阿里开源黑白图片上色算法DDColor的部署与测试并将模型转onnx后用c++推理

阿里开源黑白图片上色算法DDColor的部署与测试并将模型转onnx后用c++推理

简介

DDColor是一种基于深度学习的图像上色技术，它利用卷积神经网络（CNN）对黑白图像进行上色处理。该模型通常包含一个编码器和一个解码器，编码器提取图像的特征，解码器则根据这些特征生成颜色。DDColor模型能够处理多种类型的图像，并生成自然且逼真的颜色效果。它在图像编辑、电影后期制作以及历史照片修复等领域有广泛的应用。

环境部署

下载源码

git clone https://github.com/piddnad/DDColor.git

安装环境

conda create -n ddcolor python=3.9
conda activate ddcolor
pip install -r requirements.txt
python3 setup.py develop
pip install modelscope
pip install onnx
pip install onnxruntime

下载模型

这里下载
或者运行下面的脚本下载：

from modelscope.hub.snapshot_download import snapshot_download
model_dir = snapshot_download('damo/cv_ddcolor_image-colorization', cache_dir='./modelscope')
print('model assets saved to %s'%model_dir)
#模型会被下载到modelscope/damo/cv_ddcolor_image-colorization/pytorch_model.pt

测试一下

import argparse
import cv2
import numpy as np
import os
from tqdm import tqdm
import torch
from basicsr.archs.ddcolor_arch import DDColor
import torch.nn.functional as F

class ImageColorizationPipeline(object):

    def __init__(self, model_path, input_size=256, model_size='large'):

        self.input_size = input_size
        if torch.cuda.is_available():
            self.device = torch.device('cuda')
        else:
            self.device = torch.device('cpu')

        if model_size == 'tiny':
            self.encoder_name = 'convnext-t'
        else:
            self.encoder_name = 'convnext-l'

        self.decoder_type = "MultiScaleColorDecoder"

        if self.decoder_type == 'MultiScaleColorDecoder':
            self.model = DDColor(
                encoder_name=self.encoder_name,
                decoder_name='MultiScaleColorDecoder',
                input_size=[self.input_size, self.input_size],
                num_output_channels=2,
                last_norm='Spectral',
                do_normalize=False,
                num_queries=100,
                num_scales=3,
                dec_layers=9,
            ).to(self.device)
        else:
            self.model = DDColor(
                encoder_name=self.encoder_name,
                decoder_name='SingleColorDecoder',
                input_size=[self.input_size, self.input_size],
                num_output_channels=2,
                last_norm='Spectral',
                do_normalize=False,
                num_queries=256,
            ).to(self.device)

        self.model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu'))['params'],strict=False)
        self.model.eval()

    @torch.no_grad()
    def process(self, img):
        self.height, self.width = img.shape[:2]
        # print(self.width, self.height)
        # if self.width * self.height < 100000:
        #     self.input_size = 256

        img = (img / 255.0).astype(np.float32)
        orig_l = cv2.cvtColor(img, cv2