Create app.py

app.py

@@ -0,0 +1,39 @@
+import streamlit as st
+from transformers import BlipForConditionalGeneration, AutoTokenizer
+import torch
+from PIL import Image
+from io import BytesIO
+
+# Load the fine-tuned model
+model_path = '/content/model_after_5_epochs.pth'
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
+model.load_state_dict(torch.load(model_path))
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+tokenizer = AutoTokenizer.from_pretrained("Salesforce/blip-image-captioning-base")
+
+# Function to generate caption for the uploaded image
+def generate_caption(image):
+    # Preprocess the image
+    image = Image.open(image).convert("RGB")
+    image = image.resize((224, 224))  # Resize the image to match model input size
+    image_tensor = torch.tensor([torch.Tensor(image)]).permute(0, 3, 1, 2).to(device)
+
+    # Generate caption
+    output = model.generate(pixel_values=image_tensor)
+    caption = tokenizer.decode(output[0], skip_special_tokens=True)
+    return caption
+
+# Streamlit app
+st.title("Image Caption Generator")
+
+uploaded_image = st.file_uploader("Upload an image", type=["jpg", "jpeg"])
+
+if uploaded_image is not None:
+    st.image(uploaded_image, caption='Uploaded Image.', use_column_width=True)
+    st.write("")
+    st.write("Generating caption...")
+
+    # Generate caption for the uploaded image
+    caption = generate_caption(uploaded_image)
+    st.write("Caption:", caption)