File size: 4,487 Bytes
1239b39 |
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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 |
# This is an improved version and model of HED edge detection with Apache License, Version 2.0.
# Please use this implementation in your products
# This implementation may produce slightly different results from Saining Xie's official implementations,
# but it generates smoother edges and is more suitable for ControlNet as well as other image-to-image translations.
# Different from official models and other implementations, this is an RGB-input model (rather than BGR)
# and in this way it works better for gradio's RGB protocol
import os
import cv2
import torch
import numpy as np
from einops import rearrange
from annotator.util import annotator_ckpts_path
class DoubleConvBlock(torch.nn.Module):
def __init__(self, input_channel, output_channel, layer_number):
super().__init__()
self.convs = torch.nn.Sequential()
self.convs.append(torch.nn.Conv2d(in_channels=input_channel, out_channels=output_channel, kernel_size=(3, 3), stride=(1, 1), padding=1))
for i in range(1, layer_number):
self.convs.append(torch.nn.Conv2d(in_channels=output_channel, out_channels=output_channel, kernel_size=(3, 3), stride=(1, 1), padding=1))
self.projection = torch.nn.Conv2d(in_channels=output_channel, out_channels=1, kernel_size=(1, 1), stride=(1, 1), padding=0)
def __call__(self, x, down_sampling=False):
h = x
if down_sampling:
h = torch.nn.functional.max_pool2d(h, kernel_size=(2, 2), stride=(2, 2))
for conv in self.convs:
h = conv(h)
h = torch.nn.functional.relu(h)
return h, self.projection(h)
class ControlNetHED_Apache2(torch.nn.Module):
def __init__(self):
super().__init__()
self.norm = torch.nn.Parameter(torch.zeros(size=(1, 3, 1, 1)))
self.block1 = DoubleConvBlock(input_channel=3, output_channel=64, layer_number=2)
self.block2 = DoubleConvBlock(input_channel=64, output_channel=128, layer_number=2)
self.block3 = DoubleConvBlock(input_channel=128, output_channel=256, layer_number=3)
self.block4 = DoubleConvBlock(input_channel=256, output_channel=512, layer_number=3)
self.block5 = DoubleConvBlock(input_channel=512, output_channel=512, layer_number=3)
def __call__(self, x):
h = x - self.norm
h, projection1 = self.block1(h)
h, projection2 = self.block2(h, down_sampling=True)
h, projection3 = self.block3(h, down_sampling=True)
h, projection4 = self.block4(h, down_sampling=True)
h, projection5 = self.block5(h, down_sampling=True)
return projection1, projection2, projection3, projection4, projection5
class HEDdetector:
def __init__(self):
remote_model_path = "https://huggingface.co/lllyasviel/Annotators/resolve/main/ControlNetHED.pth"
modelpath = os.path.join(annotator_ckpts_path, "ControlNetHED.pth")
if not os.path.exists(modelpath):
from basicsr.utils.download_util import load_file_from_url
load_file_from_url(remote_model_path, model_dir=annotator_ckpts_path)
self.netNetwork = ControlNetHED_Apache2().float().cuda().eval()
self.netNetwork.load_state_dict(torch.load(modelpath))
def __call__(self, input_image):
assert input_image.ndim == 3
H, W, C = input_image.shape
with torch.no_grad():
image_hed = torch.from_numpy(input_image.copy()).float().cuda()
image_hed = rearrange(image_hed, 'h w c -> 1 c h w')
edges = self.netNetwork(image_hed)
edges = [e.detach().cpu().numpy().astype(np.float32)[0, 0] for e in edges]
edges = [cv2.resize(e, (W, H), interpolation=cv2.INTER_LINEAR) for e in edges]
edges = np.stack(edges, axis=2)
edge = 1 / (1 + np.exp(-np.mean(edges, axis=2).astype(np.float64)))
edge = (edge * 255.0).clip(0, 255).astype(np.uint8)
return edge
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
|