|
import os |
|
import warnings |
|
|
|
import cv2 |
|
import numpy as np |
|
import torch |
|
from huggingface_hub import hf_hub_download |
|
from PIL import Image |
|
|
|
from ..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, local_files_only=False): |
|
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, local_files_only=local_files_only) |
|
|
|
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): |
|
if "return_pil" in kwargs: |
|
warnings.warn("return_pil is deprecated. Use output_type instead.", DeprecationWarning) |
|
output_type = "pil" if kwargs["return_pil"] else "np" |
|
if type(output_type) is bool: |
|
warnings.warn("Passing `True` or `False` to `output_type` is deprecated and will raise an error in future versions") |
|
if output_type: |
|
output_type = "pil" |
|
|
|
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: |
|
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 |
|
|
|
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) |
|
|
|
return detected_map |
|
|
