Related
I am trying to convert an workbook I did some time ago on Colab (using ImageDataGenerator) to one that uses tf.data.dataset as I now have a multi-gpu set up and am trying to learn how to do faster training. The model trains on the age/ gender/ race dataset from Kaggle but in this instance we're interested in just the sex and age prediction. Sex will either be 0 or 1 and the loss function is binarycrossentropy while age is an integer between 0 and 120 and the loss function is mse at it is regression.
import tensorflow as tf
import os
AUTOTUNE = tf.data.AUTOTUNE
batch_size = 64
#Load datasets from directories
train_gen = tf.data.Dataset.list_files(os.listdir(training_dir), shuffle = False)
valid_gen = tf.data.Dataset.list_files(os.listdir(validation_dir), shuffle = False)
def decode_img(img):
#Convert compressed string into a 3D tensor
img = tf.io.decode_jpeg(img, channels=3)
img = tf.image.convert_image_dtype(img, tf.float32)
#Resize the image to the desired size
return tf.image.resize(img, [128,128])
def get_label(file):
gender = get_sex(file) #returns either 0 or 1
age = get_age(file) #returns interger between 0 and about 120
return gender, age
def process_path(file):
file = file.numpy()
file_path = str(bytes.decode(file))
file = file_path.split(' ')[-1].split("\\")[-1]
labels = get_label(file)
# Load data from file as a String
img = tf.io.read_file(file_path)
img = decode_img(img)
img = img / 255.0
return img, labels
def _set_shapes(t1, t2):
t1.set_shape((128,128,3))
t2.set_shape((2,))
return (t1,t2)
train_gen = train_gen.map(lambda x: tf.py_function(process_path, [x], [tf.float32, tf.int32]), num_parallel_calls=AUTOTUNE)
valid_gen = valid_gen.map(lambda x: tf.py_function(process_path, [x], [tf.float32, tf.int32]), num_parallel_calls=AUTOTUNE)
train_gen = train_gen.map(_set_shapes,num_parallel_calls=AUTOTUNE)
valid_gen = valid_gen.map(_set_shapes, num_parallel_calls=AUTOTUNE)
train_gen = train_gen.batch(batch_size)
valid_gen = valid_gen.batch(batch_size)
train_gen
Output: <BatchDataset shapes: ((None, 128, 128, 3), (None, 2)), types: (tf.float32, tf.int32)>
#configure for performance
def config_for_performance(ds):
ds = ds.cache()
ds = ds.prefetch(buffer_size=AUTOTUNE)
return ds
train_gen = config_for_performance(train_gen)
valid_gen = config_for_performance(valid_gen)
The model itself:
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Conv2D, MaxPool2D, Dense, Dropout, Input, Activation, Flatten, BatchNormalization, PReLU
from tensorflow.keras.regularizers import l2
from tensorflow.keras.losses import BinaryCrossentropy
from keras.callbacks import EarlyStopping, ReduceLROnPlateau
from tensorflow.keras import mixed_precision
mixed_precision.set_global_policy('mixed_float16')
gpus = tf.config.list_logical_devices('GPU')
#print(gpus)
strategy = tf.distribute.MirroredStrategy(gpus,cross_device_ops=tf.distribute.ReductionToOneDevice())
with strategy.scope():
#Define the convolution layers
inp = Input(shape=(128,128,3))
cl1 = Conv2D(32,(3,3), padding='same', kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(inp)
bn1 = BatchNormalization()(cl1)
pr1 = PReLU(alpha_initializer='he_uniform')(bn1)
cl2 = Conv2D(32,(3,3), padding='same',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(pr1)
bn2 = BatchNormalization()(cl2)
pr2 = PReLU(alpha_initializer='he_uniform')(bn2)
mp1 = MaxPool2D((2,2))(pr2)
cl3 = Conv2D(64,(3,3), padding='same',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(mp1)
bn3 = BatchNormalization()(cl3)
pr3 = PReLU(alpha_initializer='he_uniform')(bn3)
cl4 = Conv2D(64,(3,3), padding='same',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(pr3)
bn4 = BatchNormalization()(cl4)
pr4 = PReLU(alpha_initializer='he_uniform')(bn4)
mp2 = MaxPool2D((2,2))(pr4)
cl5 = Conv2D(128,(3,3), padding='same',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(mp2)
