Spaces:
Running
on
T4
Running
on
T4
| import argparse | |
| import os | |
| import copy | |
| import numpy as np | |
| import json | |
| import torch | |
| import torchvision | |
| from PIL import Image, ImageDraw, ImageFont | |
| # Grounding DINO | |
| import GroundingDINO.groundingdino.datasets.transforms as T | |
| from GroundingDINO.groundingdino.models import build_model | |
| from GroundingDINO.groundingdino.util import box_ops | |
| from GroundingDINO.groundingdino.util.slconfig import SLConfig | |
| from GroundingDINO.groundingdino.util.utils import clean_state_dict, get_phrases_from_posmap | |
| # segment anything | |
| from segment_anything import build_sam, SamPredictor | |
| import cv2 | |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| # BLIP | |
| from transformers import BlipProcessor, BlipForConditionalGeneration | |
| # ChatGPT | |
| import openai | |
| def load_image(image_path): | |
| # load image | |
| image_pil = Image.open(image_path).convert("RGB") # load image | |
| transform = T.Compose( | |
| [ | |
| T.RandomResize([800], max_size=1333), | |
| T.ToTensor(), | |
| T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]), | |
| ] | |
| ) | |
| image, _ = transform(image_pil, None) # 3, h, w | |
| return image_pil, image | |
| def generate_caption(raw_image): | |
| # unconditional image captioning | |
| inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16) | |
| out = blip_model.generate(**inputs) | |
| caption = processor.decode(out[0], skip_special_tokens=True) | |
| return caption | |
| def generate_tags(caption, max_tokens=100, model="gpt-3.5-turbo"): | |
| prompt = [ | |
| { | |
| 'role': 'system', | |
| 'content': 'Extrat the unique nouns in the caption. Remove all the adjectives. ' + \ | |
| 'List the nouns in singular form. Split them by ".". ' + \ | |
| f'Caption: {caption}.' | |
| } | |
| ] | |
| response = openai.ChatCompletion.create(model=model, messages=prompt, temperature=0.6, max_tokens=max_tokens) | |
| reply = response['choices'][0]['message']['content'] | |
| # sometimes return with "noun: xxx, xxx, xxx" | |
| tags = reply.split(':')[-1].strip() | |
| return tags | |
| def check_caption(caption, pred_phrases, max_tokens=100, model="gpt-3.5-turbo"): | |
| object_list = [obj.split('(')[0] for obj in pred_phrases] | |
| object_num = [] | |
| for obj in set(object_list): | |
| object_num.append(f'{object_list.count(obj)} {obj}') | |
| object_num = ', '.join(object_num) | |
| print(f"Correct object number: {object_num}") | |
| prompt = [ | |
| { | |
| 'role': 'system', | |
| 'content': 'Revise the number in the caption if it is wrong. ' + \ | |
| f'Caption: {caption}. ' + \ | |
| f'True object number: {object_num}. ' + \ | |
| 'Only give the revised caption: ' | |
| } | |
| ] | |
| response = openai.ChatCompletion.create(model=model, messages=prompt, temperature=0.6, max_tokens=max_tokens) | |
| reply = response['choices'][0]['message']['content'] | |
| # sometimes return with "Caption: xxx, xxx, xxx" | |
| caption = reply.split(':')[-1].strip() | |
| return caption | |
| def load_model(model_config_path, model_checkpoint_path, device): | |
| args = SLConfig.fromfile(model_config_path) | |
| args.device = device | |
| model = build_model(args) | |
| checkpoint = torch.load(model_checkpoint_path, map_location="cpu") | |
| load_res = model.load_state_dict(clean_state_dict(checkpoint["model"]), strict=False) | |
| print(load_res) | |
| _ = model.eval() | |
| return model | |
| def get_grounding_output(model, image, caption, box_threshold, text_threshold,device="cpu"): | |
| caption = caption.lower() | |
| caption = caption.strip() | |
| if not caption.endswith("."): | |
