Download face_segment.py from Saphyiera/face_detection: direct link, hf CLI and curl.
- Browser
- Download file 2.67 kB
-
https://huggingface.co/Saphyiera/face_detection/resolve/main/face_segment.py
- Command line
-
hf download hf://Saphyiera/face_detection/face_segment.py
-
curl -L -o face_segment.py https://huggingface.co/Saphyiera/face_detection/resolve/main/face_segment.py
2.67 kB
| import torch | |
| import torch.nn.functional as F | |
| import torchvision.transforms as T | |
| from bert.modeling_bert import BertModel | |
| from lib import segmentation | |
| import numpy as np | |
| class FaceSegment: | |
| def __init__( | |
| self, | |
| model_path: str, | |
| embedding_path: str = None, | |
| device: str = "cpu", | |
| img_size: int = 480, | |
| ): | |
| self.device = torch.device(device) | |
| self.transform = T.Compose([ | |
| T.Resize(img_size), | |
| T.ToTensor(), | |
| T.Normalize( | |
| mean=[0.485, 0.456, 0.406], | |
| std=[0.229, 0.224, 0.225] | |
| ) | |
| ]) | |
| token_ids = [101, 2529, 2132, 102] | |
| max_len = 20 | |
| padded = token_ids + [0] * (max_len - len(token_ids)) | |
| attn_mask = [1] * len(token_ids) + [0] * (max_len - len(token_ids)) | |
| self.sent_tensor = torch.tensor([padded], dtype=torch.long, device=self.device) | |
| self.mask_tensor = torch.tensor([attn_mask], dtype=torch.long, device=self.device) | |
| self.l_mask4seg = self.mask_tensor.unsqueeze(-1) | |
| class Opts: | |
| swin_type = "base" | |
| window12 = True | |
| mha = "" | |
| fusion_drop= 0.0 | |
| self.model_seg = segmentation.lavt(pretrained="", args=Opts()) | |
| self.model_seg.load_state_dict(torch.load(model_path, map_location="cpu")["model"]) | |
| self.model_seg.to(self.device).eval() | |
| if embedding_path: | |
| emb_data = torch.load(embedding_path, map_location=self.device) | |
| self.embedding = emb_data["embedding"].to(self.device) | |
| else: | |
| bert_ckpt = torch.load(model_path, map_location="cpu")["bert_model"] | |
| self.bert = BertModel.from_pretrained("bert-base-uncased") | |
| self.bert.pooler = None | |
| self.bert.load_state_dict(bert_ckpt) | |
| self.bert.to(self.device).eval() | |
| with torch.no_grad(): | |
| last_hidden = self.bert(self.sent_tensor, attention_mask=self.mask_tensor)[0] | |
| self.embedding = last_hidden.permute(0, 2, 1).contiguous() | |
| def get_face(self, image_pil): | |
| orig_w, orig_h = image_pil.size | |
| x = self.transform(image_pil).unsqueeze(0).to(self.device) | |
| with torch.no_grad(): | |
| out = self.model_seg(x, self.embedding, l_mask=self.l_mask4seg) | |
| out = out.argmax(dim=1, keepdim=True).float() | |
| out = F.interpolate(out, size=(orig_h, orig_w), mode="nearest") | |
| mask = (out.squeeze(0).squeeze(0).cpu().numpy() > 0).astype(np.uint8) * 255 | |
| rgb = np.array(image_pil, dtype=np.uint8) | |
| rgba = np.dstack([rgb, mask]) | |
| return rgba | |