Automatic Chinese fonts plotting (#4951)

* Automatic Chinese fonts plotting

* Default PIL=False

detect.py

@@ -23,7 +23,7 @@ if str(ROOT) not in sys.path:
 from models.experimental import attempt_load
 from utils.datasets import LoadImages, LoadStreams
 from utils.general import apply_classifier, check_img_size, check_imshow, check_requirements, check_suffix, colorstr, \
-    increment_path, is_ascii, non_max_suppression, print_args, save_one_box, scale_coords, set_logging, \
+    increment_path, non_max_suppression, print_args, save_one_box, scale_coords, set_logging, \
     strip_optimizer, xyxy2xywh
 from utils.plots import Annotator, colors
 from utils.torch_utils import load_classifier, select_device, time_sync
@@ -108,7 +108,6 @@ def run(weights='yolov5s.pt',  # model.pt path(s)
             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:
@@ -190,7 +189,7 @@ def run(weights='yolov5s.pt',  # model.pt path(s)
             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)
+            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()

models/common.py

@@ -18,7 +18,7 @@ from PIL import Image
 from torch.cuda import amp
 
 from utils.datasets import exif_transpose, letterbox
-from utils.general import colorstr, increment_path, is_ascii, make_divisible, non_max_suppression, save_one_box, \
+from utils.general import colorstr, increment_path, make_divisible, non_max_suppression, save_one_box, \
     scale_coords, xyxy2xywh
 from utils.plots import Annotator, colors
 from utils.torch_utils import time_sync
@@ -356,7 +356,6 @@ class Detections:
         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
@@ -369,13 +368,13 @@ class Detections:
     def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
         crops = []
         for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
-            str = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '
+            s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '  # string
             if pred.shape[0]:
                 for c in pred[:, -1].unique():
                     n = (pred[:, -1] == c).sum()  # detections per class
-                    str += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                    s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
                 if show or save or render or crop:
-                    annotator = Annotator(im, pil=not self.ascii)
+                    annotator = Annotator(im, example=str(self.names))
                     for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
                         label = f'{self.names[int(cls)]} {conf:.2f}'
                         if crop:
@@ -386,11 +385,11 @@ class Detections:
                             annotator.box_label(box, label, color=colors(cls))
                     im = annotator.im
             else:
-                str += '(no detections)'
+                s += '(no detections)'
 
             im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im  # from np
             if pprint:
-                LOGGER.info(str.rstrip(', '))
+                LOGGER.info(s.rstrip(', '))
             if show:
                 im.show(self.files[i])  # show
             if save:

utils/general.py

@@ -161,10 +161,9 @@ def is_pip():
     return 'site-packages' in Path(__file__).resolve().parts
 
 
-def is_ascii(s=''):
+def is_chinese(s='人工智能'):
-    # Is string composed of all ASCII (no UTF) characters?
+    # Is string composed of any Chinese characters?
-    s = str(s)  # convert list, tuple, None, etc. to str
+    return re.search('[\u4e00-\u9fff]', s)
-    return len(s.encode().decode('ascii', 'ignore')) == len(s)
 
 
 def emojis(str=''):

utils/plots.py

@@ -17,7 +17,7 @@ import seaborn as sn
 import torch
 from PIL import Image, ImageDraw, ImageFont
 
-from utils.general import user_config_dir, is_ascii, xywh2xyxy, xyxy2xywh
+from utils.general import user_config_dir, is_chinese, xywh2xyxy, xyxy2xywh
 from utils.metrics import fitness
 
 # Settings
@@ -66,20 +66,21 @@ class Annotator:
         check_font()  # download TTF if necessary
 
     # 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=True):
+    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.'
-        self.pil = pil
+        self.pil = pil or not example.isascii() or is_chinese(example)
         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_font(font, size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12))
+            self.font = check_font(font='Arial.Unicode.ttf' if is_chinese(example) 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 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):
+        if self.pil or not label.isascii():
             self.draw.rectangle(box, width=self.lw, outline=color)  # box
             if label:
                 w, h = self.font.getsize(label)  # text width, height
@@ -177,7 +178,7 @@ def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max
 
     # Annotate
     fs = int((h + w) * ns * 0.01)  # font size
-    annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs)
+    annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True)
     for i in range(i + 1):
         x, y = int(w * (i // ns)), int(h * (i % ns))  # block origin
         annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2)  # borders