Update app.py

app.py

@@ -252,7 +252,7 @@ def predict(image):
     # Reshape the image to match the model's input shape
     image = image.reshape(3, 640, 640)
 
-    # Normalize the image
+    #  Normalize output image using ImageNet-style normalization
     mean = [0.485, 0.456, 0.406]
     std = [0.229, 0.224, 0.225]
     mean = np.expand_dims(mean, axis=(1,2))
@@ -277,15 +277,15 @@ def predict(image):
     # Postprocess output image
     
     annotated_img = output[0]
-
-    print("Output[0] image shape:", annotated_img.shape)
     
     # annotated_img = (output[0] / 255.0 - mean)/std
     # annotated_img = classes[output[0][0].argmax(0)]
-    print("Annotated image type:", type(annotated_img))
-    print("Annotated image:", annotated_img)
-    print("Min value of image:", np.min(annotated_img))
-    print("Max value of image:", np.max(annotated_img))
+    
+    print("Annotated image type before normalization:", type(annotated_img))
+    print("annotated_img shape before normalization:", annotated_img.shape)
+    # print("Annotated image before normalization:", annotated_img)
+    print("Min value of image before normalization:", np.min(annotated_img))
+    print("Max value of image before normalization:", np.max(annotated_img))
 
     # # Normalize output image using ImageNet-style normalization (again)
     # annotated_img = (annotated_img / 255.0 - mean)/std
@@ -297,7 +297,8 @@ def predict(image):
 
     print("Min value of image after normalization:", np.min(annotated_img))
     print("Max value of image after normalization:", np.max(annotated_img))
-    print("Type of annotated_img after normalization:", type(annotated_img))
+    print("annotated_img type after normalization:", type(annotated_img))
+    print("annotated_img shape after normalization:", annotated_img.shape)
 
     # Convert to PIL Image
     # annotated_img = Image.fromarray(annotated_img)