Spaces:
Runtime error
Runtime error
File size: 2,482 Bytes
c19ca42 |
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 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 |
import os
import cv2
import numpy as np
import torch
from huggingface_hub import hf_hub_download
from PIL import Image
from modules import devices
from modules.shared import opts
from modules.control.util import HWC3, resize_image
from .models.mbv2_mlsd_large import MobileV2_MLSD_Large
from .utils import pred_lines
class MLSDdetector:
def __init__(self, model):
self.model = model
@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/mlsd_large_512_fp32.pth"
else:
filename = filename or "mlsd_large_512_fp32.pth"
if os.path.isdir(pretrained_model_or_path):
model_path = os.path.join(pretrained_model_or_path, filename)
else:
model_path = hf_hub_download(pretrained_model_or_path, filename, cache_dir=cache_dir)
model = MobileV2_MLSD_Large()
model.load_state_dict(torch.load(model_path), strict=True)
model.eval()
return cls(model)
def to(self, device):
self.model.to(device)
return self
def __call__(self, input_image, thr_v=0.1, thr_d=0.1, detect_resolution=512, image_resolution=512, output_type="pil", **kwargs):
self.model.to(devices.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
img = input_image
img_output = np.zeros_like(img)
try:
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:
pass
detected_map = img_output[:, :, 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 output_type == "pil":
detected_map = Image.fromarray(detected_map)
if opts.control_move_processor:
self.model.to('cpu')
return detected_map
|