def plot(self, im, det):
'''names = self.names; colors = self.colors
for *xyxy, conf, c in reversed(det): # (x1,y1,x2,y2,conf,cls)
c = int(c); label = f'{names[c]} {conf:.2f}' # Add bbox to image
plot_one_box(xyxy, im, label=label, color=colors[c], line_width=2)#'''
names = self.names
from utils.plots import colors
annotator = Annotator(im, line_width=2, example=str(names))
for *xyxy, conf, c in reversed(det): # (x1,y1,x2,y2,conf,cls)
c = int(c)
label = f'{names[c]} {conf:.2f}' # Add bbox to image
annotator.box_label(xyxy, label, color=colors(c, True))
im[:] = annotator.result() #'''
return {
names[int(c)]: int((det[:, -1] == c).sum())
for c in det[:, -1].unique()
}
def run(
weights=ROOT / 'yolov5s.pt', # model.pt path(s)
source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
imgsz=640, # inference size (pixels)
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
webcam = source.isnumeric() or source.endswith(
'.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
# 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
# Initialize
set_logging()
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# Load model
w = str(weights[0] if isinstance(weights, list) else weights)
classify, suffix, suffixes = False, Path(w).suffix.lower(), [
'.pt', '.onnx', '.tflite', '.pb', ''
]
check_suffix(w, suffixes) # check weights have acceptable suffix
pt, onnx, tflite, pb, saved_model = (suffix == x
for x in suffixes) # backend booleans
stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
if pt:
model = torch.jit.load(w) if 'torchscript' in w else attempt_load(
weights, map_location=device, fuse=False)
stride = int(model.stride.max()) # model stride
names = model.module.names if hasattr(
model, 'module') else model.names # get class names
"""
for _, param in enumerate(model.named_parameters()):
print("====>", param[0], param[1].shape)
torch.save(model.state_dict(), 'new_params.pt')
for k, v in model.state_dict().items():
print(k, v.shape)
exit()
"""
if half:
model.half() # to FP16
if classify: # second-stage classifier
modelc = load_classifier(name='resnet50', n=2) # initialize
modelc.load_state_dict(
torch.load('resnet50.pt',
map_location=device)['model']).to(device).eval()
elif onnx:
if dnn:
# check_requirements(('opencv-python>=4.5.4',))
net = cv2.dnn.readNetFromONNX(w)
else:
check_requirements(('onnx', 'onnxruntime'))
import onnxruntime
session = onnxruntime.InferenceSession(w, None)
else: # TensorFlow models
check_requirements(('tensorflow>=2.4.1', ))
import tensorflow as tf
if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
def wrap_frozen_graph(gd, inputs, outputs):
x = tf.compat.v1.wrap_function(
lambda: tf.compat.v1.import_graph_def(gd, name=""),
[]) # wrapped import
return x.prune(
tf.nest.map_structure(x.graph.as_graph_element, inputs),
tf.nest.map_structure(x.graph.as_graph_element, outputs))
graph_def = tf.Graph().as_graph_def()
graph_def.ParseFromString(open(w, 'rb').read())
frozen_func = wrap_frozen_graph(gd=graph_def,
inputs="x:0",
outputs="Identity:0")
elif saved_model:
model = tf.keras.models.load_model(w)
elif tflite:
interpreter = tf.lite.Interpreter(
model_path=w) # load TFLite model
interpreter.allocate_tensors() # allocate
input_details = interpreter.get_input_details() # inputs
output_details = interpreter.get_output_details() # outputs
int8 = input_details[0][
'dtype'] == np.uint8 # is TFLite quantized uint8 model
imgsz = check_img_size(imgsz, s=stride) # check image size
# 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
if pt and device.type != 'cpu':
model(
