Update Image Caption Generator.py

Image Caption Generator.py

@@ -1,56 +1,56 @@
-import gradio as gr
-import numpy as np
-from PIL import Image
-from transformers import AutoProcessor, BlipForConditionalGeneration
-import os
-# Load the pretrained processor and model
-processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
-
-def caption_image(input_image: np.ndarray):
-    # Convert numpy array to PIL Image and convert to RGB
-    raw_image = Image.fromarray(input_image).convert('RGB')
-
-    # Process the image
-    inputs = processor(raw_image, return_tensors="pt")
-
-
-    # Generate a caption for the image
-    out = model.generate(**inputs,max_length=50)
-
-    # Decode the generated tokens to text
-    caption = processor.decode(out[0], skip_special_tokens=True)
-
-    return caption
-
-# Save the data to the Hugging Face dataset
-HF_TOKEN = os.getenv("HF_TOKEN")
-hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "crowdsourced-images-data")
-
-
-# Define examples
-examples = [
-    ["1.jpg"], 
-    ["2.jpg"], 
-    ["3.jpg"],
-    ["4.jpg"],
-]
-
-
-
-# Create a Gradio interface
-
-iface = gr.Interface(
-    fn=caption_image, 
-    inputs=gr.Image(), 
-    outputs=gr.Textbox(label="Generated Caption", lines=2),
-    title="🔍 Image Caption Generator 🖼️",
-    description = "Generate stunning captions for your images with our AI-powered model! 🌟\n\n🚫📚 Note: Please avoid entering any sensitive or personal information, as inputs may be reviewed or used for training purposes.",
-    allow_flagging="auto",
-    flagging_callback=hf_writer,
-    examples=examples,
-    
-)
-
-iface.launch()
-
+import gradio as gr
+import numpy as np
+from PIL import Image
+from transformers import AutoProcessor, BlipForConditionalGeneration
+import os
+# Load the pretrained processor and model
+processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-large")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large")
+
+def caption_image(input_image: np.ndarray):
+    # Convert numpy array to PIL Image and convert to RGB
+    raw_image = Image.fromarray(input_image).convert('RGB')
+
+    # Process the image
+    inputs = processor(raw_image, return_tensors="pt")
+
+
+    # Generate a caption for the image
+    out = model.generate(**inputs,max_length=50)
+
+    # Decode the generated tokens to text
+    caption = processor.decode(out[0], skip_special_tokens=True)
+
+    return caption
+
+# Save the data to the Hugging Face dataset
+HF_TOKEN = os.getenv("HF_TOKEN")
+hf_writer = gr.HuggingFaceDatasetSaver(HF_TOKEN, "crowdsourced-images-data")
+
+
+# Define examples
+examples = [
+    ["1.jpg"], 
+    ["2.jpg"], 
+    ["3.jpg"],
+    ["4.jpg"],
+]
+
+
+
+# Create a Gradio interface
+
+iface = gr.Interface(
+    fn=caption_image, 
+    inputs=gr.Image(), 
+    outputs=gr.Textbox(label="Generated Caption", lines=2),
+    title="🔍 Image Caption Generator 🖼️ ",
+    description = "Generate stunning captions for your images with our AI-powered model! 🌟\n\n🚫📚 Note: Please avoid entering any sensitive or personal information, as inputs may be reviewed or used for training purposes.",
+    allow_flagging="auto",
+    flagging_callback=hf_writer,
+    examples=examples,
+    
+)
+
+iface.launch()
+