Update app.py

app.py

@@ -1,4 +1,3 @@
-import gradio as gr
 import requests
 from PIL import Image
 from transformers import AutoProcessor, BlipForConditionalGeneration
@@ -7,9 +6,19 @@ from transformers import AutoProcessor, BlipForConditionalGeneration
 processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base")
 
+# Load your image, DON'T FORGET TO WRITE YOUR IMAGE NAME
+img_path = "YOUR IMAGE NAME.jpeg"
+# convert it into an RGB format 
+image = Image.open(img_path).convert('RGB')
 
-def greet(name):
-    return "Hello " + name + "!!"
+# You do not need a question for image captioning
+text = "the image of"
+inputs = processor(images=image, text=text, return_tensors="pt")
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+# Generate a caption for the image
+outputs = model.generate(**inputs, max_length=50)
+
+# Decode the generated tokens to text
+caption = processor.decode(outputs[0], skip_special_tokens=True)
+# Print the caption
+print(caption)