additional epochs.'
% (weights, ckpt['epoch'], epochs))
epochs += ckpt['epoch'] # finetune additional epochs
del ckpt, state_dict
# Image sizes
gs = int(max(model.stride)) # grid size (max stride)
imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size
] # verify imgsz are gs-multiples
# DP mode
if cuda and rank == -1 and torch.cuda.device_count() > 1:
model = torch.nn.DataParallel(model)
# SyncBatchNorm
if opt.sync_bn and cuda and rank != -1:
model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
logger.info('Using SyncBatchNorm()')
# EMA
ema = ModelEMA(model) if rank in [-1, 0] else None
# DDP mode
if cuda and rank != -1:
model = DDP(model,
device_ids=[opt.local_rank],
output_device=opt.local_rank)
# xiezheng add
# Set hook to store Conv results for No
register_hook(model, hook_conv_results)
logger.info("len(oaq_conv_result)={},\noaq_conv_result={}".format(
len(oaq_conv_result), oaq_conv_result))
# Trainloader
dataloader, dataset = create_dataloader(train_path,
imgsz,
batch_size,
gs,
opt,
hyp=hyp,
augment=True,
cache=opt.cache_images,
rect=opt.rect,
rank=rank,
world_size=opt.world_size,
workers=opt.workers,
image_weights=opt.image_weights)
mlc = np.concatenate(dataset.labels, 0)[:, 0].max() # max label class
nb = len(dataloader) # number of batches
assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (
mlc, nc, opt.data, nc - 1)
# Process 0
if rank in [-1, 0]:
ema.updates = start_epoch * nb // accumulate # set EMA updates
testloader = create_dataloader(
test_path,
imgsz_test,
total_batch_size,
gs,
opt, # testloader
hyp=hyp,
cache=opt.cache_images and not opt.notest,
rect=True,
rank=-1,
world_size=opt.world_size,
workers=opt.workers,
pad=0.5)[0]
if not opt.resume:
labels = np.concatenate(dataset.labels, 0)
c = torch.tensor(labels[:, 0]) # classes
# cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency
# model._initialize_biases(cf.to(device))
if plots:
Thread(target=plot_labels,
args=(labels, save_dir, loggers),
daemon=True).start()
if tb_writer:
tb_writer.add_histogram('classes', c, 0)
# Anchors
if not opt.noautoanchor:
check_anchors(dataset,
model=model,
thr=hyp['anchor_t'],
imgsz=imgsz)
# Model parameters
hyp['cls'] *= nc / 80. # scale coco-tuned hyp['cls'] to current dataset
model.nc = nc # attach number of classes to model
model.hyp = hyp # attach hyperparameters to model
model.gr = 1.0 # iou loss ratio (obj_loss = 1.0 or iou)
model.class_weights = labels_to_class_weights(dataset.labels, nc).to(
device) # attach class weights
model.names = names
# Start training
t0 = time.time()
nw = max(round(hyp['warmup_epochs'] * nb),
1000) # number of warmup iterations, max(3 epochs, 1k iterations)
# nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training
maps = np.zeros(nc) # mAP per class
results = (0, 0, 0, 0, 0, 0, 0
) # P, R, [email protected], [email protected], val_loss(box, obj, cls)
scheduler.last_epoch = start_epoch - 1 # do not move
# scaler = amp.GradScaler(enabled=cuda)
logger.info('Image sizes %g train, %g test\n'
'Using %g dataloader workers\nLogging results to %s\n'
'Starting training for %g epochs...' %
(imgsz, imgsz_test, dataloader.num_workers, save_dir, epochs))
for epoch in range(
start_epoch, epochs
): # epoch ------------------------------------------------------------------
model.train()
if opt.quantization:
tflite.unfreeze_model(model) # unfreeze the activation range
# Update image weights (optional)
if opt.image_weights:
# Generate indices
if rank in [-1, 0]:
cw = model.class_weights.cpu().numpy() * (
1 - maps)**2 # class weights
iw = labels_to_image_weights(dataset.labels,
nc=nc,
class_weights=cw) # image weights
dataset.indices = random.choices(
range(dataset.n), weights=iw,
k=dataset.n) # rand weighted idx
# Broadcast if DDP
if rank != -1:
indices = (torch.tensor(dataset.indices)
if rank == 0 else torch.zeros(dataset.n)).int()
dist.broadcast(indices, 0)
if rank != 0:
dataset.indices = indices.cpu().numpy()
# Update mosaic border
# b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
# dataset.mosaic_border = [b - imgsz, -b] # height, width borders
mloss = torch.zeros(4, device=device) # mean losses
if rank != -1:
dataloader.sampler.set_epoch(epoch)
pbar = enumerate(dataloader)
logger.info(
('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls',
'total', 'targets', 'img_size'))
if rank in [-1, 0]:
pbar = tqdm(pbar, total=nb) # progress bar
optimizer.zero_grad()
for i, (
imgs, targets, paths, _
) in pbar: # batch -------------------------------------------------------------
ni = i + nb * epoch # number integrated batches (since train start)
imgs = imgs.to(device, non_blocking=True).float(
) / 255.0 # uint8 to float32, 0-255 to 0.0-1.0
# Warmup
if ni <= nw:
xi = [0, nw] # x interp
# model.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou)
accumulate = max(
1,
np.interp(ni, xi, [1, nbs / total_batch_size]).round())
for j, x in enumerate(optimizer.param_groups):
# bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
x['lr'] = np.interp(ni, xi, [
hyp['warmup_bias_lr'] if j == 2 else 0.0,
x['initial_lr'] * lf(epoch)
])
if 'momentum' in x:
x['momentum'] = np.interp(
ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
# Multi-scale
if opt.multi_scale:
sz = random.randrange(imgsz * 0.5,
imgsz * 1.5 + gs) // gs * gs # size
sf = sz / max(imgs.shape[2:]) # scale factor
if sf != 1:
ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]
] # new shape (stretched to gs-multiple)
imgs = F.interpolate(imgs,
size=ns,
mode='bilinear',
align_corners=False)
# Forward
# with amp.autocast(enabled=cuda):
pred = model(imgs) # forward
loss, loss_items = compute_loss(pred, targets.to(device),
model) # loss scaled by batch_size
if rank != -1:
loss *= opt.world_size # gradient averaged between devices in DDP mode
# Backward
# scaler.scale(loss).backward()
loss.backward()
# Optimize
if ni % accumulate == 0:
# scaler.step(optimizer) # optimizer.step
# scaler.update()
optimizer.step()
optimizer.zero_grad()
if ema:
ema.update(model)
# Print
if rank in [-1, 0]:
mloss = (mloss * i + loss_items) / (i + 1
) # update mean losses
mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9
if torch.cuda.is_available() else 0) # (GB)
s = ('%10s' * 2 +
'%10.4g' * 6) % ('%g/%g' % (epoch, epochs - 1), mem,
*mloss, targets.shape[0], imgs.shape[-1])
pbar.set_description(s)
# Plot
if plots and ni < 3:
f = save_dir / f'train_batch{ni}.jpg' # filename
Thread(target=plot_images,
args=(imgs, targets, paths, f),
daemon=True).start()
# if tb_writer:
# tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
# tb_writer.add_graph(model, imgs) # add model to tensorboard
elif plots and ni == 3 and wandb:
wandb.log({
"Mosaics": [
wandb.Image(str(x), caption=x.name)
for x in save_dir.glob('train*.jpg')
]
})
# xiezheng add
# calculating No and updating alpha are executed every M=50 steps
if ni > nw and (ni - nw) % opt.OAQ_m == 0:
logger.info("ni={}, calculate No and updata alpha!".format(ni))
No = calculate_No(device, model, oaq_conv_result,
opt.conv_accumulator_bits, logger)
lr_max = hyp['lr0']
lr_curr = [x['lr']
for x in optimizer.param_groups][1] # weight lr
iteration_batch_size = imgs.size(0)
update_alpha(device, model, No, iteration_batch_size, lr_max,
lr_curr, logger)
# Test: calculate No and updata alpha
# logger.info("ni={}, calculate No and updata alpha!".format(ni))
# No = calculate_No(device, model, oaq_conv_result, opt.conv_accumulator_bits, logger)
# lr_max = hyp['lr0']
# lr_curr = [x['lr'] for x in optimizer.param_groups][1] # weight lr
# iteration_batch_size = imgs.size(0)
# update_alpha(device, model, No, iteration_batch_size, lr_max, lr_curr, logger)
# xiezheng add
# clear hook results
oaq_conv_result.clear()
