File size: 1,672 Bytes
18dd6ad |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
# MLSD Line Detection
# From https://github.com/navervision/mlsd
# Apache-2.0 license
import cv2
import numpy as np
import torch
import os
from einops import rearrange
from .models.mbv2_mlsd_tiny import MobileV2_MLSD_Tiny
from .models.mbv2_mlsd_large import MobileV2_MLSD_Large
from .utils import pred_lines
from annotator.util import annotator_ckpts_path
remote_model_path = "https://huggingface.co/lllyasviel/Annotators/resolve/main/mlsd_large_512_fp32.pth"
class MLSDdetector:
def __init__(self):
model_path = os.path.join(annotator_ckpts_path, "mlsd_large_512_fp32.pth")
if not os.path.exists(model_path):
from basicsr.utils.download_util import load_file_from_url
load_file_from_url(remote_model_path, model_dir=annotator_ckpts_path)
model = MobileV2_MLSD_Large()
# model.load_state_dict(torch.load(model_path), strict=True)
# self.model = model.cuda().eval()
model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')), strict=True)
self.model = model.cpu().eval()
def __call__(self, input_image, thr_v, thr_d):
assert input_image.ndim == 3
img = input_image
img_output = np.zeros_like(img)
try:
with torch.no_grad():
lines = pred_lines(img, self.model, [img.shape[0], img.shape[1]], thr_v, thr_d)
for line in lines:
x_start, y_start, x_end, y_end = [int(val) for val in line]
cv2.line(img_output, (x_start, y_start), (x_end, y_end), [255, 255, 255], 1)
except Exception as e:
pass
return img_output[:, :, 0]
|