Spaces:
Running
Running
| import os | |
| import sys | |
| # sys.path.append(os.path.abspath(os.path.dirname(os.getcwd()))) | |
| # os.chdir("../") | |
| import gradio as gr | |
| import numpy as np | |
| from pathlib import Path | |
| from matplotlib import pyplot as plt | |
| import torch | |
| import tempfile | |
| from lama_inpaint import inpaint_img_with_lama, build_lama_model, inpaint_img_with_builded_lama | |
| from utils import load_img_to_array, save_array_to_img, dilate_mask, \ | |
| show_mask, show_points | |
| from PIL import Image | |
| sys.path.insert(0, str(Path(__file__).resolve().parent / "third_party" / "segment-anything")) | |
| from segment_anything import SamPredictor, sam_model_registry | |
| import argparse | |
| def setup_args(parser): | |
| parser.add_argument( | |
| "--lama_config", type=str, | |
| default="./third_party/lama/configs/prediction/default.yaml", | |
| help="The path to the config file of lama model. " | |
| "Default: the config of big-lama", | |
| ) | |
| parser.add_argument( | |
| "--lama_ckpt", type=str, | |
| default="pretrained_models/big-lama", | |
| help="The path to the lama checkpoint.", | |
| ) | |
| parser.add_argument( | |
| "--sam_ckpt", type=str, | |
| default="./pretrained_models/sam_vit_h_4b8939.pth", | |
| help="The path to the SAM checkpoint to use for mask generation.", | |
| ) | |
| def mkstemp(suffix, dir=None): | |
| fd, path = tempfile.mkstemp(suffix=f"{suffix}", dir=dir) | |
| os.close(fd) | |
| return Path(path) | |
| def get_sam_feat(img): | |
| model['sam'].set_image(img) | |
| features = model['sam'].features | |
| orig_h = model['sam'].orig_h | |
| orig_w = model['sam'].orig_w | |
| input_h = model['sam'].input_h | |
| input_w = model['sam'].input_w | |
| model['sam'].reset_image() | |
| return features, orig_h, orig_w, input_h, input_w | |
| def get_masked_img(img, w, h, features, orig_h, orig_w, input_h, input_w, dilate_kernel_size): | |
| point_coords = [w, h] | |
| point_labels = [1] | |
| model['sam'].is_image_set = True | |
| model['sam'].features = features | |
| model['sam'].orig_h = orig_h | |
| model['sam'].orig_w = orig_w | |
| model['sam'].input_h = input_h | |
| model['sam'].input_w = input_w | |
| # model['sam'].set_image(img) # todo : update here for accelerating | |
| masks, _, _ = model['sam'].predict( | |
| point_coords=np.array([point_coords]), | |
| point_labels=np.array(point_labels), | |
| multimask_output=True, | |
| ) | |
| masks = masks.astype(np.uint8) * 255 | |
| dilate_kernel_size = 20 | |
| # dilate mask to avoid unmasked edge effect | |
| if dilate_kernel_size is not None: | |
| masks = [dilate_mask(mask, dilate_kernel_size) for mask in masks] | |
| else: | |
| masks = [mask for mask in masks] | |
| figs = [] | |
| for idx, mask in enumerate(masks): | |
| # save the pointed and masked image | |
| tmp_p = mkstemp(".png") | |
| dpi = plt.rcParams['figure.dpi'] | |
| height, width = img.shape[:2] | |
| fig = plt.figure(figsize=(width/dpi/0.77, height/dpi/0.77)) | |
| plt.imshow(img) | |
| plt.axis('off') | |
| show_points(plt.gca(), [point_coords], point_labels, | |
| size=(width*0.04)**2) | |
| show_mask(plt.gca(), mask, random_color=False) | |
| plt.tight_layout() | |
| plt.savefig(tmp_p, bbox_inches='tight', pad_inches=0) | |
| figs.append(fig) | |
| plt.close() | |
| return *figs, *masks | |
| def get_inpainted_img(img,mask): | |
| lama_config = args.lama_config | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| if len(mask.shape)==3: | |
| mask = mask[:,:,0] | |
| img_inpainted = inpaint_img_with_builded_lama( | |
| model['lama'], img, mask, lama_config, device=device) | |
| return img_inpainted | |
| # get args | |
| parser = argparse.ArgumentParser() | |
| setup_args(parser) | |
| args = parser.parse_args(sys.argv[1:]) | |
| # build models | |
| model = {} | |
| # build the sam model | |
| model_type="vit_h" | |
| ckpt_p=args.sam_ckpt | |
| model_sam = sam_model_registry[model_type](checkpoint=ckpt_p) | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| model_sam.to(device=device) | |
| model['sam'] = SamPredictor(model_sam) | |
| # build the lama model | |
| lama_config = args.lama_config | |
| lama_ckpt = args.lama_ckpt | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| model['lama'] = build_lama_model(lama_config, lama_ckpt, device=device) | |
| image_input = gr.Image(label="Input Image") | |
| mask_input = gr.Image(label="Mask Image") | |
| demo = gr.Interface( | |
| fn=get_inpainted_img, | |
| inputs=[image_input, mask_input], | |
| outputs=gr.Image(type="numpy", label="Output Image"), | |
| title="Image and Mask Processor", | |
| description="Upload an image and a mask to process the image. The mask highlights the areas to be processed.", | |
| ) | |
| if __name__ == "__main__": | |
| demo.queue(api_open=True) | |
| demo.launch(show_api=True) |