# end batch ------------------------------------------------------------------------------------------------
# end epoch ----------------------------------------------------------------------------------------------------
# Scheduler
lr = [x['lr'] for x in optimizer.param_groups] # for tensorboard
scheduler.step()
# DDP process 0 or single-GPU
if rank in [-1, 0]:
# mAP
if ema:
ema.update_attr(
model,
include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride'])
final_epoch = epoch + 1 == epochs
if not opt.notest or final_epoch: # Calculate mAP
if opt.quantization:
tflite.freeze_model(ema.ema)
results, maps, times = test.test(
opt.data,
batch_size=total_batch_size,
imgsz=imgsz_test,
model=ema.ema,
single_cls=opt.single_cls,
dataloader=testloader,
save_dir=save_dir,
plots=plots and final_epoch,
log_imgs=opt.log_imgs if wandb else 0)
# Write
with open(results_file, 'a') as f:
f.write(
s + '%10.4g' * 7 % results +
'\n') # P, R, [email protected], [email protected], val_loss(box, obj, cls)
if len(opt.name) and opt.bucket:
os.system('gsutil cp %s gs://%s/results/results%s.txt' %
(results_file, opt.bucket, opt.name))
# Log
tags = [
'train/box_loss',
'train/obj_loss',
'train/cls_loss', # train loss
'metrics/precision',
'metrics/recall',
'metrics/mAP_0.5',
'metrics/mAP_0.5:0.95',
'val/box_loss',
'val/obj_loss',
'val/cls_loss', # val loss
'x/lr0',
'x/lr1',
'x/lr2'
] # params
for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags):
if tb_writer:
tb_writer.add_scalar(tag, x, epoch) # tensorboard
if wandb:
wandb.log({tag: x}) # W&B
# Update best mAP
fi = fitness(np.array(results).reshape(
1, -1)) # weighted combination of [P, R, [email protected], [email protected]]
if fi > best_fitness:
best_fitness = fi
# Save model
save = (not opt.nosave) or (final_epoch and not opt.evolve)
if save:
with open(results_file, 'r') as f: # create checkpoint
ckpt = {
'epoch':
epoch,
'best_fitness':
best_fitness,
'training_results':
f.read(),
'model':
ema.ema,
'optimizer':
None if final_epoch else optimizer.state_dict(),
'wandb_id':
wandb_run.id if wandb else None
}
# Save last, best and delete
torch.save(ckpt, last)
if best_fitness == fi:
torch.save(ckpt, best)
del ckpt
# end epoch ----------------------------------------------------------------------------------------------------
# end training
if rank in [-1, 0]:
# Strip optimizers
for f in [last, best]:
if f.exists(): # is *.pt
strip_optimizer(f) # strip optimizer
os.system('gsutil cp %s gs://%s/weights' %
(f, opt.bucket)) if opt.bucket else None # upload
# Plots
if plots:
plot_results(save_dir=save_dir) # save as results.png
if wandb:
files = [
'results.png', 'precision_recall_curve.png',
'confusion_matrix.png'
]
wandb.log({
"Results": [
wandb.Image(str(save_dir / f), caption=f)
for f in files if (save_dir / f).exists()
]
})
logger.info('%g epochs completed in %.3f hours.\n' %
(epoch - start_epoch + 1, (time.time() - t0) / 3600))
# Test best.pt
if opt.data.endswith('coco.yaml') and nc == 80: # if COCO
if opt.quantization:
model_test = torch.load(
best if best.exists() else last,
map_location=device)['model'].float().eval()
tflite.freeze_model(model_test)
else:
model_test = attempt_load(best if best.exists() else last,
device)
results, _, _ = test.test(
opt.data,
batch_size=total_batch_size,
imgsz=imgsz_test,
model=model_test,
single_cls=opt.single_cls,
dataloader=testloader,
save_dir=save_dir,
save_json=True, # use pycocotools
plots=False)
# Write
with open(results_file, 'a') as f:
f.write("Test best.pt:\n")
f.write(
s + '%10.4g' * 7 % results +
'\n') # P, R, [email protected], [email protected], val_loss(box, obj, cls)
else:
dist.destroy_process_group()
wandb.run.finish() if wandb and wandb.run else None
torch.cuda.empty_cache()
return results
def detect():
weights, imgsz = opt.checkpoint, opt.img_size
# Initialize
device = torch_utils.select_device(opt.device)
if os.path.exists(opt.output_images):
shutil.rmtree(opt.output_images) # delete output folder
