Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import torch | |
| from transformers import AutoProcessor, AutoModel | |
| from PIL import Image, ImageDraw, ImageFont | |
| import numpy as np | |
| import random | |
| import os | |
| import wget | |
| import traceback | |
| # --- Configuration & Model Loading --- | |
| # Device Selection with fallback | |
| DEVICE = "cuda" if torch.cuda.is_available() and torch.cuda.current_device() >= 0 else "cpu" | |
| print(f"Using device: {DEVICE}") | |
| # --- CLIP Setup --- | |
| CLIP_MODEL_ID = "openai/clip-vit-base-patch32" | |
| clip_processor = None | |
| clip_model = None | |
| def load_clip_model(): | |
| global clip_processor, clip_model | |
| if clip_processor is None: | |
| try: | |
| print(f"Loading CLIP processor: {CLIP_MODEL_ID}...") | |
| clip_processor = AutoProcessor.from_pretrained(CLIP_MODEL_ID) | |
| print("CLIP processor loaded.") | |
| except Exception as e: | |
| print(f"Error loading CLIP processor: {e}") | |
| return False | |
| if clip_model is None: | |
| try: | |
| print(f"Loading CLIP model: {CLIP_MODEL_ID}...") | |
| clip_model = AutoModel.from_pretrained(CLIP_MODEL_ID).to(DEVICE) | |
| print(f"CLIP model loaded to {DEVICE}.") | |
| except Exception as e: | |
| print(f"Error loading CLIP model: {e}") | |
| return False | |
| return True | |
| # --- FastSAM Setup --- | |
| FASTSAM_CHECKPOINT = "FastSAM-s.pt" | |
| FASTSAM_CHECKPOINT_URL = f"https://huggingface.co/CASIA-IVA-Lab/FastSAM-s/resolve/main/{FASTSAM_CHECKPOINT}" | |
| fastsam_model = None | |
| fastsam_lib_imported = False | |
| def check_and_import_fastsam(): | |
| global fastsam_lib_imported | |
| if not fastsam_lib_imported: | |
| try: | |
| from fastsam import FastSAM, FastSAMPrompt | |
| globals()['FastSAM'] = FastSAM | |
| globals()['FastSAMPrompt'] = FastSAMPrompt | |
| fastsam_lib_imported = True | |
| print("fastsam library imported successfully.") | |
| except ImportError as e: | |
| print(f"Error: 'fastsam' library not found. Install with 'pip install fastsam': {e}") | |
| fastsam_lib_imported = False | |
| except Exception as e: | |
| print(f"Unexpected error during fastsam import: {e}") | |
| traceback.print_exc() | |
| fastsam_lib_imported = False | |
| return fastsam_lib_imported | |
| def download_fastsam_weights(retries=3): | |
| if not os.path.exists(FASTSAM_CHECKPOINT): | |
| print(f"Downloading FastSAM weights: {FASTSAM_CHECKPOINT} from {FASTSAM_CHECKPOINT_URL}...") | |
| for attempt in range(retries): | |
| try: | |
| wget.download(FASTSAM_CHECKPOINT_URL, FASTSAM_CHECKPOINT) | |
| print("FastSAM weights downloaded.") | |
| break | |
| except Exception as e: | |
| print(f"Attempt {attempt + 1}/{retries} failed: {e}") | |
| if attempt + 1 == retries: | |
| print("Failed to download weights after all attempts.") | |
| return False | |
| return os.path.exists(FASTSAM_CHECKPOINT) | |
| def load_fastsam_model(): | |
| global fastsam_model | |
| if fastsam_model is None: | |
| if not check_and_import_fastsam(): | |
| print("Cannot load FastSAM model due to library import failure.") | |
| return False | |
| if download_fastsam_weights(): | |
| try: | |
| print(f"Loading FastSAM model: {FASTSAM_CHECKPOINT}...") | |
| fastsam_model = FastSAM(FASTSAM_CHECKPOINT) | |
| print("FastSAM model loaded.") | |
| return True | |
| except Exception as e: | |
| print(f"Error loading FastSAM model: {e}") | |
| traceback.print_exc() | |
| return False | |
| else: | |
| print("FastSAM weights not found or download failed.") | |
| return False | |
| return True | |
| # --- Processing Functions --- | |
| def run_clip_zero_shot(image: Image.Image, text_labels: str): | |
| if clip_model is None or clip_processor is None: | |
| if not load_clip_model(): | |
| return "Error: CLIP Model could not be loaded.", None | |
