step 1

app.py

@@ -0,0 +1,74 @@
+import gradio as gr
+from PIL import Image
+from torchvision.transforms import Compose, Resize, CenterCrop, ToTensor, Normalize
+from transformers import CLIPProcessor, CLIPModel
+import torch
+
+
+#Load the pre-trained CLIP model and its tokenizer:
+model_name = "openai/clip-vit-base-patch32"
+processor = CLIPProcessor.from_pretrained(model_name)
+model = CLIPModel.from_pretrained(model_name)
+
+
+#Define the preprocessing function for images:
+def preprocess_image(image):
+    preprocess = Compose([
+        Resize(256, interpolation=Image.BICUBIC),
+        CenterCrop(224),
+        ToTensor(),
+        Normalize((0.48145466, 0.4578275, 0.40821073), (0.26862954, 0.26130258, 0.27577711)),
+    ])
+    return preprocess(image).unsqueeze(0)
+
+
+#Define a function to process the image and text inputs:
+def process_query(image, text):
+    image_tensor = preprocess_image(image)
+    inputs = processor(text, return_tensors="pt", padding=True, truncation=True)
+
+    with torch.no_grad():
+        outputs = model(input_ids=inputs["input_ids"], pixel_values=image_tensor)
+        logits_per_image = outputs.logits_per_image
+        probs = logits_per_image.softmax(dim=-1)
+        similarities = probs.squeeze()
+
+    # Calculate the similarity scores for each product in the dataset
+    product_scores = []
+    for product in deepfashion_database:
+        # Preprocess product image and compute similarity
+        product_image = Image.open(product["image_path"]).convert("RGB")
+        product_image_tensor = preprocess_image(product_image)
+        product_text = product["description"]
+        product_inputs = processor(product_text, return_tensors="pt", padding=True, truncation=True)
+
+        with torch.no_grad():
+            product_outputs = model(input_ids=product_inputs["input_ids"], pixel_values=product_image_tensor)
+            product_logits_per_image = product_outputs.logits_per_image
+            product_probs = product_logits_per_image.softmax(dim=-1)
+            product_similarity = product_probs.squeeze().item()
+
+        product_scores.append((product, product_similarity))
+
+    # Sort products by similarity and return the top 3 matches
+    top_3_products = sorted(product_scores, key=lambda x: x[1], reverse=True)[:3]
+    return '\n'.join([f"{product['description']} (score: {score:.2f})" for product, score in top_3_products])
+
+@gr.app
+def product_search_app(image, text):
+    return process_query(image, text)
+
+
+iface = gr.Interface(
+    fn=process_query,
+    inputs=[
+        gr.inputs.Image(),
+        gr.inputs.Textbox(lines=3, label="Text Query")
+    ],
+    outputs=gr.outputs.Textbox(label="Top 3 Matches"),
+    title="Product Search",
+    description="Find the best matching products based on image and text queries.",
+)
+
+
+iface.launch()