Testing ViT

app.py

@@ -7,15 +7,15 @@ from transformers import CLIPProcessor, CLIPModel
 model = CLIPModel.from_pretrained("openai/clip-vit-base-patch32")
 processor = CLIPProcessor.from_pretrained("openai/clip-vit-base-patch32")
 
-# load model
-model = yolov5.load('keremberke/yolov5m-license-plate')
+# # load model
+# model = yolov5.load('keremberke/yolov5m-license-plate')
 
-# set model parameters
-model.conf = 0.5  # NMS confidence threshold
-model.iou = 0.25  # NMS IoU threshold
-model.agnostic = False  # NMS class-agnostic
-model.multi_label = False  # NMS multiple labels per box
-model.max_det = 1000  # maximum number of detections per image
+# # set model parameters
+# model.conf = 0.5  # NMS confidence threshold
+# model.iou = 0.25  # NMS IoU threshold
+# model.agnostic = False  # NMS class-agnostic
+# model.multi_label = False  # NMS multiple labels per box
+# model.max_det = 1000  # maximum number of detections per image
 
 def license_plate_detect(img):
     results = model(img, size=640)
@@ -36,10 +36,13 @@ def read_license_number(img):
 
 
 def zero_shot_classification(image, labels):
+    print(type(image))
     inputs = processor(text=labels,
                        images=image,
                        return_tensors="pt",
                        padding=True)
+    print(type(inputs))
+    print(inputs)
     outputs = model(**inputs)
     logits_per_image = outputs.logits_per_image # this is the image-text similarity score
     return logits_per_image.softmax(dim=1) # we can take the softmax to get the label probabilities
@@ -68,7 +71,9 @@ def check_solarplant_broken(image):
 
 
 def greet(img):
-    lns = read_license_number(img)
+    print(type(img))
+    # lns = read_license_number(img)
+    lns = [1,2,3]
     if len(lns):
         # return (seg,
         return ("車牌： " + '; '.join(lns) + "\n\n" \