os.makedirs(opt.output_images) # make new output folder
half = device.type != 'cpu' # half precision only supported on CUDA
with open(opt.project) as f:
data_dict = yaml.load(f, Loader=yaml.FullLoader)
names = data_dict['names']
dest_object = data_dict[
'dest_object'] if 'dest_object' in data_dict else names
if 'name_map' in data_dict:
name_map = data_dict['name_map']
else:
name_map = defaultdict()
for x in dest_object:
name_map[x] = x
draw_names = set()
for k, v in name_map.items():
draw_names.add(v)
draw_names = list(draw_names)
colors = get_all_colors(len(draw_names))
model = Model(data_dict).to(device)
model.load_state_dict(torch.load(weights, map_location=device))
model.to(device).eval()
if half:
model.half() # to FP16
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 f in os.listdir(opt.input_images):
t1 = time.time()
path = os.path.join(opt.input_images, f)
im0s = cv2.imread(path)
pred = forward_one(model, im0s, imgsz, device, half, opt)
for i, det in enumerate(pred): # detections per image
if det is not None and len(det):
for *xyxy, conf, cls in det:
if names[int(cls)] in dest_object:
draw_str = name_map[names[int(cls)]]
color = colors[draw_names.index(draw_str)]
label = '%s %.2f' % (draw_str, conf)
xmin, ymin, xmax, ymax = xyxy
cv2.rectangle(im0s, (xmin, ymin), (xmax, ymax),
color=color,
thickness=1)
cv2.putText(im0s, label, (xmin, ymax),
cv2.FONT_HERSHEY_SIMPLEX, 0.6, color, 1)
cv2.imwrite(os.path.join(opt.output_images, f), im0s)
print('%s Done. (%.3fs)' % (f, time.time() - t1))
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 == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')
# Initialize
device = torch_utils.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
google_utils.attempt_download(weights)
# model = torch.load(weights, map_location=device)['model'].float() # load to FP32
from models.yolo import Model
model = Model(model_cfg='/home/ai/yulu/yolov5/models/yolov5s.yaml').to(device)
if os.path.exists(opt.weights):
ckpt = torch.load('/home/ai/yulu/yolov5/weights/best0722.pt', map_location=device)
state_dict = {key:ckpt['state_dict'][key] for key in model.state_dict().keys()}
model.load_state_dict(state_dict)
# ################
# model = torch.load(weights, map_location=device)
# ckpt = {'epoch': model['epoch'],
# 'best_fitness': model['best_fitness'],
# 'training_results': model['training_results'],
# 'state_dict': model['model'].state_dict(),
# 'optimizer': None}
# #
# #
# # # Save last, best and delete
# torch.save(ckpt, 'yolov5_adult_kid.pt')
# ################
# 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
torch.backends.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 = ['child', 'adult']
# names = model.names if hasattr(model, 'names') else model.modules.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 = torch_utils.time_synchronized()
# img_input = torch.cat([img[..., ::2, ::2], img[..., 1::2, ::2], img[..., ::2, 1::2], img[..., 1::2, 1::2]], 1)
pred = model(img, augment=opt.augment)[0]
# Apply NMS
# pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres,
# fast=True, classes=opt.classes, agnostic=opt.agnostic_nms)
pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres,
fast=False, classes=opt.classes, agnostic=True)
t2 = torch_utils.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)
s += '%gx%g ' % img.shape[2:] # print string
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]].float() # 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 det:
if save_txt: # Write to file
xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() # normalized xywh
with open(save_path[:save_path.rfind('.')] + '.txt', 'a') as file:
file.write(('%g %g %g %g %g' + '\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)
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)
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)
print('Done. (%.3fs)' % (time.time() - t0))
