Update app.py

app.py

@@ -3,37 +3,65 @@ import torch
 import torchvision.transforms as transforms
 from PIL import Image
 
-# Load the trained model
-model_path = "cifar_net.pth"
+file_urls = [
+    "https://www.bing.com/images/search?view=detailV2&ccid=YaFiK%2bN6&id=D84622E2396A39F168D279F32AC31F05096187AB&thid=OIP.YaFiK-N6iDdJR6B6DMBHpgHaFj&mediaurl=https%3a%2f%2fwww.practicalcaravan.com%2fwp-content%2fuploads%2f2016%2f03%2f5907569-scaled.jpg&exph=1921&expw=2560&q=audi+a4+car+image&simid=608053806389945942&FORM=IRPRST&ck=7DDB4BC7AA27F8E3EDA4433E669D3CC4&selectedIndex=6&ajaxhist=0&ajaxserp=0","https://www.bing.com/images/search?view=detailV2&ccid=CHONQxwQ&id=B8BCD1A5420658017C772CF149AFB7D24F2F8322&thid=OIP.CHONQxwQrclsFp-VXh4aOQHaFD&mediaurl=https%3a%2f%2fs3-eu-west-1.amazonaws.com%2feurekar-v2%2fuploads%2fimages%2foriginal%2fa4salfront.jpg&exph=1025&expw=1500&q=audi+a4+car+image&simid=608024308599848180&FORM=IRPRST&ck=3A2EA226332024ECB13B2F27682C15CA&selectedIndex=3&ajaxhist=0&ajaxserp=0"
+]
+ 
+def download_file(url, save_name):
+    url = url
+    if not os.path.exists(save_name):
+        file = requests.get(url)
+        open(save_name, 'wb').write(file.content)
+ 
+for i, url in enumerate(file_urls):
+    if 'mp4' in file_urls[i]:
+        download_file(
+            file_urls[i],
+            f"video.mp4"
+        )
+    else:
+        download_file(
+            file_urls[i],
+            f"image_{i}.jpg"
+        )
+        
+model = 'cifar_net.pth'
+path  = [['image_0.jpg'], ['image_1.jpg']]
+video_path = [['video.mp4']]
 
-state_dict = torch.load(model_path)
 
-model = torch.nn.Module()
-model.load_state_dict(state_dict)
-model.eval()
+def show_preds_image(image_path):
+    image = cv2.imread(image_path)
+    outputs = model.predict(source=image_path)
+    results = outputs[0].cpu().numpy()
+    for i, det in enumerate(results.boxes.xyxy):
+        cv2.rectangle(
+            image,
+            (int(det[0]), int(det[1])),
+            (int(det[2]), int(det[3])),
+            color=(0, 0, 255),
+            thickness=2,
+            lineType=cv2.LINE_AA
+        )
+    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
+ 
+inputs_image = [
+    gr.components.Image(type="filepath", label="Input Image"),
+]
+outputs_image = [
+    gr.components.Image(type="numpy", label="Output Image"),
+]
+interface_image = gr.Interface(
+    fn=show_preds_image,
+    inputs=inputs_image,
+    outputs=outputs_image,
+    title="Car detector",
+    examples=path,
+    cache_examples=False,
+)
 
-# Prepare the image for prediction
-image_path = 'download.jpg'
-image = Image.open(image_path)
 
-# Transform the image to match CIFAR-10 format
-transform = transforms.Compose([
-    transforms.Resize((32, 32)),
-    transforms.ToTensor(),
-    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))  # Normalize with CIFAR-10 mean and std
-])
-input_image = transform(image).unsqueeze(0)
-
-# Make predictions
-with torch.no_grad():
-    outputs = model(input_image)
-
-# Retrieve the predicted class label
-_, predicted = torch.max(outputs, 1)
-class_index = predicted.item()
-
-# Load the CIFAR-10 class labels
-classes = ['airplane', 'automobile', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck']
-
-# Print the predicted class label
-print('Predicted class label:', classes[class_index])
+gr.TabbedInterface(
+    [interface_image],
+    tab_names=['Image inference']
+).queue().launch()