Update app.py

app.py

@@ -1,29 +1,64 @@
+import torch
+from PIL import Image
+from torchvision import transforms
 import gradio as gr
-from transformers import ViTFeatureExtractor, ViTForImageClassification
+import os
 
-import torch
+os.system("wget https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt")
 
 
+import torch
+model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet18', pretrained=True)
+# or any of these variants
+# model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet34', pretrained=True)
+# model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet50', pretrained=True)
+# model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet101', pretrained=True)
+# model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet152', pretrained=True)
+model.eval()
+
+# Download an example image from the pytorch website
+torch.hub.download_url_to_file("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
 
-feature_extractor = ViTFeatureExtractor.from_pretrained("google/vit-base-patch16-224")
+def inference(input_image):
+    preprocess = transforms.Compose([
+        transforms.Resize(256),
+        transforms.CenterCrop(224),
+        transforms.ToTensor(),
+        transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+    ])
+    input_tensor = preprocess(input_image)
+    input_batch = input_tensor.unsqueeze(0) # create a mini-batch as expected by the model
 
-model = ViTForImageClassification.from_pretrained("google/vit-base-patch16-224")
+    # move the input and model to GPU for speed if available
+    if torch.cuda.is_available():
+        input_batch = input_batch.to('cuda')
+        model.to('cuda')
 
-inputs = feature_extractor(image, return_tensors="pt")
+    with torch.no_grad():
+        output = model(input_batch)
+    # The output has unnormalized scores. To get probabilities, you can run a softmax on it.
+    probabilities = torch.nn.functional.softmax(output[0], dim=0)
 
-with torch.no_grad():
+    # Read the categories
+    with open("imagenet_classes.txt", "r") as f:
+        categories = [s.strip() for s in f.readlines()]
+    # Show top categories per image
+    top5_prob, top5_catid = torch.topk(probabilities, 5)
+    result = {}
+    for i in range(top5_prob.size(0)):
+        result[categories[top5_catid[i]]] = top5_prob[i].item()
+    return result
 
-    logits = model(**inputs).logits
+inputs = gr.inputs.Image(type='pil')
+outputs = gr.outputs.Label(type="confidences",num_top_classes=5)
 
-# model predicts one of the 1000 ImageNet classes
+title = "ResNet"
+description = "Gradio demo for ResNet, Deep residual networks pre-trained on ImageNet. To use it, simply upload your image, or click one of the examples to load them. Read more at the links below."
 
-predicted_label = logits.argmax(-1).item()
+article = "<p style='text-align: center'><a href='https://arxiv.org/abs/1512.03385' target='_blank'>Deep Residual Learning for Image Recognition</a> | <a href='https://github.com/pytorch/vision/blob/main/torchvision/models/resnet.py' target='_blank'>Github Repo</a></p>"
 
-print(model.config.id2label[predicted_label])
+examples = [
+            ['dog.jpg']
+]
 
-gr.Interface.load(
-             inference,
-             theme="default",
-             examples=[["alligator.jpg"], ["laptop.jpg"]],
-             css=".footer{display:none !important}",
-             title=None).launch()
+gr.Interface(inference, inputs, outputs, title=title, description=description, article=article, examples=examples, analytics_enabled=False).launch()