| if image is None: | |
| return "Please upload an image.", None | |
| if not text_labels: | |
| return {}, image | |
| labels = [label.strip() for label in text_labels.split(',') if label.strip()] | |
| if not labels: | |
| return {}, image | |
| print(f"Running CLIP zero-shot classification with labels: {labels}") | |
| try: | |
| if image.mode != "RGB": | |
| image = image.convert("RGB") | |
| inputs = clip_processor(text=labels, images=image, return_tensors="pt", padding=True).to(DEVICE) | |
| with torch.no_grad(): | |
| outputs = clip_model(**inputs) | |
| probs = outputs.logits_per_image.softmax(dim=1) | |
| confidences = {labels[i]: float(probs[0, i].item()) for i in range(len(labels))} | |
| return confidences, image | |
| except Exception as e: | |
| print(f"Error during CLIP processing: {e}") | |
| traceback.print_exc() | |
| return f"Error: {e}", image | |
| def run_fastsam_segmentation(image_pil: Image.Image, conf_threshold: float = 0.4, iou_threshold: float = 0.9): | |
| if not load_fastsam_model() or not fastsam_lib_imported: | |
| return "Error: FastSAM not loaded or library unavailable." | |
| if image_pil is None: | |
| return "Please upload an image." | |
| print("Running FastSAM 'segment everything'...") | |
| try: | |
| if image_pil.mode != "RGB": | |
| image_pil = image_pil.convert("RGB") | |
| image_np_rgb = np.array(image_pil) | |
| everything_results = fastsam_model( | |
| image_np_rgb, device=DEVICE, retina_masks=True, imgsz=640, | |
| conf=conf_threshold, iou=iou_threshold, verbose=True | |
| ) | |
| prompt_process = FastSAMPrompt(image_np_rgb, everything_results, device=DEVICE) | |
| ann = prompt_process.everything_prompt() | |
| output_image = image_pil.copy() | |
| if ann and ann[0] and 'masks' in ann[0] and len(ann[0]['masks']) > 0: | |
| masks = ann[0]['masks'].cpu().numpy() | |
| print(f"Found {len(masks)} masks with shape: {masks.shape}") | |
| overlay = Image.new('RGBA', output_image.size, (0, 0, 0, 0)) | |
| draw = ImageDraw.Draw(overlay) | |
| for mask in masks: | |
| mask = (mask > 0).astype(np.uint8) * 255 | |
| color = (random.randint(50, 255), random.randint(50, 255), random.randint(50, 255), 180) | |
| mask_image = Image.fromarray(mask, mode='L') | |
| draw.bitmap((0, 0), mask_image, fill=color) | |
| output_image = Image.alpha_composite(output_image.convert('RGBA'), overlay).convert('RGB') | |
| else: | |
| print("No masks detected in 'segment everything' mode.") | |
| return output_image | |
| except Exception as e: | |
| print(f"Error during FastSAM 'everything' processing: {e}") | |
| traceback.print_exc() | |
| return f"Error: {e}" | |
| def run_text_prompted_segmentation(image_pil: Image.Image, text_prompts: str, conf_threshold: float = 0.4, iou_threshold: float = 0.9): | |
| if not load_fastsam_model(): | |
| return "Error: FastSAM Model not loaded.", "Model load failure." | |
| if not fastsam_lib_imported: | |
| return "Error: FastSAM library not available.", "Library import error." | |
| if image_pil is None: | |
| return "Please upload an image.", "No image provided." | |
| if not text_prompts: | |
| return image_pil, "Please enter text prompts (e.g., 'person, dog')." | |
| prompts = [p.strip() for p in text_prompts.split(',') if p.strip()] | |
| if not prompts: | |
| return image_pil, "No valid text prompts entered." | |
| print(f"Running FastSAM text-prompted segmentation for: {prompts}") | |
| try: | |
| if image_pil.mode != "RGB": | |
| image_pil = image_pil.convert("RGB") | |
| image_np_rgb = np.array(image_pil) | |
| everything_results = fastsam_model( | |
| image_np_rgb, device=DEVICE, retina_masks=True, imgsz=640, | |
| conf=conf_threshold, iou=iou_threshold, verbose=True | |
| ) | |
| prompt_process = FastSAMPrompt(image_np_rgb, everything_results, device=DEVICE) | |