bn5 = BatchNormalization()(cl5)
pr5 = PReLU(alpha_initializer='he_uniform')(bn5)
mp3 = MaxPool2D((2,2))(pr5)
cl6 = Conv2D(256,(3,3), padding='same',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(mp3)
bn6 = BatchNormalization()(cl6)
pr6 = PReLU(alpha_initializer='he_uniform')(bn6)
mp4 = MaxPool2D((2,2))(pr6)
cl7 = Conv2D(512,(3,3), padding='same',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(mp4)
bn7 = BatchNormalization()(cl7)
pr7 = PReLU(alpha_initializer='he_uniform')(bn7)
mp5 = MaxPool2D((2,2))(pr7)
flt = Flatten()(mp5)
#This layer predicts age
agelayer = Dense(128, activation='relu',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(flt)
agelayer = BatchNormalization()(agelayer)
agelayer = Dropout(0.6)(agelayer)
agelayer = Dense(1, activation='relu', name='age_output', kernel_initializer='he_uniform', dtype='float32')(agelayer)
#This layer predicts gender
glayer = Dense(128, activation='relu',kernel_regularizer=l2(0.001), kernel_initializer='he_uniform')(flt)
glayer = BatchNormalization()(glayer)
glayer = Dropout(0.5)(glayer)
glayer = Dense(1, activation='sigmoid', name='gender_output', kernel_initializer='he_uniform', dtype='float32')(glayer)
modelA = Model(inputs=inp, outputs=[glayer,agelayer])
model_folder = 'C:/Users/mm/OneDrive/Documents/Age estimation & gender classification/models'
if not os.path.exists(model_folder):
os.mkdir(model_folder)
#Callback to control learning rate during training. Reduces learning rate by 5% after 3 epochs of no improvement on validation loss
lr_callback = ReduceLROnPlateau(monitor='val_loss', factor=0.95, patience=3,min_lr=0.000005)
#Callback to stop training if after 100 epochs of no improvement it stops and restores the best weights
es_callback = EarlyStopping(monitor='val_loss', patience=100, restore_best_weights=True, min_delta=0.001)
#Compile Model A
modelA.compile(optimizer='Adam', loss={'gender_output': BinaryCrossentropy(), 'age_output': 'mse'}, metrics={'gender_output': 'accuracy', 'age_output':'mae'})
#Training Model A
history = modelA.fit(train_gen, epochs=100, validation_data=valid_gen, callbacks=[es_callback,lr_callback])
The error message:
INFO:tensorflow:Using MirroredStrategy with devices ('/job:localhost/replica:0/task:0/device:GPU:0', '/job:localhost/replica:0/task:0/device:GPU:1')
Epoch 1/100
INFO:tensorflow:Error reported to Coordinator: logits and labels must have the same shape ((None, 1) vs (None, 2))
Traceback (most recent call last):
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\ops\nn_impl.py", line 130, in sigmoid_cross_entropy_with_logits
labels.get_shape().assert_is_compatible_with(logits.get_shape())
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\framework\tensor_shape.py", line 1161, in assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (None, 2) and (None, 1) are incompatible
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\training\coordinator.py", line 297, in stop_on_exception
yield
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\distribute\mirrored_run.py", line 346, in run
self.main_result = self.main_fn(*self.main_args, **self.main_kwargs)
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\autograph\impl\api.py", line 692, in wrapper
return converted_call(f, args, kwargs, options=options)
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\autograph\impl\api.py", line 382, in converted_call
return _call_unconverted(f, args, kwargs, options)
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\autograph\impl\api.py", line 463, in _call_unconverted
return f(*args, **kwargs)
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\keras\engine\training.py", line 835, in run_step
outputs = model.train_step(data)
show more (open the raw output data in a text editor) ...
