为了社区的利益,本文将翻译agrits在评论中提供的链接中包含的以下编程代码。
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]
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)
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 )
filename_pairs = gen_filename_pairs(data_dir, v_regex, l_regex)
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)
v_nii = nib.load(v_filename)
v_np = v_nii.get_data().astype('int16')
v_np = crop_brain(v_np)
v_raw = v_np.tostring()
l_nii = nib.load(l_filename)
l_np = l_nii.get_data().astype('int16')
l_np = preproc_brain(l_np)
l_raw = l_np.tostring()
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))
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()