制作tfrecord并读取
import os
import tensorflow as tf
import numpy as np
import pandas as pd
import skimage.io as io
import matplotlib.pyplot as plt
def get_data (filename):
class_train = []
label_train = []
label_data = pd.read_csv('./breastpathq/datasets/train_labels.csv')
label_data.sort_values(by=['rid', 'slide'], ascending=True)
for item in label_data['y']:
if item == 0.0:
label_train.append(0)
elif item > 0.0 and item <= 0.1:
label_train.append(1)
elif item > 0.1 and item <= 0.2:
label_train.append(2)
elif item > 0.2 and item <= 0.3:
label_train.append(3)
elif item > 0.3 and item <= 0.4:
label_train.append(4)
elif item > 0.4 and item <= 0.6:
label_train.append(5)
elif item > 0.6 and item <= 0.8:
label_train.append(6)
elif item > 0.8 and item <= 0.9:
label_train.append(7)
elif item > 0.9 and item < 1:
label_train.append(8)
else:
label_train.append(9)
for i in range(label_data.shape[0]):
class_train.append(
filename + str(int(label_data.ix[i]['slide'])) + '_' + str(int(label_data.ix[i]['rid'])) + '.tif')
print(label_train)
print(class_train)
# label_train = tf.one_hot(label_train, depth=10, on_value=0, off_value=1, axis=-1)
temp = np.array([class_train, label_train])
temp = temp.transpose()
print(temp)
np.random.shuffle(temp)
# temp = {class_train: label_train}
image_list = list(temp[:,0])
label_list = list(temp[:,1])
# image_list = list(temp.keys())
# label_list = list(temp.values())
label_list = [int(float(i)) for i in label_list]
return image_list,label_list
# 转化成字符串
def _int64_feature(value):
return tf.train.Feature(int64_list=tf.train.Int64List(value=[value]))
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value]))
def convert_tfrecord(images,labels,save_filename):
writer = tf.python_io.TFRecordWriter(save_filename)
print("Transform start....")
num_examples= len(labels)
if np.shape(images)[0]!=num_examples:
raise ValueError('Images size %d does not match label size %d.' % (images.shape[0], num_examples))
for index in np.arange(0,num_examples):
try:
image = io.imread(images[index],as_grey=False)
#image = tf.image.decode_jpeg(images[index])
#print(image.shape)
image_raw = image.tostring()
#print(len(image_raw))
example = tf.train.Example(features = tf.train.Features(feature={
'label' :_int64_feature(int(labels[index])),
'image_raw':_bytes_feature(image_raw)
}))
writer.write(example.SerializeToString())
except IOError as e:
print('Could not read:',images[index])
print('error :%s Skip it !\n'%e)
writer.close()
print("success!")
def read_and_decodes(tfrecords_file,batch_size):
reader = tf.TFRecordReader()
filename_queue = tf.train.string_input_producer([tfrecords_file])
_,serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
features={
'label': tf.FixedLenFeature([],tf.int64),
'image_raw': tf.FixedLenFeature([], tf.string)
}
)
#print(features['image_raw'])
capacity = 1000+3*batch_size
image = tf.decode_raw(features['image_raw'],tf.uint8)
#wuhong
label = tf.one_hot(features['label'], depth=10, on_value=1, off_value=0, axis=-1)
label = tf.cast(label, tf.int32)
#原始的
# label = tf.cast(features['label'],tf.int32)
#image = tf.image.resize_images(image,[300, 200, 1])
image = tf.reshape(image,[512,512,3])
image_batch,label_batch = tf.train.batch([image,label],
batch_size=batch_size,
capacity=capacity)
# image_batch = tf.image.resize_image_with_crop_or_pad(image_batch,512,512)
image_batch = tf.cast(image_batch, tf.float32) * (1. / 255)
return image_batch,label_batch
def plot_images(images, labels):
'''plot one batch size
'''
for i in np.arange(0, 2):
plt.subplot(3, 3, i + 1)
plt.axis('off')
# plt.title((labels[i] - 1), fontsize = 14)
plt.subplots_adjust(top=1)
print(labels[i])
print(images.shape)
# print(images[i].shape)
plt.imshow(images[i][:,:,:])
plt.show()
def train():
# image,label = get_data('./breastpathq/datasets/train/')
# convert_tfrecord(image,label,'2.tfrecords')
x_batch, y_batch = read_and_decodes('2.tfrecords', batch_size=128)
with tf.Session() as sess:
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
try:
i=0
while not coord.should_stop() and i<3:
# just plot one batch size
image, label = sess.run([x_batch, y_batch])
plot_images(image, label)
i+=1
except tf.errors.OutOfRangeError:
print('done!')
finally:
coord.request_stop()
coord.join(threads)
if __name__ == "__main__":
train()
tensorflow官网上的example：
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import argparse
import os.path
import sys
import time
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import mnist
# Basic model parameters as external flags.
FLAGS = None
# Constants used for dealing with the files, matches convert_to_records.
TRAIN_FILE = 'train.tfrecords'
VALIDATION_FILE = 'validation.tfrecords'
def read_and_decode(filename_queue):
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
# Defaults are not specified since both keys are required.
features={
'image_raw': tf.FixedLenFeature([], tf.string),
'label': tf.FixedLenFeature([], tf.int64),
})
# Convert from a scalar string tensor (whose single string has
# length mnist.IMAGE_PIXELS) to a uint8 tensor with shape
# [mnist.IMAGE_PIXELS].
image = tf.decode_raw(features['image_raw'], tf.uint8)
image.set_shape([mnist.IMAGE_PIXELS])
# OPTIONAL: Could reshape into a 28x28 image and apply distortions
# here. Since we are not applying any distortions in this
# example, and the next step expects the image to be flattened
# into a vector, we don't bother.
# Convert from [0, 255] -> [-0.5, 0.5] floats.
image = tf.cast(image, tf.float32) * (1. / 255) - 0.5
# Convert label from a scalar uint8 tensor to an int32 scalar.
label = tf.cast(features['label'], tf.int32)
return image, label
def inputs(train, batch_size, num_epochs):
"""Reads input data num_epochs times.