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\util\dispatch.py", line 206, in wrapper
return target(*args, **kwargs)
File "C:\Users\mm\AppData\Roaming\Python\Python39\site-packages\tensorflow\python\ops\nn_impl.py", line 132, in sigmoid_cross_entropy_with_logits
raise ValueError("logits and labels must have the same shape (%s vs %s)" %
ValueError: logits and labels must have the same shape ((None, 1) vs (None, 2))
Managed to resove this with a bit of research and trial and error. Main issues are:
The labels are being fed to the model as a tuple instead of being separated. When it is multiple output heads this is necessary:
def process_path(file):
file = file.numpy()
file_path = str(bytes.decode(file))
file = file_path.split("\\")[-1]
gender, age = get_label(file)
# Load data from file as a String
img = tf.io.read_file(file_path)
img = decode_img(img)
img = img / 255.0
return img, gender, age
NB: I made a modification to extracting the labels from the filename as it wasn't getting it right all the time:
file = file_path.split("\\")[-1]
Due to the change on 1, the map functions need an additional dtype for the other label, so it becomes:
train_gen = train_gen.map(lambda x: tf.py_function(process_path, [x], [tf.float32, tf.int32, tf.int32]), num_parallel_calls=AUTOTUNE)
valid_gen = valid_gen.map(lambda x: tf.py_function(process_path, [x], [tf.float32, tf.int32, tf.int32]), num_parallel_calls=AUTOTUNE)
Each label needs to be reshaped:
def _set_shapes(t1, t2, t3):
t1.set_shape((128,128,3))
t2.set_shape((1,))
t3.set_shape((1,))
t2 = tf.reshape(t2, [-1,1])
t3 = tf.reshape(t3, [-1,1])
return (t1,t2,t3)
I am trying to build machine leaning program to compare between the images of Cat and dogs and have created TFRecords file successfully and now when i am trying to read the file for training, i am getting an error which is as given below.This is my code:
import tensorflow as tf
import numpy as np
import matplotlib.pyplot as plt
data_path = 'train.tfrecords'
with tf.Session() as sess:
feature = {'train/image': tf.FixedLenFeature([],tf.string),
'train/label': tf.FixedLenFeature([],tf.int64)}
filename_queue = tf.train.string_input_producer([data_path],num_epochs=1000)
reader = tf.TFRecordReader()
serialized_example = reader.read(queue=filename_queue,name=None)
features = tf.parse_single_example(serialized_example,features=feature)
image = tf.decode_raw(features['train/image'], tf.float32)
label = tf.cast(features['train/label'], tf.int32)
image = tf.reshape(image, [224, 224, 3])
images, labels = tf.train.shuffle_batch([image, label], batch_size=10, capacity=30, num_threads=1,
min_after_dequeue=10)
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for batch_index in range(5):
img, lbl = sess.run([images, labels])
img = img.astype(np.uint8)
for j in range(6):
plt.subplot(2, 3, j + 1)
plt.imshow(img[j, ...])
plt.title('cat' if lbl[j] == 0 else 'dog')
pl t.show()
coord.request_stop()
coord.join(threads)
sess.close()
I am getting this error
C:\Users\snklp\Anaconda3\envs\untitled\python.exe C/Users/snklp/PycharmProjects/untitled/read_tfrecords.py
2018-07-24 14:58:44.870802: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX AVX2
Traceback (most recent call last):
File "C:/Users/snklp/PycharmProjects/untitled/read_tfrecords.py", line 18, in <module>
serialized_example = tf.TFRecordReader.read(queue=filename_queue,name=None)
TypeError: read() missing 1 required positional argument: 'self'
Process finished with exit code 1
I tried to create a class Read with self argument in the read() function but nothing happened. I m am not getting this error. Can anybody help me in this???
I use Python 2.7.13 and Tensorflow 1.3.0 on CPU.
I want to use DensNet( https://github.com/pudae/tensorflow-densenet ) for regression problem. My data contains 60000 jpeg images with 37 float labels for each image.
