Spaces:
Sleeping
Sleeping
| from transformers import BlipProcessor, BlipForConditionalGeneration | |
| from PIL import Image | |
| import gradio as gr | |
| import torch | |
| from datetime import datetime | |
| from reportlab.lib.pagesizes import letter | |
| from reportlab.pdfgen import canvas | |
| # Load BLIP model and processor | |
| processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base") | |
| model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base") | |
| model.eval() | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| model.to(device) | |
| # Inference function to generate captions from images dynamically | |
| def generate_captions_from_image(image): | |
| if image.mode != "RGB": | |
| image = image.convert("RGB") | |
| # Preprocess the image and generate a caption | |
| inputs = processor(image, return_tensors="pt").to(device, torch.float16) | |
| output = model.generate(**inputs, max_new_tokens=50) | |
| caption = processor.decode(output[0], skip_special_tokens=True) | |
| return caption | |
| # Function to generate the daily progress report | |
| def generate_dpr(files): | |
| dpr_text = [] | |
| current_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S") | |
| # Add header to the PDF | |
| dpr_text.append(f"Daily Progress Report\nGenerated on: {current_time}\n") | |
| # Process each uploaded file (image) | |
| for file in files: | |
| # Open the image from file path | |
| image = Image.open(file.name) # Using file.name for filepath | |
| if image.mode != "RGB": | |
| image = image.convert("RGB") | |
| # Dynamically generate a caption based on the image | |
| caption = generate_captions_from_image(image) | |
| # Generate DPR section for this image with dynamic caption | |
| dpr_section = f"\nImage: {file.name}\nDescription: {caption}\n" | |
| dpr_text.append(dpr_section) | |
| # Generate a PDF report | |
| pdf_path = "dpr_report.pdf" | |
| c = canvas.Canvas(pdf_path, pagesize=letter) | |
| c.drawString(100, 750, "Daily Progress Report") | |
| c.drawString(100, 730, f"Generated on: {current_time}") | |
| # Add the detailed captions for each image to the PDF (in text format) | |
| y_position = 700 | |
| for section in dpr_text: | |
| c.drawString(100, y_position, section) | |
| y_position -= 100 # Move down for the next section | |
| if y_position < 100: | |
| c.showPage() | |
| y_position = 750 | |
| c.save() | |
| return pdf_path | |
| # Gradio interface for uploading multiple files | |
| iface = gr.Interface( | |
| fn=generate_dpr, | |
| inputs=gr.Files(type="filepath", label="Upload Site Photos"), # Handle batch upload of images | |
| outputs="file", | |
| title="Daily Progress Report Generator", | |
| description="Upload up to 10 site photos. The AI model will dynamically detect construction activities, materials, and progress and generate a PDF report.", | |
| allow_flagging="never" # Optional: Disable flagging | |
| ) | |
| iface.launch() | |