def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
# Add one xyxy box to image with label
if self.pil or not is_ascii(label):
self.draw.rectangle(box, width=self.lw, outline=color) # box
if label:
w, h = self.font.getsize(label) # text width, height
outside = box[1] - h >= 0 # label fits outside box
self.draw.rectangle(
(box[0], box[1] - h if outside else box[1], box[0] + w + 1,
box[1] + 1 if outside else box[1] + h + 1),
fill=color,
)
# self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0
self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font)
else: # cv2
p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
if label:
tf = max(self.lw - 1, 1) # font thickness
w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height
outside = p1[1] - h - 3 >= 0 # label fits outside box
p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled
cv2.putText(self.im,
label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2),
0,
self.lw / 3,
txt_color,
thickness=tf,
lineType=cv2.LINE_AA)
def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'):
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.'
non_ascii = not is_ascii(example) # non-latin labels, i.e. asian, arabic, cyrillic
self.pil = pil or non_ascii
if self.pil: # use PIL
self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
self.draw = ImageDraw.Draw(self.im)
self.font = check_pil_font(font='Arial.Unicode.ttf' if non_ascii else font,
size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12))
else: # use cv2
self.im = im
self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width
def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
super().__init__()
d = pred[0].device # device
gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs] # normalizations
self.imgs = imgs # list of images as numpy arrays
self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
self.names = names # class names
self.ascii = is_ascii(names) # names are ascii (use PIL for UTF-8)
self.files = files # image filenames
self.xyxy = pred # xyxy pixels
self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
self.n = len(self.pred) # number of images (batch size)
self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
self.s = shape # inference BCHW shape
def plot_one_box(box,
im,
color=(128, 128, 128),
txt_color=(255, 255, 255),
label=None,
line_width=3,
use_pil=False):
# Plots one xyxy box on image im with label
assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to plot_on_box() input image.'
lw = line_width or max(int(min(im.size) / 200), 2) # line width
if use_pil or not is_ascii(label): # use PIL
im = Image.fromarray(im)
draw = ImageDraw.Draw(im)
draw.rectangle(box, width=lw + 1, outline=color) # plot
if label:
font = ImageFont.truetype("Arial.ttf",
size=max(round(max(im.size) / 40), 12))
txt_width, txt_height = font.getsize(label)
draw.rectangle(
[box[0], box[1] - txt_height + 4, box[0] + txt_width, box[1]],
fill=color)
draw.text((box[0], box[1] - txt_height + 1),
label,
fill=txt_color,
font=font)
return np.asarray(im)
else: # use OpenCV
c1, c2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
cv2.rectangle(im, c1, c2, color, thickness=lw, lineType=cv2.LINE_AA)
if label:
tf = max(lw - 1, 1) # font thickness
txt_width, txt_height = cv2.getTextSize(label,
0,
fontScale=lw / 3,
thickness=tf)[0]
c2 = c1[0] + txt_width, c1[1] - txt_height - 3
cv2.rectangle(im, c1, c2, color, -1, cv2.LINE_AA) # filled
cv2.putText(im,
label, (c1[0], c1[1] - 2),
0,
lw / 3,
txt_color,
thickness=tf,
lineType=cv2.LINE_AA)
return im
def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
# Add one xyxy box to image with label
if self.pil or not is_ascii(label):
self.draw.rectangle(box, width=self.lw, outline=color) # box
if label:
w = self.font.getsize(label)[0] # text width
self.draw.rectangle([box[0], box[1] - self.fh, box[0] + w + 1, box[1] + 1], fill=color)
self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls')
else: # cv2
c1, c2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
cv2.rectangle(self.im, c1, c2, color, thickness=self.lw, lineType=cv2.LINE_AA)
if label:
tf = max(self.lw - 1, 1) # font thickness
w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0]
c2 = c1[0] + w, c1[1] - h - 3
cv2.rectangle(self.im, c1, c2, color, -1, cv2.LINE_AA) # filled
cv2.putText(self.im, label, (c1[0], c1[1] - 2), 0, self.lw / 3, txt_color, thickness=tf,
lineType=cv2.LINE_AA)
def run(weights='yolov5s.pt', # model.pt path(s)
source='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='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
):
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
stride = int(model.stride.max()) # model stride
names = model.module.names if hasattr(model, 'module') else model.names # get class names
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:
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
ascii = is_ascii(names) # names are ascii (use PIL for UTF-8)
# 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]
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 = 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, pil=not ascii)
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)
