Update app.py

app.py

@@ -1,5 +1,6 @@
 
 import os
+import numpy as np
 import gradio as gr
 import torch
 from torchvision import models, transforms
@@ -61,15 +62,14 @@ n_labels = len(LABELS)
 MEAN = [0.485, 0.456, 0.406]
 STD = [0.229, 0.224, 0.225]
 
-carTransforms = transforms.Compose([transforms.Resize(224)])
-                                    #transforms.ToTensor(),
-                                    #transforms.Normalize(mean=MEAN, std=STD)])
+carTransforms = transforms.Compose([transforms.Resize(224),
+                                    transforms.ToTensor(),
+                                    transforms.Normalize(mean=MEAN, std=STD)])
 
 def classifyCar(im):
   #im = Image.fromarray(im.astype('uint8'), 'RGB')
   try:
     im = cv2.imread(im)
-    im = carTransforms(im)
   except:
     return im, {"error0": im.shape}
   try:
@@ -88,12 +88,12 @@ def classifyCar(im):
   try:
     im2 = carTransforms(im).unsqueeze(0)  # transform and add batch dimension
   except:
-    return im, {"error4": 0.5}
+    return Image.fromarray(np.uint8(out.get_image())).convert('RGB'), {"error4": 0.5}
   try:
     with torch.no_grad():
       scores = torch.nn.functional.softmax(DesignModernityModel(im2)[0])
   except:
-    return im, {"error5": 0.5}
+    return Image.fromarray(np.uint8(out.get_image())).convert('RGB'), {"error5": 0.5}
   return Image.fromarray(np.uint8(out.get_image())).convert('RGB'), {LABELS[i]: float(scores[i]) for i in range(n_labels)}
 
 #examples = [[example_img.jpg], [example_img2.jpg]]  # must be uploaded in repo