I saved my data into tfrecords files by:
def Read_Labels(label_path):
labels_csv = pd.read_csv(label_path)
labels = np.array(labels_csv)
return labels[:,1:]
`
def load_image(addr):
# read an image and resize to (224, 224)
img = cv2.imread(addr)
img = cv2.resize(img, (224, 224), interpolation=cv2.INTER_CUBIC)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
img = img.astype(np.float32)
return img
def Shuffle_images_with_labels(shuffle_data, photo_filenames, labels):
if shuffle_data:
c = list(zip(photo_filenames, labels))
shuffle(c)
addrs, labels = zip(*c)
return addrs, labels
def image_to_tfexample_mine(image_data, image_format, height, width, label):
return tf.train.Example(features=tf.train.Features(feature={
'image/encoded': bytes_feature(image_data),
'image/format': bytes_feature(image_format),
'image/class/label': _float_feature(label),
'image/height': int64_feature(height),
'image/width': int64_feature(width),
}))
def _convert_dataset(split_name, filenames, labels, dataset_dir):
assert split_name in ['train', 'validation']
num_per_shard = int(math.ceil(len(filenames) / float(_NUM_SHARDS)))
with tf.Graph().as_default():
for shard_id in range(_NUM_SHARDS):
output_filename = _get_dataset_filename(dataset_path, split_name, shard_id)
with tf.python_io.TFRecordWriter(output_filename) as tfrecord_writer:
start_ndx = shard_id * num_per_shard
end_ndx = min((shard_id+1) * num_per_shard, len(filenames))
for i in range(start_ndx, end_ndx):
sys.stdout.write('\r>> Converting image %d/%d shard %d' % (
i+1, len(filenames), shard_id))
sys.stdout.flush()
img = load_image(filenames[i])
image_data = tf.compat.as_bytes(img.tostring())
label = labels[i]
example = image_to_tfexample_mine(image_data, image_format, height, width, label)
# Serialize to string and write on the file
tfrecord_writer.write(example.SerializeToString())
sys.stdout.write('\n')
sys.stdout.flush()
def run(dataset_dir):
labels = Read_Labels(dataset_dir + '/training_labels.csv')
photo_filenames = _get_filenames_and_classes(dataset_dir + '/images_training')
shuffle_data = True
photo_filenames, labels = Shuffle_images_with_labels(
shuffle_data,photo_filenames, labels)
training_filenames = photo_filenames[_NUM_VALIDATION:]
training_labels = labels[_NUM_VALIDATION:]
validation_filenames = photo_filenames[:_NUM_VALIDATION]
validation_labels = labels[:_NUM_VALIDATION]
_convert_dataset('train',
training_filenames, training_labels, dataset_path)
_convert_dataset('validation',
validation_filenames, validation_labels, dataset_path)
print('\nFinished converting the Flowers dataset!')
And I decode it by:
with tf.Session() as sess:
feature = {
'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
'image/format': tf.FixedLenFeature((), tf.string, default_value='jpeg'),
'image/class/label': tf.FixedLenFeature(
[37,], tf.float32, default_value=tf.zeros([37,], dtype=tf.float32)),
}
filename_queue = tf.train.string_input_producer([data_path], num_epochs=1)
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(serialized_example, features=feature)
image = tf.decode_raw(features['image/encoded'], tf.float32)
print(image.get_shape())
label = tf.cast(features['image/class/label'], tf.float32)
image = tf.reshape(image, [224, 224, 3])
images, labels = tf.train.shuffle_batch([image, label], batch_size=10, capacity=30, num_threads=1, min_after_dequeue=10)
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
for batch_index in range(6):
img, lbl = sess.run([images, labels])
img = img.astype(np.uint8)
print(img.shape)
for j in range(6):
plt.subplot(2, 3, j+1)
plt.imshow(img[j, ...])
plt.show()
coord.request_stop()
coord.join(threads)
It's all fine up to this point. But when I use the bellow commands for decoding TFRecord files:
reader = tf.TFRecordReader
keys_to_features = {
'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
'image/format': tf.FixedLenFeature((), tf.string, default_value='raw'),
'image/class/label': tf.FixedLenFeature(
[37,], tf.float32, default_value=tf.zeros([37,], dtype=tf.float32)),
}
items_to_handlers = {
'image': slim.tfexample_decoder.Image('image/encoded'),
'label': slim.tfexample_decoder.Tensor('image/class/label'),
}
decoder = slim.tfexample_decoder.TFExampleDecoder(
keys_to_features, items_to_handlers)
I get the following error.
INFO:tensorflow:Error reported to Coordinator: , assertion failed: [Unable to decode bytes as JPEG, PNG, GIF, or BMP]
[[Node: case/If_0/decode_image/cond_jpeg/cond_png/cond_gif/Assert_1/Assert = Assert[T=[DT_STRING], summarize=3, _device="/job:localhost/replica:0/task:0/cpu:0"](case/If_0/decode_image/cond_jpeg/cond_png/cond_gif/is_bmp, case/If_0/decode_image/cond_jpeg/cond_png/cond_gif/Assert_1/Assert/data_0)]]
INFO:tensorflow:Caught OutOfRangeError. Stopping Training.
