import numpy as np import cv2 import os import torch from einops import rearrange from huggingface_hub import hf_hub_download from PIL import Image from ..open_pose.util import HWC3, resize_image class Network(torch.nn.Module): def __init__(self, model_path): super().__init__() self.netVggOne = torch.nn.Sequential( torch.nn.Conv2d(in_channels=3, out_channels=64, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=64, out_channels=64, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False) ) self.netVggTwo = torch.nn.Sequential( torch.nn.MaxPool2d(kernel_size=2, stride=2), torch.nn.Conv2d(in_channels=64, out_channels=128, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=128, out_channels=128, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False) ) self.netVggThr = torch.nn.Sequential( torch.nn.MaxPool2d(kernel_size=2, stride=2), torch.nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=256, out_channels=256, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False) ) self.netVggFou = torch.nn.Sequential( torch.nn.MaxPool2d(kernel_size=2, stride=2), torch.nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False) ) self.netVggFiv = torch.nn.Sequential( torch.nn.MaxPool2d(kernel_size=2, stride=2), torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False), torch.nn.Conv2d(in_channels=512, out_channels=512, kernel_size=3, stride=1, padding=1), torch.nn.ReLU(inplace=False) ) self.netScoreOne = torch.nn.Conv2d(in_channels=64, out_channels=1, kernel_size=1, stride=1, padding=0) self.netScoreTwo = torch.nn.Conv2d(in_channels=128, out_channels=1, kernel_size=1, stride=1, padding=0) self.netScoreThr = torch.nn.Conv2d(in_channels=256, out_channels=1, kernel_size=1, stride=1, padding=0) self.netScoreFou = torch.nn.Conv2d(in_channels=512, out_channels=1, kernel_size=1, stride=1, padding=0) self.netScoreFiv = torch.nn.Conv2d(in_channels=512, out_channels=1, kernel_size=1, stride=1, padding=0) self.netCombine = torch.nn.Sequential( torch.nn.Conv2d(in_channels=5, out_channels=1, kernel_size=1, stride=1, padding=0), torch.nn.Sigmoid() ) self.load_state_dict({strKey.replace('module', 'net'): tenWeight for strKey, tenWeight in torch.load(model_path).items()}) def forward(self, tenInput): tenInput = tenInput * 255.0 tenInput = tenInput - torch.tensor(data=[104.00698793, 116.66876762, 122.67891434], dtype=tenInput.dtype, device=tenInput.device).view(1, 3, 1, 1) tenVggOne = self.netVggOne(tenInput) tenVggTwo = self.netVggTwo(tenVggOne) tenVggThr = self.netVggThr(tenVggTwo) tenVggFou = self.netVggFou(tenVggThr) tenVggFiv = self.netVggFiv(tenVggFou) tenScoreOne = self.netScoreOne(tenVggOne) tenScoreTwo = self.netScoreTwo(tenVggTwo) tenScoreThr = self.netScoreThr(tenVggThr) tenScoreFou = self.netScoreFou(tenVggFou) tenScoreFiv = self.netScoreFiv(tenVggFiv) tenScoreOne = torch.nn.functional.interpolate(input=tenScoreOne, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False) tenScoreTwo = torch.nn.functional.interpolate(input=tenScoreTwo, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False) tenScoreThr = torch.nn.functional.interpolate(input=tenScoreThr, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False) tenScoreFou = torch.nn.functional.interpolate(input=tenScoreFou, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False) tenScoreFiv = torch.nn.functional.interpolate(input=tenScoreFiv, size=(tenInput.shape[2], tenInput.shape[3]), mode='bilinear', align_corners=False) return self.netCombine(torch.cat([ tenScoreOne, tenScoreTwo, tenScoreThr, tenScoreFou, tenScoreFiv ], 1)) class HEDdetector: def __init__(self, netNetwork): self.netNetwork = netNetwork.eval() @classmethod def from_pretrained(cls, pretrained_model_or_path, filename=None, cache_dir=None): if pretrained_model_or_path == "lllyasviel/ControlNet": filename = filename or "annotator/ckpts/network-bsds500.pth" else: filename = filename or "network-bsds500.pth" model_path = hf_hub_download(pretrained_model_or_path, filename, cache_dir=cache_dir) netNetwork = Network(model_path) return cls(netNetwork) def __call__(self, input_image, detect_resolution=512, image_resolution=512, return_pil=True, scribble=False): device = next(iter(self.netNetwork.parameters())).device if not isinstance(input_image, np.ndarray): input_image = np.array(input_image, dtype=np.uint8) input_image = HWC3(input_image) input_image = resize_image(input_image, detect_resolution) assert input_image.ndim == 3 input_image = input_image[:, :, ::-1].copy() with torch.no_grad(): image_hed = torch.from_numpy(input_image).float() image_hed = image_hed.to(device) image_hed = image_hed / 255.0 image_hed = rearrange(image_hed, 'h w c -> 1 c h w') edge = self.netNetwork(image_hed)[0] edge = (edge.cpu().numpy() * 255.0).clip(0, 255).astype(np.uint8) detected_map = edge[0] detected_map = HWC3(detected_map) img = resize_image(input_image, image_resolution) H, W, C = img.shape detected_map = cv2.resize(detected_map, (W, H), interpolation=cv2.INTER_LINEAR) if scribble: detected_map = nms(detected_map, 127, 3.0) detected_map = cv2.GaussianBlur(detected_map, (0, 0), 3.0) detected_map[detected_map > 4] = 255 detected_map[detected_map < 255] = 0 if return_pil: detected_map = Image.fromarray(detected_map) return detected_map def nms(x, t, s): x = cv2.GaussianBlur(x.astype(np.float32), (0, 0), s) f1 = np.array([[0, 0, 0], [1, 1, 1], [0, 0, 0]], dtype=np.uint8) f2 = np.array([[0, 1, 0], [0, 1, 0], [0, 1, 0]], dtype=np.uint8) f3 = np.array([[1, 0, 0], [0, 1, 0], [0, 0, 1]], dtype=np.uint8) f4 = np.array([[0, 0, 1], [0, 1, 0], [1, 0, 0]], dtype=np.uint8) y = np.zeros_like(x) for f in [f1, f2, f3, f4]: np.putmask(y, cv2.dilate(x, kernel=f) == x, x) z = np.zeros_like(y, dtype=np.uint8) z[y > t] = 255 return z