Create app.py

app.py

@@ -0,0 +1,53 @@
+import os
+import clip
+import torch
+from torchvision.datasets import CIFAR100
+from PIL import Image
+
+# Load the model
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model, preprocess = clip.load('ViT-B/32', device)
+
+# Download the dataset
+cifar100 = CIFAR100(root=os.path.expanduser("~/.cache"), download=True, train=False)
+text_inputs = torch.cat([clip.tokenize(f"a photo of a {c}") for c in cifar100.classes]).to(device)
+
+def generateOutput(source):
+    # Prepare the inputs
+    # image, class_id = cifar100[3637]
+    image_input = preprocess(source).unsqueeze(0).to(device)
+
+    with torch.no_grad():
+        image_features = model.encode_image(image_input)
+        text_features = model.encode_text(text_inputs)
+    
+    # Pick the top 5 most similar labels for the image
+    image_features /= image_features.norm(dim=-1, keepdim=True)
+    text_features /= text_features.norm(dim=-1, keepdim=True)
+    similarity = (100.0 * image_features @ text_features.T).softmax(dim=-1)
+    values, indices = similarity[0].topk(5)
+    
+    # Result in Text
+    outputText = "\nTop predictions:\n"
+    for value, index in zip(values, indices):
+        outputText = outputText + f"{cifar100.classes[index]:>16s}: {100 * value.item():.2f}% \n"
+    
+    return(outputText)
+
+title = "CLIP Classification Inference Trials"
+description = "Shows the CLIP Classification based on CIFAR100 data with your own image"
+examples = [["Elephants.jpg"],["941398-beautiful-farm-animals-wallpaper-2000x1402-for-meizu.jpg"], ["Puppies.jpg"], ["photo2.JPG"], ["MultipleItems.jpg"]]
+demo = gr.Interface(
+    generateOutput, 
+    inputs = [
+        gr.Image(width=256, height=256, label="Input Image"), 
+        ], 
+    outputs = [
+        gr.Text(),
+        ],
+    title = title,
+    description = description,
+    examples = examples,
+    cache_examples=False
+)
+demo.launch()