目录
Annotator
yolo中有一个现成的类。
class Annotator:
# YOLOv5 Annotator for train/val mosaics and jpgs and detect/hub inference annotations
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
# box [tensor, tensor, tensor, tensor]
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 (WARNING: deprecated) in 9.2.0
# _, _, w, h = self.font.getbbox(label) # text width, height (New)
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
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 masks(self, masks, colors, im_gpu, alpha=0.5, retina_masks=False):
"""Plot masks at once.
Args:
masks (tensor): predicted masks on cuda, shape: [n, h, w]
colors (List[List[Int]]): colors for predicted masks, [[r, g, b] * n]
im_gpu (tensor): img is in cuda, shape: [3, h, w], range: [0, 1]
alpha (float): mask transparency: 0.0 fully transparent, 1.0 opaque
"""
if self.pil:
# convert to numpy first
self.im = np.asarray(self.im).copy()
if len(masks) == 0:
self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
colors = torch.tensor(colors, device=im_gpu.device, dtype=torch.float32) / 255.0
colors = colors[:, None, None] # shape(n,1,1,3)
masks = masks.unsqueeze(3) # shape(n,h,w,1)
masks_color = masks * (colors * alpha) # shape(n,h,w,3)
inv_alph_masks = (1 - masks * alpha).cumprod(0) # shape(n,h,w,1)
mcs = (masks_color * inv_alph_masks).sum(0) * 2 # mask color summand shape(n,h,w,3)
im_gpu = im_gpu.flip(dims=[0]) # flip channel
im_gpu = im_gpu.permute(1, 2, 0).contiguous() # shape(h,w,3)
im_gpu = im_gpu * inv_alph_masks[-1] + mcs
im_mask = (im_gpu * 255).byte().cpu().numpy()
self.im[:] = im_mask if retina_masks else scale_image(im_gpu.shape, im_mask, self.im.shape)
if self.pil:
# convert im back to PIL and update draw
self.fromarray(self.im)
def rectangle(self, xy, fill=None, outline=None, width=1):
# Add rectangle to image (PIL-only)
self.draw.rectangle(xy, fill, outline, width)
def text(self, xy, text, txt_color=(255, 255, 255), anchor='top'):
# Add text to image (PIL-only)
if anchor == 'bottom': # start y from font bottom
w, h = self.font.getsize(text) # text width, height
xy[1] += 1 - h
self.draw.text(xy, text, fill=txt_color, font=self.font)
def fromarray(self, im):
# Update self.im from a numpy array
self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
self.draw = ImageDraw.Draw(self.im)
def result(self):
# Return annotated image as array
return np.asarray(self.im)
初始化:
参数:
im: 需要绘制的图片(h, w, c)
line_width: 线的宽度
font_size:字体,不填将下载yolo字体
example: 如果需要显示汉字则 输入一个汉字, 默认英文字符
box_label
参数:
box:[x1, y1, x2, y2]
label: str 标签名
color: (128, 128, 128) box颜色值
txt_color=(255, 255, 255) 文本颜色值
rectangle
绘制矩形只使用plt
text
绘制文字
参数:
xy: 绘制文字的位置
text: 文本
result
返回绘制完成的结果
例子
if __name__ == '__main__':
im = cv2.imread('F:\PycharmProjects\yolov5\data\images\\bus.jpg')
a = Annotator(im, example='是')
# l = [torch.tensor(0), torch.tensor(256), torch.tensor(456), torch.tensor(789)]
l = [0, 256, 456, 789]
a.box_label(l, '是')
xy = [77, 88]
a.rectangle([78, 777, 789, 456])
a.text(xy, '是是')
im = a.result()
cv2.imshow('ss', im)
cv2.waitKey(0)