How to split own data set to train and validation in Tensorflow CNN - tensorflow

Question

I'm using CNN Tensorflow code in --> https://www.tensorflow.org/tutorials/layers
I'm trying to run my own data instead MNIST dataset. Since I'm new in this area, I have many struggles with coding and errors :(
I made a file.txt which it's contained each image path in my computer and its label.I have 400 images, gray scale, 16x16.
Here it is the code:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import tensorflow as tf
...
from PIL import Image
import PIL.Image
#import imageflow
import os
import cv2
#import glob
import __main__ as _main_module
import matplotlib.pyplot as plt
from tensorflow.python.framework import ops
from tensorflow.python.framework import dtypes
from sklearn.model_selection import train_test_split
...
from tensorflow.contrib import learn
from tensorflow.contrib.learn.python.learn.estimators import model_fn as model_fn_lib
#tf.logging.set_verbosity(tf.logging.INFO)
#%%%%%%%%%%%%%%%%%%%%%% MY DATA %%%%%%%%%%%%%%%%%%%%%%%
def main(unused_argv):
path = 'C:/Users/.../ImageDir-Lables-01.txt'
filenames = []
labels = []
#Reading file and extracting paths and labels
with open(path, 'r') as File:
infoFile = File.readlines() #Reading all the lines from File
for line in infoFile: #Reading line-by-line
words = line.split() #Splitting lines in words using space character as separator
filenames.append(words[0])
labels.append(int(words[1]))
NumFiles = len(filenames)
print (NumFiles)
#Converting filenames and labels into tensors
tfilenames = ops.convert_to_tensor(filenames, dtype=dtypes.string)
tlabels = ops.convert_to_tensor(labels, dtype=dtypes.int32)
#Creating a queue which contains the list of files to read and the value of the labels
filename_queue = tf.train.slice_input_producer([tfilenames, tlabels],
num_epochs=10,
shuffle=True,
capacity=NumFiles)
#Reading the image files and decoding them
rawIm= tf.read_file(filename_queue[0])
decodedIm = tf.image.decode_image(rawIm) # png or jpg decoder
#Extracting the labels queue
label_queue = filename_queue[1]
#Initializing Global and Local Variables so we avoid warnings and errors
init_op = tf.group(tf.local_variables_initializer() ,tf.global_variables_initializer())
#Creating an InteractiveSession so we can run in iPython
sess = tf.InteractiveSession()
with sess.as_default():
sess.run(init_op)
# Start populating the filename queue.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for i in range(NumFiles): #length of your filenames list
nm, image, lb = sess.run([filename_queue[0], decodedIm, label_queue])
print (image.shape)
print (nm)
print (lb)
#Showing the current image
jpgfile = Image.open(nm)
jpgfile.show()
coord.request_stop()
coord.join(threads)
train_data, train_labels, eval_data, eval_labels =
tf.train_split([filename_queue[0], filename_queue[1]], frac=.1)
# train_data, eval_data, train_labels, eval_labels =
train_test_split([filename_queue[0], filename_queue[1]], frac=0.2)
# train_data, train_labels, eval_data, eval_labels =
tf.split(tf.random_shuffle(filename_queue[0], filename_queue[1],
frac=0.25))
return train_data, train_labels, eval_data, eval_labels
print (train_data.shape)
###########################################
# Create the Estimator
Xray_classifier = learn.Estimator(model_fn=cnn_model_fn, model_dir="/tmp/Xray_convnet_model")
###########################################
# Set up logging for predictions
# Log the values in the "Softmax" tensor with label "probabilities"
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(
tensors=tensors_to_log, every_n_iter=50)
# Train the model
Xray_classifier.fit(
x=train_data,
y=train_labels,
batch_size=10,
steps=20000,
monitors=[logging_hook])
# Configure the accuracy metric for evaluation
metrics = {
"accuracy":
learn.MetricSpec(
metric_fn=tf.metrics.accuracy, prediction_key="classes"),
}
# Evaluate the model and print results
eval_results = Xray_classifier.evaluate(
x=eval_data, y=eval_labels, metrics=metrics)
print(eval_results)
# Our application logic will be added here
if __name__ == "__main__":
tf.app.run()
I used 3 different codes to divide my dataset. I used --> train_data, train_labels, eval_data, eval_labels = tf.train_split(image, lb, frac=.1)
it gives this error --> AttributeError: module 'tensorflow' has no attribute 'train_split'
when I used --> train_data, eval_data, train_labels, eval_labels = train_test_split([filename_queue[0], filename_queue[1]], frac=0.2)
it gives the error--> TypeError: Invalid parameters passed: {'frac': 0.2}
When I used--> train_data, train_labels, eval_data, eval_labels = tf.split(tf.random_shuffle(filename_queue[0], filename_queue[1], frac=0.25))
It gives this error --> TypeError: random_shuffle() got an unexpected keyword argument 'frac'
Does someone have an idea what should I write for splitting?
Any help would be appreciated. Thank you

Answer 1

You can use http://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html Scikit Learn's train_test_split function.