import gradio as gr import cv2 import matplotlib import numpy as np import os from PIL import Image import spaces import torch import tempfile from gradio_imageslider import ImageSlider from huggingface_hub import hf_hub_download from models.PDFNet import build_model import torch import cv2 import matplotlib.pyplot as plt import numpy as np from tqdm import tqdm import argparse from args import get_args_parser from torchvision.transforms.functional import normalize import huggingface_hub from DAM_V2.depth_anything_v2.dpt import DepthAnythingV2 css = """ #img-display-container { max-height: 100vh; } #img-display-input { max-height: 80vh; } #img-display-output { max-height: 80vh; } #download { height: 62px; } """ # device = 'cuda' if torch.cuda.is_available() else 'cpu' device = torch.device('cpu') parser = argparse.ArgumentParser('PDFNet Testing script', parents=[get_args_parser()]) args = parser.parse_args(args=[]) model,model_name = build_model(args) model_path = hf_hub_download(repo_id="Tennineee/PDFNet-general",filename="PDF-Generally.pth", repo_type="model") model.load_state_dict(torch.load(model_path,map_location='cpu'),strict=False) model = model.to(device).eval() DAMV2_configs = { 'vits': {'encoder': 'vits', 'features': 64, 'out_channels': [48, 96, 192, 384]}, 'vitb': {'encoder': 'vitb', 'features': 128, 'out_channels': [96, 192, 384, 768]}, 'vitl': {'encoder': 'vitl', 'features': 256, 'out_channels': [256, 512, 1024, 1024]}, } encoder = 'vitb' # or 'vits', 'vitb', 'vitl' encoder2name = { 'vits': 'Small', 'vitb': 'Base', 'vitl': 'Large', 'vitg': 'Giant', # we are undergoing company review procedures to release our giant model checkpoint } model_name = encoder2name[encoder] DAMV2 = DepthAnythingV2(**DAMV2_configs[encoder]) filepath = hf_hub_download(repo_id=f"depth-anything/Depth-Anything-V2-{model_name}", filename=f"depth_anything_v2_{encoder}.pth", repo_type="model") state_dict = torch.load(filepath, map_location="cpu") DAMV2.load_state_dict(state_dict) DAMV2 = DAMV2.to(device).eval() title = "# PDFNet" description = """Official demo for **PDFNet**-general, train on DIS-5K, HRSOD-TR, UHRSD-TR and UHRSD-TE. And here uses DAMV2-base to generate depth map. Please refer to our [paper](https://arxiv.org/abs/2503.06100) and [github](https://github.com/Tennine2077/PDFNet) for more details.""" class GOSNormalize(object): def __init__(self, mean=[0.485,0.456,0.406], std=[0.229,0.224,0.225]): self.mean = mean self.std = std def __call__(self,image): image = normalize(image,self.mean,self.std) return image transforms = GOSNormalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]) def predict(image): H,W = image.shape[:2] depth = DAMV2.infer_image(image) image = torch.nn.functional.interpolate(torch.from_numpy(image).permute(2,0,1)[None,...],size=[1024,1024],mode='bilinear',align_corners=True)[0] depth = torch.nn.functional.interpolate(torch.from_numpy(depth)[None,None,...],size=[1024,1024],mode='bilinear',align_corners=True) image = torch.divide(image,255.0) depth = torch.divide(depth,255.0) image = transforms(image).unsqueeze(0) DIS_map = model.inference(image.to(device),depth.to(device))[0][0][0].cpu() DIS_map = cv2.resize(np.array(DIS_map), (W,H)) return DIS_map with gr.Blocks(css=css) as demo: gr.Markdown(title) gr.Markdown(description) gr.Markdown("### Dichotomous Image Segmentation demo") with gr.Row(): input_image = gr.Image(label="Input Image", type='numpy', elem_id='img-display-input') dis_image = gr.Image(label="Pedict View",type='numpy', elem_id='img-display-output') # dis_image_slider = ImageSlider(label="Pedict View", type="pil", elem_id='img-display-output',upload_count=2) submit = gr.Button(value="Compute") def on_submit(image): original_image = image.copy() DIS_map = predict(np.array(image)) DIS_map = (DIS_map - DIS_map.min()) / (DIS_map.max() - DIS_map.min()) * 255.0 # matting = (DIS_map[...,None] / 255.0 * original_image) + (255-DIS_map[...,None]) alpha_img = np.concatenate([np.array(original_image),DIS_map[...,None]],axis=-1).astype(np.uint16) return alpha_img submit.click(on_submit, inputs=[input_image], outputs=dis_image) example_files = os.listdir('assets/examples') example_files.sort() example_files = [os.path.join('assets/examples', filename) for filename in example_files] examples = gr.Examples(examples=example_files, inputs=[input_image], outputs=dis_image, fn=on_submit) if __name__ == '__main__': demo.queue().launch(share=True)