Spaces:
Sleeping
Sleeping
| import re | |
| import gradio as gr | |
| from transformers import AutoProcessor, AutoModelForImageTextToText | |
| from PIL import Image | |
| # Load model & processor once at startup | |
| processor = AutoProcessor.from_pretrained("ds4sd/SmolDocling-256M-preview") | |
| model = AutoModelForImageTextToText.from_pretrained("ds4sd/SmolDocling-256M-preview") | |
| def smoldocling_readimage(image, prompt_text="Convert to docling"): | |
| messages = [ | |
| {"role": "user", "content": [{"type": "image"}, {"type": "text", "text": prompt_text}]} | |
| ] | |
| prompt = processor.apply_chat_template(messages, add_generation_prompt=True) | |
| inputs = processor(text=prompt, images=[image], return_tensors="pt") | |
| outputs = model.generate(**inputs, max_new_tokens=1024) | |
| prompt_length = inputs.input_ids.shape[1] | |
| generated = outputs[:, prompt_length:] | |
| result = processor.batch_decode(generated, skip_special_tokens=False)[0] | |
| return result.replace("<end_of_utterance>", "").strip() | |
| def extract_numbers(docling_text): | |
| # Extract all floating numbers from the docling text using regex | |
| numbers = re.findall(r"[-+]?\d*\.\d+|\d+", docling_text) | |
| return list(map(float, numbers)) | |
| def compare_outputs(img1, img2): | |
| # Extract docling text from both images | |
| output1 = smoldocling_readimage(img1) | |
| output2 = smoldocling_readimage(img2) | |
| # Extract numbers from both outputs | |
| nums1 = extract_numbers(output1) | |
| nums2 = extract_numbers(output2) | |
| # Compare numbers — find matching count based on position | |
| length = min(len(nums1), len(nums2)) | |
| matches = sum(1 for i in range(length) if abs(nums1[i] - nums2[i]) < 1e-3) | |
| # Calculate similarity accuracy percentage | |
| total = max(len(nums1), len(nums2)) | |
| accuracy = (matches / total) * 100 if total > 0 else 0 | |
| # Prepare result text | |
| result_text = ( | |
| f"Output for Image 1:\n{output1}\n\n" | |
| f"Output for Image 2:\n{output2}\n\n" | |
| f"Similarity Accuracy: {accuracy:.2f}%\n" | |
| f"Matching Values: {matches} out of {total}" | |
| ) | |
| return result_text | |
| # Gradio UI: take 2 images, output similarity report | |
| demo = gr.Interface( | |
| fn=compare_outputs, | |
| inputs=[ | |
| gr.Image(type="pil", label="Upload Image 1"), | |
| gr.Image(type="pil", label="Upload Image 2"), | |
| ], | |
| outputs="text", | |
| title="SmolDocling Image Comparison", | |
| description="Upload two document images. This app extracts data from both and compares similarity." | |
| ) | |
| demo.launch() | |
| import re | |
| import gradio as gr | |
| from transformers import AutoProcessor, AutoModelForImageTextToText | |
| from PIL import Image | |
| # Load model & processor once at startup | |
| processor = AutoProcessor.from_pretrained("ds4sd/SmolDocling-256M-preview") | |
| model = AutoModelForImageTextToText.from_pretrained("ds4sd/SmolDocling-256M-preview") | |
| def smoldocling_readimage(image, prompt_text="Convert to docling"): | |
| messages = [ | |
| {"role": "user", "content": [{"type": "image"}, {"type": "text", "text": prompt_text}]} | |
| ] | |
| prompt = processor.apply_chat_template(messages, add_generation_prompt=True) | |
| inputs = processor(text=prompt, images=[image], return_tensors="pt") | |
| outputs = model.generate(**inputs, max_new_tokens=1024) | |
| prompt_length = inputs.input_ids.shape[1] | |
| generated = outputs[:, prompt_length:] | |
| result = processor.batch_decode(generated, skip_special_tokens=False)[0] | |
| return result.replace("<end_of_utterance>", "").strip() | |
| def extract_numbers(docling_text): | |
| # Extract all floating numbers from the docling text | |
| numbers = re.findall(r"[-+]?\d*\.\d+|\d+", docling_text) | |
| return list(map(float, numbers)) | |
| def compare_outputs(img1, img2): | |
| # Get outputs | |
| output1 = smoldocling_readimage(img1) | |
| output2 = smoldocling_readimage(img2) | |
| # Extract numbers | |
| nums1 = extract_numbers(output1) | |
| nums2 = extract_numbers(output2) | |
| length = min(len(nums1), len(nums2)) | |
| matches = 0 | |
| mismatches = [] | |
| for i in range(length): | |
| if abs(nums1[i] - nums2[i]) < 1e-3: | |
| matches += 1 | |
| else: | |
| mismatches.append(f"Pos {i+1}: {nums1[i]} ≠ {nums2[i]}") | |
| total = max(len(nums1), len(nums2)) | |
| accuracy = (matches / total) * 100 if total > 0 else 0 | |
| mismatch_text = "\n".join(mismatches) if mismatches else "✅ All values match." | |
| result_text = ( | |
| f"📄 Output for Image 1:\n{output1}\n\n" | |
| f"📄 Output for Image 2:\n{output2}\n\n" | |
| f"🔍 Similarity Accuracy: {accuracy:.2f}%\n" | |
| f"✅ Matching Values: {matches} / {total}\n" | |
| f"❌ Mismatches:\n{mismatch_text}" | |
| ) | |
| return result_text | |
| # Gradio UI | |
| demo = gr.Interface( | |
| fn=compare_outputs, | |
| inputs=[ | |
| gr.Image(type="pil", label="Upload Image 1"), | |
| gr.Image(type="pil", label="Upload Image 2"), | |
| ], | |
| outputs="text", | |
| title="SmolDocling Image Comparison", | |
| description="Upload two document images to extract values and compare similarity, with detailed mismatches." | |
| ) | |
| demo.launch() | |