python - 将晦涩的文件类型输入到tensorflow中

Question

我目前正在尝试在 MRI 扫描图像上训练神经网络模型。这些图像采用 NIfTI (.nii) 文件格式，我不相信 TensorFlow 或 keras 具有固有的读取能力。我有一个 python 包，允许我在 python 中读取这些文件，但是我无法弄清楚如何将该包与 tensorflow 接口(interface)。我首先创建一个 tf.data.Dataset 对象，其中包含每个 MRI 扫描的路径，然后尝试使用 Dataset.map() 函数读取每个文件并创建图像、标签对的数据集。我的问题是 tf.data.Dataset 对象似乎将每个文件名存储在张量而不是字符串中，但是可以读取 .nii 文件类型的函数无法读取张量。有没有办法将文件路径字符串张量转换为可读字符串以允许我打开文件？如果没有，是否有更好的方法来创建数据集？

Answer 1

指定下面的代码，该代码出现在 Link 中由评论部分的“agrits”指定，以造福社区。

# Creates a .tfrecord file from a directory of nifti images.
#   This assumes your niftis are soreted into subdirs by directory, and a regex
#   can be written to match a volume-filenames and label-filenames
#
# USAGE
#  python ./genTFrecord.py <data-dir> <input-vol-regex> <label-vol-regex>
# EXAMPLE:
#  python ./genTFrecord.py ./buckner40 'norm' 'aseg' buckner40.tfrecords
#
# Based off of this: 
#   http://warmspringwinds.github.io/tensorflow/tf-slim/2016/12/21/tfrecords-guide/

# imports
import numpy as np
import tensorflow as tf
import nibabel as nib
import os, sys, re

def _bytes_feature(value):
    return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))

def _int64_feature(value):
    return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))

def select_hipp(x):
    x[x != 17] = 0
    x[x == 17] = 1
    return x

def crop_brain(x):
    x = x[90:130,90:130,90:130] #should take volume zoomed in on hippocampus area
    return x

def preproc_brain(x):
    x = select_hipp(x)
    x = crop_brain(x)   
    return x

def listfiles(folder):
    for root, folders, files in os.walk(folder):
        for filename in folders + files:
            yield os.path.join(root, filename)

def gen_filename_pairs(data_dir, v_re, l_re):
    unfiltered_filelist=list(listfiles(data_dir))
    input_list = [item for item in unfiltered_filelist if re.search(v_re,item)]
    label_list = [item for item in unfiltered_filelist if re.search(l_re,item)]
    print("input_list size:    ", len(input_list))
    print("label_list size:    ", len(label_list))
    if len(input_list) != len(label_list):
        print("input_list size and label_list size don't match")
        raise Exception
    return zip(input_list, label_list)

# parse args
data_dir = sys.argv[1]
v_regex  = sys.argv[2]
l_regex  = sys.argv[3]
outfile  = sys.argv[4]
print("data_dir:   ", data_dir)
print("v_regex:    ", v_regex )
print("l_regex:    ", l_regex )
print("outfile:    ", outfile )

# Generate a list of (volume_filename, label_filename) tuples
filename_pairs = gen_filename_pairs(data_dir, v_regex, l_regex)

# To compare original to reconstructed images
original_images = []

writer = tf.python_io.TFRecordWriter(outfile)
for v_filename, l_filename in filename_pairs:

    print("Processing:")
    print("  volume: ", v_filename)
    print("  label:  ", l_filename) 

    # The volume, in nifti format   
    v_nii = nib.load(v_filename)
    # The volume, in numpy format
    v_np = v_nii.get_data().astype('int16')
    # The volume, in raw string format
    v_np = crop_brain(v_np)
    # The volume, in raw string format
    v_raw = v_np.tostring()

    # The label, in nifti format
    l_nii = nib.load(l_filename)
    # The label, in numpy format
    l_np = l_nii.get_data().astype('int16')
    # Preprocess the volume
    l_np = preproc_brain(l_np)
    # The label, in raw string format
    l_raw = l_np.tostring()

    # Dimensions
    x_dim = v_np.shape[0]
    y_dim = v_np.shape[1]
    z_dim = v_np.shape[2]
    print("DIMS: " + str(x_dim) + str(y_dim) + str(z_dim))

    # Put in the original images into array for future check for correctness
    # Uncomment to test (this is a memory hog)
    ########################################
    # original_images.append((v_np, l_np))

    data_point = tf.train.Example(features=tf.train.Features(feature={
        'image_raw': _bytes_feature(v_raw),
        'label_raw': _bytes_feature(l_raw)}))

    writer.write(data_point.SerializeToString())

writer.close()