Args:
train: Selects between the training (True) and validation (False) data.
batch_size: Number of examples per returned batch.
num_epochs: Number of times to read the input data, or 0/None to
train forever
Returns:
A tuple (images, labels), where:
* images is a float tensor with shape [batch_size, mnist.IMAGE_PIXELS]
in the range [-0.5, 0.5].
* labels is an int32 tensor with shape [batch_size] with the true label,
a number in the range [0, mnist.NUM_CLASSES).
Note that an tf.train.QueueRunner is added to the graph, which
must be run using e.g. tf.train.start_queue_runners().
"""
if not num_epochs: num_epochs = None
filename = os.path.join(FLAGS.train_dir,
TRAIN_FILE if train else VALIDATION_FILE)
with tf.name_scope('input'):
filename_queue = tf.train.string_input_producer(
[filename], num_epochs=num_epochs)
# Even when reading in multiple threads, share the filename
# queue.
image, label = read_and_decode(filename_queue)
# Shuffle the examples and collect them into batch_size batches.
# (Internally uses a RandomShuffleQueue.)
# We run this in two threads to avoid being a bottleneck.
images, sparse_labels = tf.train.shuffle_batch(
[image, label], batch_size=batch_size, num_threads=2,
capacity=1000 + 3 * batch_size,
# Ensures a minimum amount of shuffling of examples.
min_after_dequeue=1000)
return images, sparse_labels
def run_training():
"""Train MNIST for a number of steps."""
# Tell TensorFlow that the model will be built into the default Graph.
with tf.Graph().as_default():
# Input images and labels.
images, labels = inputs(train=True, batch_size=FLAGS.batch_size,
num_epochs=FLAGS.num_epochs)
# Build a Graph that computes predictions from the inference model.
logits = mnist.inference(images,
FLAGS.hidden1,
FLAGS.hidden2)
# Add to the Graph the loss calculation.
loss = mnist.loss(logits, labels)
# Add to the Graph operations that train the model.
train_op = mnist.training(loss, FLAGS.learning_rate)
# The op for initializing the variables.
init_op = tf.group(tf.global_variables_initializer(),
tf.local_variables_initializer())
# Create a session for running operations in the Graph.
sess = tf.Session()
# Initialize the variables (the trained variables and the
# epoch counter).
sess.run(init_op)
# Start input enqueue threads.
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
try:
step = 0
while not coord.should_stop():
start_time = time.time()
# Run one step of the model. The return values are
# the activations from the `train_op` (which is
# discarded) and the `loss` op. To inspect the values
# of your ops or variables, you may include them in
# the list passed to sess.run() and the value tensors
# will be returned in the tuple from the call.
_, loss_value = sess.run([train_op, loss])
duration = time.time() - start_time
# Print an overview fairly often.
if step % 100 == 0:
print('Step %d: loss = %.2f (%.3f sec)' % (step, loss_value,
duration))
step += 1
except tf.errors.OutOfRangeError:
print('Done training for %d epochs, %d steps.' % (FLAGS.num_epochs, step))
finally:
# When done, ask the threads to stop.
coord.request_stop()
# Wait for threads to finish.
coord.join(threads)
sess.close()
def main(_):
run_training()
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument(
'--learning_rate',
type=float,
default=0.01,
help='Initial learning rate.'
)
parser.add_argument(
'--num_epochs',
type=int,
default=2,
help='Number of epochs to run trainer.'
)
parser.add_argument(
'--hidden1',
type=int,
default=128,
help='Number of units in hidden layer 1.'
)
parser.add_argument(
'--hidden2',
type=int,
default=32,
help='Number of units in hidden layer 2.'
)
parser.add_argument(
'--batch_size',
type=int,
default=100,
help='Batch size.'
)
parser.add_argument(
'--train_dir',
type=str,
default='/tmp/data',
help='Directory with the training data.'
)
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)在模型中读取tfrecord
def train():
x_batch, y_batch = read_and_decodes('2.tfrecords', batch_size=32)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
merged = tf.summary.merge_all()
train_writer = tf.summary.FileWriter(_SAVE_BOARD_PATH, sess.graph)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
try:
while not coord.should_stop():
batch_xs, batch_ys = sess.run([x_batch, y_batch])
start_time = time()
i_global, _ = sess.run([global_step, optimizer], feed_dict={x: batch_xs, y: batch_ys})
duration = time() - start_time
_loss, batch_acc = sess.run([loss, accuracy], feed_dict={x: batch_xs, y: batch_ys})
msg = "Glo bal Step: {0:>6}, accuracy: {1:>6.1%}, loss = {2:.2f} ({3:.1f} examples/sec, {4:.2f} sec/batch)"
print(msg.format(i_global, batch_acc, _loss, _BATCH_SIZE / duration, duration))
resultmerged = sess.run(merged, feed_dict={x: batch_xs, y: batch_ys})
train_writer.add_summary(resultmerged, i_global)
if (i_global % 100 == 0):
saver.save(sess, save_path=_SAVE_PATH, global_step=global_step)
print("Saved checkpoint")