torch.zeros(1, 3, *imgsz).to(device).type_as(
next(model.parameters()))) # run once
dt, seen = [0.0, 0.0, 0.0], 0
for path, img, im0s, vid_cap in dataset:
t1 = time_sync()
if onnx:
img = img.astype('float32')
else:
img = torch.from_numpy(img).to(device)
img = img.half() if half else img.float() # uint8 to fp16/32
img = img / 255.0 # 0 - 255 to 0.0 - 1.0
if len(img.shape) == 3:
img = img[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
if pt:
visualize = increment_path(save_dir / Path(path).stem,
mkdir=True) if visualize else False
pred = model(img, augment=augment, visualize=visualize)[0]
anchor_grid = model.model[-1].anchors * model.model[-1].stride[
..., None, None]
delattr(model.model[-1],
'anchor_grid') # model.model[-1] is detect layer
model.model[-1].register_buffer("anchor_grid", anchor_grid)
model.to(device).eval()
wts_file = "generated.wts"
with open(wts_file, 'w') as f:
f.write('{}\n'.format(len(model.state_dict().keys())))
for k, v in model.state_dict().items():
if len(v.shape) == 0:
continue
print(k, v.shape)
vr = v.reshape(-1).cpu().numpy()
f.write('{} {} {} {}'.format(
k, len(vr), v.shape[0],
v.shape[1] if len(v.shape) > 1 else 0))
for vv in vr:
f.write(' ')
f.write(struct.pack('>f', float(vv)).hex())
f.write('\n')
exit()
elif onnx:
if dnn:
net.setInput(img)
pred = torch.tensor(net.forward())
else:
pred = torch.tensor(
session.run([session.get_outputs()[0].name],
{session.get_inputs()[0].name: img}))
else: # tensorflow model (tflite, pb, saved_model)
imn = img.permute(0, 2, 3, 1).cpu().numpy() # image in numpy
if pb:
pred = frozen_func(x=tf.constant(imn)).numpy()
elif saved_model:
pred = model(imn, training=False).numpy()
elif tflite:
if int8:
scale, zero_point = input_details[0]['quantization']
imn = (imn / scale + zero_point).astype(
np.uint8) # de-scale
interpreter.set_tensor(input_details[0]['index'], imn)
interpreter.invoke()
pred = interpreter.get_tensor(output_details[0]['index'])
if int8:
scale, zero_point = output_details[0]['quantization']
pred = (pred.astype(np.float32) -
zero_point) * scale # re-scale
pred[..., 0] *= imgsz[1] # x
pred[..., 1] *= imgsz[0] # y
pred[..., 2] *= imgsz[1] # w
pred[..., 3] *= imgsz[0] # h
pred = torch.tensor(pred)
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)
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# Process predictions
for i, det in enumerate(pred): # per image
seen += 1
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(
), dataset.count
else:
p, s, im0, frame = path, '', im0s.copy(), getattr(
dataset, 'frame', 0)
p = Path(p) # to Path
save_path = str(save_dir / p.name) # img.jpg
txt_path = str(save_dir / 'labels' / p.stem) + (
'' if dataset.mode == 'image' else f'_{frame}') # img.txt
s += '%gx%g ' % img.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(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
# 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)
# Print time (inference-only)
print(f'{s}Done. ({t3 - t2:.3f}s)')
# 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 += '.mp4'
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
print(
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 ''
print(f"Results saved to {colorstr('bold', save_dir)}{s}")
if update:
strip_optimizer(weights) # update model (to fix SourceChangeWarning)
gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh
imc = img0.copy() # for save_crop
annotator = Annotator(im0, line_width=line_thickness)
if 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
# Write results
for *xyxy, conf, cls in reversed(det):