| all_matching_masks = [] | |
| found_prompts = [] | |
| for text in prompts: | |
| print(f" Processing prompt: '{text}'") | |
| ann = prompt_process.text_prompt(text=text) | |
| if ann and ann[0] and 'masks' in ann[0] and len(ann[0]['masks']) > 0: | |
| num_found = len(ann[0]['masks']) | |
| print(f" Found {num_found} mask(s) with shape: {ann[0]['masks'].shape}") | |
| found_prompts.append(f"{text} ({num_found})") | |
| masks = ann[0]['masks'].cpu().numpy() | |
| all_matching_masks.extend(masks) | |
| else: | |
| print(f" No masks found for '{text}'.") | |
| found_prompts.append(f"{text} (0)") | |
| output_image = image_pil.copy() | |
| status_message = f"Found segments for: {', '.join(found_prompts)}" if found_prompts else "No matches found." | |
| if all_matching_masks: | |
| masks_np = np.stack(all_matching_masks, axis=0) | |
| print(f"Total masks stacked: {masks_np.shape}") | |
| overlay = Image.new('RGBA', output_image.size, (0, 0, 0, 0)) | |
| draw = ImageDraw.Draw(overlay) | |
| for mask in masks_np: | |
| mask = (mask > 0).astype(np.uint8) * 255 | |
| color = (random.randint(50, 255), random.randint(50, 255), random.randint(50, 255), 180) | |
| mask_image = Image.fromarray(mask, mode='L') | |
| draw.bitmap((0, 0), mask_image, fill=color) | |
| output_image = Image.alpha_composite(output_image.convert('RGBA'), overlay).convert('RGB') | |
| return output_image, status_message | |
| except Exception as e: | |
| print(f"Error during FastSAM text-prompted processing: {e}") | |
| traceback.print_exc() | |
| return image_pil, f"Error: {e}" | |
| # --- Gradio Interface --- | |
| print("Attempting to preload models...") | |
| load_fastsam_model() # Load FastSAM eagerly | |
| print("Preloading finished.") | |
| with gr.Blocks(theme=gr.themes.Soft()) as demo: | |
| gr.Markdown("# CLIP & FastSAM Demo") | |
| gr.Markdown("Explore Zero-Shot Classification, 'Segment Everything', and Text-Prompted Segmentation.") | |
| with gr.Tabs(): | |
| with gr.TabItem("CLIP Zero-Shot Classification"): | |
| gr.Markdown("Upload an image and provide comma-separated labels (e.g., 'cat, dog, car').") | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| clip_input_image = gr.Image(type="pil", label="Input Image") | |
| clip_text_labels = gr.Textbox(label="Comma-Separated Labels", placeholder="e.g., astronaut, moon") | |
| clip_button = gr.Button("Run CLIP Classification", variant="primary") | |
| with gr.Column(scale=1): | |
| clip_output_label = gr.Label(label="Classification Probabilities") | |
| clip_output_image_display = gr.Image(type="pil", label="Input Image Preview") | |
| clip_button.click( | |
| run_clip_zero_shot, | |
| inputs=[clip_input_image, clip_text_labels], | |
| outputs=[clip_output_label, clip_output_image_display] | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| ["examples/astronaut.jpg", "astronaut, moon, rover"], | |
| ["examples/dog_bike.jpg", "dog, bicycle, person"], | |
| ["examples/clip_logo.png", "logo, text, graphics"], | |
| ], | |
| inputs=[clip_input_image, clip_text_labels], | |
| outputs=[clip_output_label, clip_output_image_display], | |
| fn=run_clip_zero_shot, | |
| cache_examples=False, | |
| ) | |
| with gr.TabItem("FastSAM Segment Everything"): | |
| gr.Markdown("Upload an image to segment all objects/regions.") | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| fastsam_input_image_all = gr.Image(type="pil", label="Input Image") | |
| with gr.Row(): | |
| fastsam_conf_all = gr.Slider(minimum=0.1, maximum=1.0, value=0.4, step=0.05, label="Confidence Threshold") | |
| fastsam_iou_all = gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="IoU Threshold") | |
| fastsam_button_all = gr.Button("Run FastSAM Segmentation", variant="primary") | |
| with gr.Column(scale=1): | |
| fastsam_output_image_all = gr.Image(type="pil", label="Segmented Image") | |
