Auto-UTF handling (ultralytics#4594)

detect.py

@@ -21,9 +21,9 @@
 
 from models.experimental import attempt_load
 from utils.datasets import LoadStreams, LoadImages
-from utils.general import check_img_size, check_requirements, check_imshow, colorstr, non_max_suppression, \
+from utils.general import check_img_size, check_requirements, check_imshow, colorstr, is_ascii, non_max_suppression, \
     apply_classifier, scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path, save_one_box
-from utils.plots import colors, Annotator
+from utils.plots import Annotator, colors
 from utils.torch_utils import select_device, load_classifier, time_sync
 
 
@@ -105,6 +105,7 @@ def wrap_frozen_graph(gd, inputs, outputs):
             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:
@@ -181,7 +182,7 @@ def wrap_frozen_graph(gd, inputs, outputs):
             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=False)
+            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()

models/common.py

@@ -18,9 +18,9 @@
 from torch.cuda import amp
 
 from utils.datasets import exif_transpose, letterbox
-from utils.general import colorstr, non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh, \
-    save_one_box
-from utils.plots import colors, Annotator
+from utils.general import colorstr, increment_path, is_ascii, make_divisible, non_max_suppression, save_one_box, \
+    scale_coords, xyxy2xywh
+from utils.plots import Annotator, colors
 from utils.torch_utils import time_sync
 
 LOGGER = logging.getLogger(__name__)
@@ -354,6 +354,7 @@ def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
         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
@@ -371,7 +372,7 @@ def display(self, pprint=False, show=False, save=False, crop=False, render=False
                     n = (pred[:, -1] == c).sum()  # detections per class
                     str += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
                 if show or save or render or crop:
-                    annotator = Annotator(im, pil=False)
+                    annotator = Annotator(im, pil=not self.ascii)
                     for *box, conf, cls in reversed(pred):  # xyxy, confidence, class
                         label = f'{self.names[int(cls)]} {conf:.2f}'
                         if crop:

utils/general.py

@@ -124,7 +124,7 @@ def is_pip():
 
 def is_ascii(s=''):
     # Is string composed of all ASCII (no UTF) characters?
-    s = str(s)  # convert to str() in case of None, etc.
+    s = str(s)  # convert list, tuple, None, etc. to str
     return len(s.encode().decode('ascii', 'ignore')) == len(s)