INFO:sensorflow:Finished training! Saving model to disk.
To use Densenet for my problem, I should fix this error first.
Could anybody please help me out of this problem. This code works perfectly for the datasets like flowers, MNIST and CIFAR10 available at https://github.com/pudae/tensorflow-densenet/tree/master/datasets but does not work for my data.
Thanks to pudae, the problem is solved. I was needed to use:
image_data = tf.gfile.FastGFile(filenames[i], 'rb').read()
Instead of this for loading data. That works perfectly now.
img = load_image(filenames[i])
image_data = tf.compat.as_bytes(img.tostring())
According to the error, I think the problem is that you use an image decoder for array data (decoded data) because you saved decoded data when creating TFRecords. Maybe you have noticed, when you are not using slim, you use tf.decode_raw to decode the data. But when you use slim, the 'image/format': tf.FixedLenFeature((), tf.string, default_value='raw') is not used and by default, slim will use image decoder.
I believe you use the code in slim/data,
where format_key = 'image/format' is you need. So, like this:
keys_to_features = {
'image/encoded': tf.FixedLenFeature((), tf.string, default_value=''),
'image/format': tf.FixedLenFeature((), tf.string, default_value='raw'),
'image/class/label': tf.FixedLenFeature(
[1], tf.int64, default_value=tf.zeros([1], dtype=tf.int64)),
}
items_to_handlers = {
'image': tfexample_decoder.Image(
image_key = 'image/encoded',
format_key = 'image/format',
'label': tfexample_decoder.Tensor('image/class/label'),
}
decoder = tfexample_decoder.TFExampleDecoder(
keys_to_features, items_to_handlers)
But I am not sure this can solve your problem perfectly because I can't reproduce your work in my machine.
Maybe there is a problem with your image itself as follows：
In the context of creating and loading a .tfrecord file i encountered the following Problem:
Generating the dataset.tfrecord file
The Folder /Batch_manager/assets contains some *.tif Images that are used to generate a dataset.tfrecord file:
def _save_as_tfrecord(self, path, name):
self.__filename = os.path.join(path, name + '.tfrecord')
writer = tf.python_io.TFRecordWriter(self.__filename)
print('Writing', self.__filename)
for index, img in enumerate(self.load(get_iterator=True, n_images=1)):
img = img[0]
image_raw = img.tostring()
rows = img.shape[0]
cols = img.shape[1]
try:
depth = img.shape[2]
except IndexError:
depth = 1
example = tf.train.Example(features=tf.train.Features(feature={
'height': self._int64_feature(rows),
'width': self._int64_feature(cols),
'depth': self._int64_feature(depth),
'label': self._int64_feature(int(self.target[index])),
'image_raw': self._bytes_feature(image_raw)
}))
writer.write(example.SerializeToString())
writer.close()
Reading from the dataset.tfrecord file
Next i try to read from this file using where path directs towards the dataset.tfrecord file:
def dataset_input_fn(self, path):
dataset = tf.contrib.data.TFRecordDataset(path)
def parser(record):
keys_to_features = {
"height": tf.FixedLenFeature((), tf.int64, default_value=""),
"width": tf.FixedLenFeature((), tf.int64, default_value=""),
"depth": tf.FixedLenFeature((), tf.int64, default_value=""),
"label": tf.FixedLenFeature((), tf.int64, default_value=""),
"image_raw": tf.FixedLenFeature((), tf.string, default_value=""),
}
print(record)
features = tf.parse_single_example(record, features=keys_to_features)
print(features)
label = features['label']
height = features['height']
width = features['width']
depth = features['depth']
image = tf.decode_raw(features['image_raw'], tf.float32)
image = tf.reshape(image, [height, width, -1])
label = tf.cast(features["label"], tf.int32)
return {"image_raw": image, "height": height, "width": width, "depth":depth, "label":label}
dataset = dataset.map(parser)
dataset = dataset.shuffle(buffer_size=10000)
dataset = dataset.batch(32)
iterator = dataset.make_one_shot_iterator()
# `features` is a dictionary in which each value is a batch of values for
# that feature; `labels` is a batch of labels.
features = iterator.get_next()
return Features
Error message:
TypeError: Expected int64, got '' of type 'str' instead.