# 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}')
label= None
annotator.box_label(xyxy, label, color=colors(c, True))
# Stream results
im0 = annotator.result()
if True:
cv2.imwrite("pred.jpg", im0)
cv2.waitKey(0) # 1 millisecond
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,
fp16=half)
stride, names, pt = model.stride, model.names, model.pt
imgsz = check_img_size(imgsz, s=stride) # check image size
# 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)) # 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 model.fp16 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(f'{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 run(
weights=ROOT / 'yolov5s.pt', # model.pt path(s) 训练的权重
source=ROOT /
'data/images', # file/dir/URL/glob, 0 for webcam 测试数据，图片/视频路径，'0'摄像头，rtsp视频流
imgsz=640, # inference size (pixels) 网络输入图片大小
conf_thres=0.25, # confidence threshold 置信度阈值
iou_thres=0.45, # NMS IOU threshold nms的iou阈值
max_det=1000, # maximum detections per image 分类数
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu 设备
view_img=True, # show results 是否展示预测之后的图片/视频
save_txt=False, # save results to *.txt 是否将预测的框坐标保持txt格式，默认false
# save_conf=False, # save confidences in --save-txt labels 置信度保存
save_crop=False, # save cropped prediction boxes
nosave=False, # do not save images/videos 不保存
classes=None, # filter by class: --class 0, or --class 0 2 3 设置只保留某一部分类别
agnostic_nms=False, # class-agnostic NMS 进行nms是否也去除不同类别之间的框
augment=False, # augmented inference 图像增强
visualize=False, # visualize features 可视化
# update=False, # update all models 若ture，则对所有模型进行strip_optimizer操作，去除pt文件中的优化器等信息，默认false
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
):
source = str(source)
save_img = not nosave and not source.endswith(
'.txt') # save inference images
webcam = source.isnumeric() or source.endswith(
'.txt') or source.lower().startswith(
('rtsp://', 'rtmp://', 'http://', 'https://'))
# 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
# Initialize
set_logging()
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# Load model
w = weights[0] if isinstance(weights, list) else weights
classify, suffix, suffixes = False, Path(w).suffix.lower(), [
'.pt', '.onnx', '.tflite', '.pb', ''
]
check_suffix(w, suffixes) # check weights have acceptable suffix
pt, onnx, tflite, pb, saved_model = (suffix == x
for x in suffixes) # backend booleans
stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
if pt:
model = attempt_load(
weights,
map_location=device) # load FP32 model 加载float32模型，确保图片分辨率能整除32
stride = int(model.stride.max()) # model stride
names = model.module.names if hasattr(
model, 'module') else model.names # get class names
#设置Float16
if half:
model.half() # to FP16
# 设置2次分类
if classify: # second-stage classifier
modelc = load_classifier(name='resnet50', n=2) # initialize
modelc.load_state_dict(
torch.load('resnet50.pt',
map_location=device)['model']).to(device).eval()
# elif onnx:
# check_requirements(('onnx', 'onnxruntime'))
# import onnxruntime
# session = onnxruntime.InferenceSession(w, None)
else: # TensorFlow models
check_requirements(('tensorflow>=2.4.1', ))
import tensorflow as tf
if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
def wrap_frozen_graph(gd, inputs, outputs):
x = tf.compat.v1.wrap_function(
lambda: tf.compat.v1.import_graph_def(gd, name=""),
[]) # wrapped import
return x.prune(
tf.nest.map_structure(x.graph.as_graph_element, inputs),
tf.nest.map_structure(x.graph.as_graph_element, outputs))
graph_def = tf.Graph().as_graph_def()
graph_def.ParseFromString(open(w, 'rb').read())