| caption = caption + "." | |
| model = model.to(device) | |
| image = image.to(device) | |
| with torch.no_grad(): | |
| outputs = model(image[None], captions=[caption]) | |
| logits = outputs["pred_logits"].cpu().sigmoid()[0] # (nq, 256) | |
| boxes = outputs["pred_boxes"].cpu()[0] # (nq, 4) | |
| logits.shape[0] | |
| # filter output | |
| logits_filt = logits.clone() | |
| boxes_filt = boxes.clone() | |
| filt_mask = logits_filt.max(dim=1)[0] > box_threshold | |
| logits_filt = logits_filt[filt_mask] # num_filt, 256 | |
| boxes_filt = boxes_filt[filt_mask] # num_filt, 4 | |
| logits_filt.shape[0] | |
| # get phrase | |
| tokenlizer = model.tokenizer | |
| tokenized = tokenlizer(caption) | |
| # build pred | |
| pred_phrases = [] | |
| scores = [] | |
| for logit, box in zip(logits_filt, boxes_filt): | |
| pred_phrase = get_phrases_from_posmap(logit > text_threshold, tokenized, tokenlizer) | |
| pred_phrases.append(pred_phrase + f"({str(logit.max().item())[:4]})") | |
| scores.append(logit.max().item()) | |
| return boxes_filt, torch.Tensor(scores), pred_phrases | |
| def show_mask(mask, ax, random_color=False): | |
| if random_color: | |
| color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0) | |
| else: | |
| color = np.array([30/255, 144/255, 255/255, 0.6]) | |
| h, w = mask.shape[-2:] | |
| mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1) | |
| ax.imshow(mask_image) | |
| def show_box(box, ax, label): | |
| x0, y0 = box[0], box[1] | |
| w, h = box[2] - box[0], box[3] - box[1] | |
| ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2)) | |
| ax.text(x0, y0, label) | |
| def save_mask_data(output_dir, caption, mask_list, box_list, label_list): | |
| value = 0 # 0 for background | |
| mask_img = torch.zeros(mask_list.shape[-2:]) | |
| for idx, mask in enumerate(mask_list): | |
| mask_img[mask.cpu().numpy()[0] == True] = value + idx + 1 | |
| plt.figure(figsize=(10, 10)) | |
| plt.imshow(mask_img.numpy()) | |
| plt.axis('off') | |
| plt.savefig(os.path.join(output_dir, 'mask.jpg'), bbox_inches="tight", dpi=300, pad_inches=0.0) | |
| json_data = { | |
| 'caption': caption, | |
| 'mask':[{ | |
| 'value': value, | |
| 'label': 'background' | |
| }] | |
| } | |
| for label, box in zip(label_list, box_list): | |
| value += 1 | |
| name, logit = label.split('(') | |
| logit = logit[:-1] # the last is ')' | |
| json_data['mask'].append({ | |
| 'value': value, | |
| 'label': name, | |
| 'logit': float(logit), | |
| 'box': box.numpy().tolist(), | |
| }) | |
| with open(os.path.join(output_dir, 'label.json'), 'w') as f: | |
| json.dump(json_data, f) | |
| if __name__ == "__main__": | |
| parser = argparse.ArgumentParser("Grounded-Segment-Anything Demo", add_help=True) | |
| parser.add_argument("--config", type=str, required=True, help="path to config file") | |
| parser.add_argument( | |
| "--grounded_checkpoint", type=str, required=True, help="path to checkpoint file" | |
| ) | |
| parser.add_argument( | |
| "--sam_checkpoint", type=str, required=True, help="path to checkpoint file" | |
| ) | |
| parser.add_argument("--input_image", type=str, required=True, help="path to image file") | |
| parser.add_argument("--openai_key", type=str, required=True, help="key for chatgpt") | |
| parser.add_argument("--openai_proxy", default=None, type=str, help="proxy for chatgpt") | |
| parser.add_argument( | |
| "--output_dir", "-o", type=str, default="outputs", required=True, help="output directory" | |
| ) | |
| parser.add_argument("--box_threshold", type=float, default=0.25, help="box threshold") | |
| parser.add_argument("--text_threshold", type=float, default=0.2, help="text threshold") | |