| fastsam_button_all.click( | |
| run_fastsam_segmentation, | |
| inputs=[fastsam_input_image_all, fastsam_conf_all, fastsam_iou_all], | |
| outputs=[fastsam_output_image_all] | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| ["examples/dogs.jpg", 0.4, 0.9], | |
| ["examples/fruits.jpg", 0.5, 0.8], | |
| ["examples/lion.jpg", 0.45, 0.9], | |
| ], | |
| inputs=[fastsam_input_image_all, fastsam_conf_all, fastsam_iou_all], | |
| outputs=[fastsam_output_image_all], | |
| fn=run_fastsam_segmentation, | |
| cache_examples=False, | |
| ) | |
| with gr.TabItem("Text-Prompted Segmentation"): | |
| gr.Markdown("Upload an image and provide comma-separated prompts (e.g., 'person, dog').") | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| prompt_input_image = gr.Image(type="pil", label="Input Image") | |
| prompt_text_input = gr.Textbox(label="Comma-Separated Text Prompts", placeholder="e.g., glasses, watch") | |
| with gr.Row(): | |
| prompt_conf = gr.Slider(minimum=0.1, maximum=1.0, value=0.4, step=0.05, label="Confidence Threshold") | |
| prompt_iou = gr.Slider(minimum=0.1, maximum=1.0, value=0.9, step=0.05, label="IoU Threshold") | |
| prompt_button = gr.Button("Segment by Text", variant="primary") | |
| with gr.Column(scale=1): | |
| prompt_output_image = gr.Image(type="pil", label="Text-Prompted Segmentation") | |
| prompt_status_message = gr.Textbox(label="Status", interactive=False) | |
| prompt_button.click( | |
| run_text_prompted_segmentation, | |
| inputs=[prompt_input_image, prompt_text_input, prompt_conf, prompt_iou], | |
| outputs=[prompt_output_image, prompt_status_message] | |
| ) | |
| gr.Examples( | |
| examples=[ | |
| ["examples/dog_bike.jpg", "person, bicycle", 0.4, 0.9], | |
| ["examples/astronaut.jpg", "person, helmet", 0.35, 0.9], | |
| ["examples/dogs.jpg", "dog", 0.4, 0.9], | |
| ["examples/fruits.jpg", "banana, apple", 0.5, 0.8], | |
| ["examples/teacher.jpg", "person, glasses", 0.4, 0.9], | |
| ], | |
| inputs=[prompt_input_image, prompt_text_input, prompt_conf, prompt_iou], | |
| outputs=[prompt_output_image, prompt_status_message], | |
| fn=run_text_prompted_segmentation, | |
| cache_examples=False, | |
| ) | |
| # Download example images with retries | |
| if not os.path.exists("examples"): | |
| os.makedirs("examples") | |
| print("Created 'examples' directory.") | |
| example_files = { | |
| "astronaut.jpg": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/d1/Astronaut_-_St._Jean_Bay.jpg/640px-Astronaut_-_St._Jean_Bay.jpg", | |
| "dog_bike.jpg": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/gradio/outputs_multimodal.jpg", | |
| "clip_logo.png": "https://raw.githubusercontent.com/openai/CLIP/main/CLIP.png", | |
| "dogs.jpg": "https://raw.githubusercontent.com/ultralytics/assets/main/im/image8.jpg", | |
| "fruits.jpg": "https://raw.githubusercontent.com/ultralytics/assets/main/im/image9.jpg", | |
| "lion.jpg": "https://huggingface.co/spaces/gradio/image-segmentation/resolve/main/images/lion.jpg", | |
| "teacher.jpg": "https://images.pexels.com/photos/848117/pexels-photo-848117.jpeg?auto=compress&cs=tinysrgb&w=600" | |
| } | |
| def download_example_file(filename, url, retries=3): | |
| filepath = os.path.join("examples", filename) | |
| if not os.path.exists(filepath): | |
| for attempt in range(retries): | |
| try: | |
| print(f"Downloading {filename} (attempt {attempt + 1}/{retries})...") | |
| wget.download(url, filepath) | |
| break | |
| except Exception as e: | |
| print(f"Attempt {attempt + 1} failed: {e}") | |
| if attempt + 1 == retries: | |
| print(f"Failed to download {filename} after {retries} attempts.") | |
| for filename, url in example_files.items(): | |
| download_example_file(filename, url) | |
| if __name__ == "__main__": | |
| demo.launch(debug=True) |