frozen_func = wrap_frozen_graph(gd=graph_def,
inputs="x:0",
outputs="Identity:0")
elif saved_model:
model = tf.keras.models.load_model(w)
elif tflite:
interpreter = tf.lite.Interpreter(
model_path=w) # load TFLite model
interpreter.allocate_tensors() # allocate
input_details = interpreter.get_input_details() # inputs
output_details = interpreter.get_output_details() # outputs
int8 = input_details[0][
'dtype'] == np.uint8 # is TFLite quantized uint8 model
imgsz = check_img_size(imgsz, s=stride) # check image size
# Dataloader
# 通过不同的输入源来设置不同的数据加载方式
# 摄像头
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
# 图片或视频
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
if pt and device.type != 'cpu':
# 进行一次前向推理，测试程序是否正常
model(
torch.zeros(1, 3, *imgsz).to(device).type_as(
next(model.parameters()))) # run once
dt, seen = [0.0, 0.0, 0.0], 0
'''
path 图片/视频路径
img 进行resize+pad之后的图片，如(3,640,512) 格式(c,h,w)
img0s 原size图片，如(1080,810,3)
cap 当读取图片时为None,读取视频时为视频源
'''
for path, img, im0s, vid_cap in dataset:
t1 = time_sync()
if onnx:
img = img.astype('float32')
else:
img = torch.from_numpy(img).to(device)
# 图片也设置为Float16或者32
img = img.half() if half else img.float() # uint8 to fp16/32
img = img / 255.0 # 0 - 255 to 0.0 - 1.0
# 没有batch_size时，在最前面添加一个轴
if len(img.shape) == 3:
img = img[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
if pt:
visualize = increment_path(save_dir / Path(path).stem,
mkdir=True) if visualize else False
'''
前向传播，返回pred的shape是(1,num_boxes,5+num_class)
h,w为传入网络图片的高和宽，注意dataset在检测时使用了矩形推理，所以h不一定等于w
num_boxes = (h/32*w/32+h/16*w/16+h/8*w/8)*3
例如：图片大小720，1280 -> 15120个boxes = (20*12 + 40*24 + 80*48 = 5040)*3
pred[...,0:4]为预测框坐标；预测框坐标为xywh
pred[...,4]为objectness置信度
pred[...,5:-1]为分类结果
'''
pred = model(img, augment=augment, visualize=visualize)[0]
# elif onnx:
# pred = torch.tensor(session.run([session.get_outputs()[0].name], {session.get_inputs()[0].name: img}))
else: # tensorflow model (tflite, pb, saved_model)
imn = img.permute(0, 2, 3, 1).cpu().numpy() # image in numpy
if pb:
pred = frozen_func(x=tf.constant(imn)).numpy()
elif saved_model:
pred = model(imn, training=False).numpy()
elif tflite:
if int8:
scale, zero_point = input_details[0]['quantization']
imn = (imn / scale + zero_point).astype(
np.uint8) # de-scale
interpreter.set_tensor(input_details[0]['index'], imn)
interpreter.invoke()
pred = interpreter.get_tensor(output_details[0]['index'])
if int8:
scale, zero_point = output_details[0]['quantization']
pred = (pred.astype(np.float32) -
zero_point) * scale # re-scale
pred[..., 0] *= imgsz[1] # x
pred[..., 1] *= imgsz[0] # y
pred[..., 2] *= imgsz[1] # w
pred[..., 3] *= imgsz[0] # h
pred = torch.tensor(pred)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
'''
pred:前向传播的输出
conf_thres:置信度阈值
iou_thres:iou阈值
classes：是否只保留特定的类别
agnostic_nmsL进行nms是否也去除不同类别之间的框
经过nms后预测框格式，xywh->xyxy(左上角右上角)
pred是一个列表list[torch.tensor],长度为nms后目标框个数
每一个torch.tensor的shape为(num_boxes,6),内容为box(4个值)+cunf+cls
'''
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)
# 添加二级分类，默认false
if classify:
pred = apply_classifier(pred, modelc, img, im0s)
# Process predictions
# 对每一张图片处理
for i, det in enumerate(pred): # per image
seen += 1
# 如果输入源是webcam，则batch_size不为1，取出dataset中的一张图片
if webcam: # batch_size >= 1
p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(
), dataset.count
else:
p, s, im0, frame = path, '', im0s.copy(), getattr(
dataset, 'frame', 0)
p = Path(p) # to Path
# 设置保存图片或视频的路径
# p是原图片路径
save_path = str(save_dir / p.name) # img.jpg
#设置保存框坐标txt文件的路径
txt_path = str(save_dir / 'labels' / p.stem) + (
