环境配置
1.环境配置
conda create -n nnUNet python=3.7
conda activate nnUNet
切换下载源
#查看当前conda配置
conda config --show channels
#设置通道
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/free/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/msys2/
conda config --add channels https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/
#设置搜索是显示通道地址
conda config --set show_channel_urls yes
conda install pytorch torchvision cudatoolkit=10.0 # 删除安装命令最后的 -c pytorch,才会采用清华源安装。
前往下载服务器最适合的CUDA版本
conda install pytorch torchvision torchaudio cudatoolkit=11.3 -c pytorch
2. 安装hiddenlayer
pip install --upgrade git+https://github.com/nanohanno/hiddenlayer.git@bugfix/get_trace_graph#egg=hiddenlayer
3. 下载安装nnUNet
新建nnUNetFrame文件夹,将nnUNet拉到本地
git clone https://github.com/MIC-DKFZ/nnUNet.git
cd nnUNet
pip install -e .
检查torch CUDA是否可用,返回True代表可用
python
import torch
print(torch.cuda.is_available())
4. 设置nnUNet默认文件路径进入bashrc文件 vim ~/.bashrc
export nnUNet_raw_data_base="/home/hj/nnUNetFrame/DATASET/nnUNet_raw"
export nnUNet_preprocessed="/home/hj/nnUNetFrame/DATASET/nnUNet_preprocessed"
export RESULTS_FOLDER="/home/hj/nnUNetFrame/DATASET/nnUNet_trained_models"
source ~/.bashrc 保存并生效
训练自己的模型
1. 构建自己的数据集
在nnUNetFrame文件夹下新建DATASET文件夹以及nnUNet_raw文件夹,按照需要新建自己的任务数据集,命名规则需要使用 Task××_, ××是个两位数.然后再对应的文件夹下放入自己的数据,ImagesTr和labelsTr中必须要有数据!
所有的数据需要按照要求转成固定nii.gz的格式.如下图
2. 生成自己的dataset.json
import os
from batchgenerators.utilities.file_and_folder_operations import save_json, subfiles
from typing import Tuple
import numpy as np
def get_identifiers_from_splitted_files(folder: str):
uniques = np.unique([i[:-7] for i in subfiles(folder, suffix='.nii.gz', join=False)])
return uniques
def generate_dataset_json(output_file: str, imagesTr_dir: str, imagesTs_dir: str, modalities: Tuple,
labels: dict, dataset_name: str, license: str = "Hebut AI", dataset_description: str = "",
dataset_reference="oai-zib", dataset_release='11/2021'):
"""
:param output_file: This needs to be the full path to the dataset.json you intend to write, so
output_file='DATASET_PATH/dataset.json' where the folder DATASET_PATH points to is the one with the
imagesTr and labelsTr subfolders
:param imagesTr_dir: path to the imagesTr folder of that dataset
:param imagesTs_dir: path to the imagesTs folder of that dataset. Can be None
:param modalities: tuple of strings with modality names. must be in the same order as the images (first entry
corresponds to _0000.nii.gz, etc). Example: ('T1', 'T2', 'FLAIR').
:param labels: dict with int->str (key->value) mapping the label IDs to label names. Note that 0 is always
supposed to be background! Example: {0: 'background', 1: 'edema', 2: 'enhancing tumor'}
:param dataset_name: The name of the dataset. Can be anything you want
:param license:
:param dataset_description:
:param dataset_reference: website of the dataset, if available
:param dataset_release:
:return:
"""
train_identifiers = get_identifiers_from_splitted_files(imagesTr_dir)
if imagesTs_dir is not None:
test_identifiers = get_identifiers_from_splitted_files(imagesTs_dir)
else:
test_identifiers = []
json_dict = {}
json_dict['name'] = "Breast"
json_dict['description'] = "Breast"
json_dict['tensorImageSize'] = "3D"
json_dict['reference'] = dataset_reference
json_dict['licence'] = license
json_dict['release'] = dataset_release
json_dict['modality'] = {"0": "CT"}
json_dict['labels'] = {
"0": "background",
"1": "Breast"
}
json_dict['numTraining'] = len(train_identifiers)
json_dict['numTest'] = len(test_identifiers)
json_dict['training'] = [
{'image': "./imagesTr/%s.nii.gz" % i, "label": "./labelsTr/%s.nii.gz" % i} for i
in
train_identifiers]
json_dict['test'] = ["./imagesTs/%s.nii.gz" % i for i in test_identifiers]
output_file += "dataset.json"
if not output_file.endswith("dataset.json"):
print("WARNING: output file name is not dataset.json! This may be intentional or not. You decide. "
"Proceeding anyways...")
save_json(json_dict, os.path.join(output_file))
if __name__ == "__main__":
output_file = r'/home/hj/nnUNetFrame/DATASET/nnUNet_raw/nnUNet_raw_data/Task58_Breast/'
imagesTr_dir = r'/home/hj/nnUNetFrame/DATASET/nnUNet_raw/nnUNet_raw_data/Task58_Breast/imagesTr'
imagesTs_dir = r'/home/hj/nnUNetFrame/DATASET/nnUNet_raw/nnUNet_raw_data/Task58_Breast/imagesTs'
labelsTr = r'/home/hj/nnUNetFrame/DATASET/nnUNet_raw/nnUNet_raw_data/Task58_Breast/labelsTr'
modalities = '"0": "CT"'
labels = {
"0": "background",
"1": "Breast"
}
get_identifiers_from_splitted_files(output_file)
generate_dataset_json(output_file,
imagesTr_dir,
imagesTs_dir,
labelsTr,
modalities,
labels
)
3.转换自己的数据集
nnUNet_convert_decathlon_task -i /home/hj/nnUNetFrame/DATASET/nnUNet_raw/nnUNet_raw_data/Task58_Breast
4. 预处理数据
nnUNet_plan_and_preprocess -t 58
5.开始训练
nnUNet_train 3d_fullres nnUNetTrainerV2 58 4
nnUNet_train 3d_fullres nnUNetTrainerV2 58 4 -c 中间断了继续训练
自己的数据预测推理
nnUNet_predict -i /home/你的主机用户名/nnUNetFrame/DATASET/nnUNet_raw/nnUNet_raw_data/Task058_Breast/imagesTs/ -o /home/你的主机用户名/nnUNetFrame/DATASET/nnUNet_raw/nnUNet_raw_data/Task058_Breast/inferTs -t 8 -m 3d_fullres -f 4