Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,2 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+# Auto detect text files and perform LF normalization
+* text=auto

Image Caption Generator.py

@@ -0,0 +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()
+

README.md

@@ -1,12 +1,6 @@
 ---
-title: Image Caption Generator
-emoji: 🏢
-colorFrom: yellow
-colorTo: gray
+title: Image_Caption_Generator
+app_file: Image Caption Generator.py
 sdk: gradio
 sdk_version: 4.31.5
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,5 @@
+gradio==4.31.5
+numpy==1.26.4
+Pillow==10.3.0
+transformers==4.41.1
+torch==2.3.0