'' if dataset.mode == 'image' else f'_{frame}') # img.txt
# 设置打印信息（图片宽高），s如'640*512'
s += '%gx%g ' % img.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
# 调整预测框坐标，基于resize+pad的图片坐标->基于原size图片坐标
# 此时坐标格式为xyxy
det[:, :4] = scale_coords(img.shape[2:], det[:, :4],
im0.shape).round()
# Print results
# 打印检测到的类别数量
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
# 保存预测结果
for *xyxy, conf, cls in reversed(det):
# if save_txt: # Write to file
# # 将xyxy格式转为xywh格式，并除上我w，h作归一化，转化为列表再保存
# 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)
# Print time (inference-only)
# print(f'{pred[0][0][0].tolist()} {pred[0][0][1].tolist()} {s}Done. ({t3 - t2:.3f}s)')
# Stream results
im0 = annotator.result()
# xxx = (pred[0][0][0].tolist()+pred[0][0][2].tolist())/2
# yyy = (pred[0][0][1].tolist()+pred[0][0][3].tolist())/2
if view_img:
# + / 2 +
cv2.imshow(str(p), im0)
cv2.moveWindow(str(p), 0, 0)
# pyautogui.moveTo(xxx, yyy)
cv2.waitKey(1000) # 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 += '.mp4'
# 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
print(
f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}'
% t)
def run(
weights=ROOT / 'yolov5s.pt', # model.pt path(s) 训练的权重
imgsz=[640, 640], # inference size (pixels) 网络输入图片大小
conf_thres=0.25, # confidence threshold 置信度阈值
iou_thres=0.45, # NMS IOU threshold nms的iou阈值
max_det=1000, # maximum detections per image 分类数
device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu 设备
view_img=True, # show results 是否展示预测之后的图片/视频
classes=None, # filter by class: --class 0, or --class 0 2 3 设置只保留某一部分类别
agnostic_nms=False, # class-agnostic NMS 进行nms是否也去除不同类别之间的框
augment=False, # augmented inference 图像增强
visualize=False, # visualize features 可视化
line_thickness=3, # bounding box thickness (pixels)
hide_labels=False, # hide labels
hide_conf=False, # hide confidences
half=False, # use FP16 half-precision inference
):
# Initialize
set_logging()
device = select_device(device)
half &= device.type != 'cpu' # half precision only supported on CUDA
# Load model
w = weights[0] if isinstance(weights, list) else weights
classify, suffix, suffixes = False, Path(w).suffix.lower(), [
'.pt', '.onnx', '.tflite', '.pb', ''
]
check_suffix(w, suffixes) # check weights have acceptable suffix
pt, onnx, tflite, pb, saved_model = (suffix == x
for x in suffixes) # backend booleans
stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
if pt:
model = attempt_load(
weights,
map_location=device) # load FP32 model 加载float32模型，确保图片分辨率能整除32
stride = int(model.stride.max()) # model stride
names = model.module.names if hasattr(
model, 'module') else model.names # get class names
#设置Float16
if half:
model.half() # to FP16
# 设置2次分类
if classify: # second-stage classifier
modelc = load_classifier(name='resnet50', n=2) # initialize
modelc.load_state_dict(
torch.load('resnet50.pt',
map_location=device)['model']).to(device).eval()
else: # TensorFlow models
check_requirements(('tensorflow>=2.4.1', ))
import tensorflow as tf
if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
def wrap_frozen_graph(gd, inputs, outputs):
x = tf.compat.v1.wrap_function(
lambda: tf.compat.v1.import_graph_def(gd, name=""),
[]) # wrapped import
return x.prune(
tf.nest.map_structure(x.graph.as_graph_element, inputs),
tf.nest.map_structure(x.graph.as_graph_element, outputs))
graph_def = tf.Graph().as_graph_def()
graph_def.ParseFromString(open(w, 'rb').read())
frozen_func = wrap_frozen_graph(gd=graph_def,
inputs="x:0",
outputs="Identity:0")
elif saved_model:
model = tf.keras.models.load_model(w)
elif tflite:
interpreter = tf.lite.Interpreter(
model_path=w) # load TFLite model
interpreter.allocate_tensors() # allocate
input_details = interpreter.get_input_details() # inputs
output_details = interpreter.get_output_details() # outputs
int8 = input_details[0][
'dtype'] == np.uint8 # is TFLite quantized uint8 model
imgsz = check_img_size(imgsz, s=stride) # check image size
# Dataloader
# 图片或视频
tmp = False
tmp2 = False
mon = {'top': 0, 'left': 0, 'width': 960, 'height': 960}
while True:
im = np.array(mss().grab(mon))
screen = cv2.cvtColor(im, cv2.COLOR_BGRA2BGR)
dataset = LoadImages(screen, img_size=imgsz, stride=stride, auto=pt)
dt, seen = [0.0, 0.0, 0.0], 0
'''
path 图片/视频路径
img 进行resize+pad之后的图片，如(3,640,512) 格式(c,h,w)
img0s 原size图片，如(1080,810,3)
cap 当读取图片时为None,读取视频时为视频源
'''
for img, im0s, vid_cap in dataset:
t1 = time_sync()
if onnx:
img = img.astype('float32')
else:
img = torch.from_numpy(img).to(device)
# print(img)
# 图片也设置为Float16或者32
img = img.half() if half else img.float() # uint8 to fp16/32
img = img / 255.0 # 0 - 255 to 0.0 - 1.0
# 没有batch_size时，在最前面添加一个轴
if len(img.shape) == 3:
img = img[None] # expand for batch dim
t2 = time_sync()
dt[0] += t2 - t1
# Inference
if pt:
'''
前向传播，返回pred的shape是(1,num_boxes,5+num_class)
h,w为传入网络图片的高和宽，注意dataset在检测时使用了矩形推理，所以h不一定等于w
num_boxes = (h/32*w/32+h/16*w/16+h/8*w/8)*3
例如：图片大小720，1280 -> 15120个boxes = (20*12 + 40*24 + 80*48 = 5040)*3
pred[...,0:4]为预测框坐标；预测框坐标为xywh
pred[...,4]为objectness置信度
pred[...,5:-1]为分类结果
'''
pred = model(img, augment=augment, visualize=visualize)[0]
else: # tensorflow model (tflite, pb, saved_model)
imn = img.permute(0, 2, 3, 1).cpu().numpy() # image in numpy
if pb:
pred = frozen_func(x=tf.constant(imn)).numpy()
elif saved_model:
pred = model(imn, training=False).numpy()
elif tflite:
if int8:
scale, zero_point = input_details[0]['quantization']
imn = (imn / scale + zero_point).astype(
np.uint8) # de-scale
interpreter.set_tensor(input_details[0]['index'], imn)
interpreter.invoke()
pred = interpreter.get_tensor(output_details[0]['index'])
if int8:
scale, zero_point = output_details[0]['quantization']
pred = (pred.astype(np.float32) -
zero_point) * scale # re-scale
pred[..., 0] *= imgsz[1] # x
pred[..., 1] *= imgsz[0] # y
pred[..., 2] *= imgsz[1] # w
pred[..., 3] *= imgsz[0] # h
pred = torch.tensor(pred)
t3 = time_sync()
dt[1] += t3 - t2
# NMS
'''
pred:前向传播的输出
conf_thres:置信度阈值
iou_thres:iou阈值
classes：是否只保留特定的类别
agnostic_nmsL进行nms是否也去除不同类别之间的框
经过nms后预测框格式，xywh->xyxy(左上角右上角)
pred是一个列表list[torch.tensor],长度为nms后目标框个数
每一个torch.tensor的shape为(num_boxes,6),内容为box(4个值)+cunf+cls
'''
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)
# 添加二级分类，默认false
# if classify:
# pred = apply_classifier(pred, modelc, img, im0s)
# Process predictions
# 对每一张图片处理
for i, det in enumerate(pred): # per image
seen += 1
s, im0 = '', im0s.copy()
# 设置打印信息（图片宽高），s如'640*512'
s += '%gx%g ' % img.shape[2:] # print string
annotator = Annotator(im0,
line_width=line_thickness,
example=str(names))
if len(det):
# Rescale boxes from img_size to im0 size
# 调整预测框坐标，基于resize+pad的图片坐标->基于原size图片坐标
# 此时坐标格式为xyxy
det[:, :4] = scale_coords(img.shape[2:], det[:, :4],
im0.shape).round()
# Print results
# 打印检测到的类别数量
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
# 保存预测结果
for *xyxy, conf, cls in reversed(det):
if 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))
# Stream results
im0 = annotator.result()
cv2.imshow('a crop of the screen', im0)
cv2.moveWindow('a crop of the screen', 960, 0)
if cv2.waitKey(1) & 0xff == ord('q'):
tmp = True
break
if tmp:
tmp2 = True
break
if tmp2:
break