LiuZichen's picture
update
f460ce6
# 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 warnings
import cv2
import numpy as np
import torch
from einops import rearrange
from PIL import Image
from .util import HWC3, nms, resize_image_with_pad, safe_step, common_input_validate
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