| parser.add_argument("--iou_threshold", type=float, default=0.5, help="iou threshold") | |
| parser.add_argument("--device", type=str, default="cpu", help="running on cpu only!, default=False") | |
| args = parser.parse_args() | |
| # cfg | |
| config_file = args.config # change the path of the model config file | |
| grounded_checkpoint = args.grounded_checkpoint # change the path of the model | |
| sam_checkpoint = args.sam_checkpoint | |
| image_path = args.input_image | |
| openai_key = args.openai_key | |
| openai_proxy = args.openai_proxy | |
| output_dir = args.output_dir | |
| box_threshold = args.box_threshold | |
| text_threshold = args.box_threshold | |
| iou_threshold = args.iou_threshold | |
| device = args.device | |
| openai.api_key = openai_key | |
| if openai_proxy: | |
| openai.proxy = {"http": openai_proxy, "https": openai_proxy} | |
| # make dir | |
| os.makedirs(output_dir, exist_ok=True) | |
| # load image | |
| image_pil, image = load_image(image_path) | |
| # load model | |
| model = load_model(config_file, grounded_checkpoint, device=device) | |
| # visualize raw image | |
| image_pil.save(os.path.join(output_dir, "raw_image.jpg")) | |
| # generate caption and tags | |
| # use Tag2Text can generate better captions | |
| # https://huggingface.co/spaces/xinyu1205/Tag2Text | |
| # but there are some bugs... | |
| processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-large") | |
| blip_model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-large", torch_dtype=torch.float16).to("cuda") | |
| caption = generate_caption(image_pil) | |
| text_prompt = generate_tags(caption) | |
| print(f"Caption: {caption}") | |
| print(f"Tags: {text_prompt}") | |
| # run grounding dino model | |
| boxes_filt, scores, pred_phrases = get_grounding_output( | |
| model, image, text_prompt, box_threshold, text_threshold, device=device | |
| ) | |
| # initialize SAM | |
| predictor = SamPredictor(build_sam(checkpoint=sam_checkpoint)) | |
| image = cv2.imread(image_path) | |
| image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) | |
| predictor.set_image(image) | |
| size = image_pil.size | |
| H, W = size[1], size[0] | |
| for i in range(boxes_filt.size(0)): | |
| boxes_filt[i] = boxes_filt[i] * torch.Tensor([W, H, W, H]) | |
| boxes_filt[i][:2] -= boxes_filt[i][2:] / 2 | |
| boxes_filt[i][2:] += boxes_filt[i][:2] | |
| boxes_filt = boxes_filt.cpu() | |
| # use NMS to handle overlapped boxes | |
| print(f"Before NMS: {boxes_filt.shape[0]} boxes") | |
| nms_idx = torchvision.ops.nms(boxes_filt, scores, iou_threshold).numpy().tolist() | |
| boxes_filt = boxes_filt[nms_idx] | |
| pred_phrases = [pred_phrases[idx] for idx in nms_idx] | |
| print(f"After NMS: {boxes_filt.shape[0]} boxes") | |
| caption = check_caption(caption, pred_phrases) | |
| print(f"Revise caption with number: {caption}") | |
| transformed_boxes = predictor.transform.apply_boxes_torch(boxes_filt, image.shape[:2]) | |
| masks, _, _ = predictor.predict_torch( | |
| point_coords = None, | |
| point_labels = None, | |
| boxes = transformed_boxes, | |
| multimask_output = False, | |
| ) | |
| # draw output image | |
| plt.figure(figsize=(10, 10)) | |
| plt.imshow(image) | |
| for mask in masks: | |
| show_mask(mask.cpu().numpy(), plt.gca(), random_color=True) | |
| for box, label in zip(boxes_filt, pred_phrases): | |
| show_box(box.numpy(), plt.gca(), label) | |
| plt.title(caption) | |
| plt.axis('off') | |
| plt.savefig( | |
| os.path.join(output_dir, "automatic_label_output.jpg"), | |
| bbox_inches="tight", dpi=300, pad_inches=0.0 | |
| ) | |
| save_mask_data(output_dir, caption, masks, boxes_filt, pred_phrases) | |