1,我想用CPU来处理DnCNN的去噪问题，请问有什么好的方法吗？ 2，为什么显示

Question

问题遇到的现象和发生背景

1,我想用CPU来处理DnCNN的去噪问题，请问有什么好的方法吗？ 2，为什么显示没有找到DnCNN model呢？如果想要添加DnCNNmodel应该在哪里添加呢？

问题相关代码，请勿粘贴截图

import os
import numpy as np
import argparse
import tensorflow as tf
import DnCNN

os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID"
os.environ["CUDA_VISIBLE_DEVICES"] = "0"

parser = argparse.ArgumentParser(decription="Tensorflow DnCNN Testing")
parser.add_argument("--epochs", default=50, type=int, help="Testing epochs")
parser.add_argument("--patch-size", default=40, type=int, help="patch size")
parser.add_argument("--c-dim", default=1, type=int, help="#of channels")
parser.add_argument("--batch-size", default=64, type=int, help="mini-batch size")
parser.add_argument("--lr", default=1e-3, type=float, help="Learning rate")
parser.add_argument("--lr-decay", default=30, type=int, help="Step of learning rate decay")
parser.add_argument("--weight-decay", default=1e-4, type=float, help="weight decay")
parser.add_argument("--sigma", default=25, type=int, help="noise level(default 25)")
parser.add_argument("--Testing-path", default='./desktop/Training_BrainImages_256x256_100.tfrecords', type=str,
help="path to Testingset")
parser.add_argument("--validate-dir", default='C:/Users/13145', type=str, help="path to Testingset")

opt = parser.parse_args()
opt.checkpoint_path = './' + opt.modale_name + '_checkpoints'

def main():
model = DnCNN()
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
model.Testing(sess, opt)

if name := 'main':
var = tf.app.run

运行结果及报错内容

2022-05-16 08:03:48.333941: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'cudart64_110.dll'; dlerror: cudart64_110.dll not found
2022-05-16 08:03:48.334140: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.
Traceback (most recent call last):
File "C:\Users\13145\Desktop\Test\full noise.py", line 29, in
import DnCNN
ModuleNotFoundError: No module named 'DnCNN'

Process finished with exit code 1

我的解答思路和尝试过的方法

我想要达到的结果

用CPU来基于DnCNN的方法处理给mat文件去噪的问题

Answer 1

DnCNN类在models模块中,需要这样导入from models import DnCNN，另外项目里的所有文件要按照原来的目录结构排列，然后进行操作。参考：
https://github.com/SaoYan/DnCNN-PyTorch