[모각코]2021-08-04

오늘할 일 : classification에 대해 공부 & 실습 예제

1. classification

• 머신러닝의 종류 중 Supervised Learning에서 사용되는 기존의 labeling된 데이터를 이용하여 데이터를 분류하는 일이다.

2. Monai 실습예제

1. 2D classification

import os
import shutil
import tempfile
import matplotlib.pyplot as plt
import PIL
import torch
import numpy as np
from sklearn.metrics import classification_report

from monai.apps import download_and_extract
from monai.config import print_config
from monai.data import decollate_batch
from monai.metrics import ROCAUCMetric
from monai.networks.nets import DenseNet121
from monai.transforms import (
    Activations,
    AddChannel,
    AsDiscrete,
    Compose,
    LoadImage,
    RandFlip,
    RandRotate,
    RandZoom,
    ScaleIntensity,
    EnsureType,
)
from monai.utils import set_determinism

print_config()


#set data directory

directory = os.environ.get("MONAI_DATA_DIRECTORY")
root_dir = tempfile.mkdtemp() if directory is None else directory
print(root_dir)

# Read image filenames from the dataset folders

class_names = sorted(x for x in os.listdir(data_dir)
                     if os.path.isdir(os.path.join(data_dir, x)))
num_class = len(class_names)
image_files = [
    [
        os.path.join(data_dir, class_names[i], x)
        for x in os.listdir(os.path.join(data_dir, class_names[i]))
    ]
    for i in range(num_class)
]
num_each = [len(image_files[i]) for i in range(num_class)]
image_files_list = []
image_class = []
for i in range(num_class):
    image_files_list.extend(image_files[i])
    image_class.extend([i] * num_each[i])
num_total = len(image_class)
image_width, image_height = PIL.Image.open(image_files_list[0]).size

print(f"Total image count: {num_total}")
print(f"Image dimensions: {image_width} x {image_height}")
print(f"Label names: {class_names}")
print(f"Label counts: {num_each}")

*** 많은 코드가 연결되어 있었지만 생략, vs코드 내에서 진행

2. 3D classification

# Read image filenames from the dataset folders


class IXIDataset(Randomizable, CacheDataset):
    resource = "http://biomedic.doc.ic.ac.uk/" \
        + "brain-development/downloads/IXI/IXI-T1.tar"
    md5 = "34901a0593b41dd19c1a1f746eac2d58"

    def __init__(
        self,
        root_dir,
        section,
        transform,
        download=False,
        seed=0,
        val_frac=0.2,
        test_frac=0.2,
        cache_num=sys.maxsize,
        cache_rate=1.0,
        num_workers=0,
    ):
        if not os.path.isdir(root_dir):
            raise ValueError("Root directory root_dir must be a directory.")
        self.section = section
        self.val_frac = val_frac
        self.test_frac = test_frac
        self.set_random_state(seed=seed)
        dataset_dir = os.path.join(root_dir, "ixi")
        tarfile_name = f"{dataset_dir}.tar"
        if download:
            download_and_extract(
                self.resource, tarfile_name, dataset_dir, self.md5)
        # as a quick demo, we just use 10 images to show

        self.datalist = [
            {"image": os.path.join(
                dataset_dir, "IXI314-IOP-0889-T1.nii.gz"), "label": 0},
            {"image": os.path.join(
                dataset_dir, "IXI249-Guys-1072-T1.nii.gz"), "label": 0},
            {"image": os.path.join(
                dataset_dir, "IXI609-HH-2600-T1.nii.gz"), "label": 0},
            {"image": os.path.join(
                dataset_dir, "IXI173-HH-1590-T1.nii.gz"), "label": 1},
            {"image": os.path.join(
                dataset_dir, "IXI020-Guys-0700-T1.nii.gz"), "label": 0},
            {"image": os.path.join(
                dataset_dir, "IXI342-Guys-0909-T1.nii.gz"), "label": 0},
            {"image": os.path.join(
                dataset_dir, "IXI134-Guys-0780-T1.nii.gz"), "label": 0},
            {"image": os.path.join(
                dataset_dir, "IXI577-HH-2661-T1.nii.gz"), "label": 1},
            {"image": os.path.join(
                dataset_dir, "IXI066-Guys-0731-T1.nii.gz"), "label": 1},
            {"image": os.path.join(
                dataset_dir, "IXI130-HH-1528-T1.nii.gz"), "label": 0},
        ]
        data = self._generate_data_list()
        super().__init__(
            data, transform, cache_num=cache_num,
            cache_rate=cache_rate, num_workers=num_workers,
        )

    def randomize(self, data=None):
        self.rann = self.R.random()

    def _generate_data_list(self):
        data = []
        for d in self.datalist:
            self.randomize()
            if self.section == "training":
                if self.rann < self.val_frac + self.test_frac:
                    continue
            elif self.section == "validation":
                if self.rann >= self.val_frac:
                    continue
            elif self.section == "test":
                if self.rann < self.val_frac or \
                        self.rann >= self.val_frac + self.test_frac:
                    continue
            else:
                raise ValueError(
                    f"Unsupported section: {self.section}, "
                    "available options are ['training', 'validation', 'test']."
                )
            data.append(d)
        return data
        
*** 많은 부분 생략, vscode_ipynb로 진행함