What is wrong with this Piece of code? I successfully validated that the dataset.tfrecord actually contains the correct Images and meta data!
The error happens because i copy and pasted this example which sets the values for all key-value pairs to an empty string, caused by default_value="". Removing that from all tf.FixedLenFeature fixed the issue.
I wrote a script to change MNIST data into TFRecord format:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
import numpy as np
def _init64_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]))
mnist = input_data.read_data_sets("/path/to/data", dtype=tf.uint8, one_hot=True)
images = mnist.train.images
labels = mnist.train.labels
num_examples = mnist.train.num_examples
num_shards = 10
instances_per_shard = int(num_examples / num_shards)
idx = 0
for i in range(num_shards):
filename = '/tmp/mnist/tfrecord-%.2d' % i
writer = tf.python_io.TFRecordWriter(filename)
for j in range(instances_per_shard):
example = tf.train.Example(features=tf.train.Features(feature={
'label': _bytes_feature(labels[idx].tostring()),
'image_raw': _bytes_feature(images[idx].tostring())
}))
writer.write(example.SerializeToString())
idx += 1
writer.close()
then read data from TFRecords files:
import tensorflow as tf
files = tf.train.match_filenames_once('/tmp/mnist/tfrecord-*')
filename_queue = tf.train.string_input_producer(files, shuffle=False)
reader = tf.TFRecordReader()
_, serialized_example = reader.read(filename_queue)
features = tf.parse_single_example(
serialized_example,
features={
'image_raw': tf.FixedLenFeature([], tf.string),
'label': tf.FixedLenFeature([], tf.string)
}
)
image = tf.decode_raw(features['image_raw'], tf.uint8)
decode_image = tf.reshape(image, [28, 28, 1])
label = features['label']
#label = tf.decode_raw(features['label'], tf.uint8)
#label = tf.reshape(label, [10])
batch_size = 4
capacity = 1000 + 3 * batch_size
example_batch, label_batch = tf.train.shuffle_batch([decode_image, label], batch_size=batch_size,
capacity=capacity, min_after_dequeue=30)
with tf.Session() as sess:
init_op = tf.group(tf.global_variables_initializer(), tf.local_variables_initializer())
sess.run(init_op)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for i in range(4):
cur_example_batch, cur_label_batch = sess.run([example_batch, label_batch])
print(cur_label_batch)
coord.request_stop()
coord.join(threads)
It runs all very well. But if I uncomment these two lines:
label = tf.decode_raw(features['label'], tf.uint8)
label = tf.reshape(label, [10])
I get the following error:
Caused by op 'shuffle_batch', defined at:
File "/home/chenk/workspace/tflearn/Learning/create_batch.py", line 27, in <module>
capacity=capacity, min_after_dequeue=30)
File "/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/input.py", line 1217, in shuffle_batch
name=name)
File "/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/training/input.py", line 788, in _shuffle_batch
dequeued = queue.dequeue_many(batch_size, name=name)
File "/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/data_flow_ops.py", line 457, in dequeue_many
self._queue_ref, n=n, component_types=self._dtypes, name=name)
File "/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/ops/gen_data_flow_ops.py", line 946, in _queue_dequeue_many_v2
timeout_ms=timeout_ms, name=name)
File "/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py", line 767, in apply_op
op_def=op_def)
File "/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 2506, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/opt/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py", line 1269, in __init__
self._traceback = _extract_stack()
OutOfRangeError (see above for traceback): RandomShuffleQueue '_1_shuffle_batch/random_shuffle_queue' is closed and has insufficient elements (requested 4, current size 0)
[[Node: shuffle_batch = QueueDequeueManyV2[component_types=[DT_UINT8, DT_UINT8], timeout_ms=-1, _device="/job:localhost/replica:0/task:0/cpu:0"](shuffle_batch/random_shuffle_queue, shuffle_batch/n)]]
Is there something wrong in my code? what is the right way to do this?
Thanks!
The mnist images are in uint8 but the labels are of type float64. When you write the tfrecords as to_string(), each float64 value will be converted to 8 bytes. So when you are reading the tfrecords you should reading it as tf.float64. Reading it as uint8 will produce 80 labels, and the error is actually caused by the reshape() function.
label = tf.decode_raw(features['label'], tf.float64)
label = tf.reshape(label, [10])