[英]Reading a new dataset in the same format as mnist dataset is read in TensorFlow
我有一個深度學習模型,必須輸入大小為100X100的圖像。 我的數據是
火車圖像x_train (530,100,100)
,火車標簽y_train (530,4)
,
測試圖片x_test(89,100,100)
,測試標簽y_test(89,4)
。
使用-讀取mnist數據集
mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
它會生成這樣的東西-
Datasets(train=tensorflow.contrib.learn.python.learn.datasets.mnist.DataSet object at 0x7fd64cae76a0,
validation=tensorflow.contrib.learn.python.learn.datasets.mnist.DataSet object at 0x7fd64cae7be0,
test=tensorflow.contrib.learn.python.learn.datasets.mnist.DataSet object at 0x7fd64cae7400)
我必須以相同的格式轉換數據,以便與我擁有的代碼一起使用。 請幫忙
epochs = 20
batch_size = 100
image_vector = 28*28
for i in range(epochs):
training_accuracy = []
epoch_loss = []
for ii in tqdm(range(mnist.train.num_examples // batch_size)):
batch = mnist.train.next_batch(batch_size)
images = batch[0].reshape((-1, 28, 28))
targets = batch[1]
c, _, a = session.run([model.cost, model.opt, model.accuracy], feed_dict={model.inputs: images, model.targets:targets})
epoch_loss.append(c)
training_accuracy.append(a)
print("Epoch: {}/{}".format(i, epochs), " | Current loss: {}".format(np.mean(epoch_loss)),
" | Training accuracy: {:.4f}%".format(np.mean(training_accuracy)))
編輯1:按照建議,我做了以下工作-
num_examples=271
batch_size=10
buffer_size=271
num_cpu_cores=4
dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
dataset = dataset.shuffle(buffer_size, reshuffle_each_iteration=True).repeat()
#dataset = dataset.apply(tf.data.batch( batch_size=batch_size, num_parallel_batches=num_cpu_cores))
#batch1=dataset.batch(10)
iterator = dataset.make_one_shot_iterator()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for ii in tqdm(range(num_examples // batch_size)):
batch = iterator.get_next()
images = batch[0]
targets = batch[1]
c, _, a = sess.run([model.cost, model.opt, model.accuracy])
epoch_loss.append(c)
training_accuracy.append(a)
print("Epoch: {}/{}".format(i, epochs), " | Current loss: {}".format(np.mean(epoch_loss)),
" | Training accuracy: {:.4f}%".format(np.mean(training_accuracy)))
圖像和目標不是批處理,而是單個圖像和標簽。
(,)
請建議如何批處理數據並將其輸入sess.run
編輯2:這是算法的整個代碼-
def LSTM_layer(lstm_cell_units, number_of_layers, batch_size, dropout_rate=0.8):
'''
This method is used to create LSTM layer/s for PixelRNN
Input(s): lstm_cell_unitis - used to define the number of units in a LSTM layer
number_of_layers - used to define how many of LSTM layers do we want in the network
batch_size - in this method this information is used to build starting state for the network
dropout_rate - used to define how many cells in a layer do we want to 'turn off'
Output(s): cell - lstm layer
init_state - zero vectors used as a starting state for the network
'''
#layer = tf.contrib.rnn.BasicLSTMCell(lstm_cell_units)
layer = tf.nn.rnn_cell.LSTMCell(lstm_cell_units,name='basic_lstm_cell')
if dropout_rate != 0:
layer = tf.contrib.rnn.DropoutWrapper(layer, dropout_rate)
cell = tf.contrib.rnn.MultiRNNCell([layer]*number_of_layers)
init_size = cell.zero_state(batch_size, tf.float32)
return cell, init_size
def rnn_output(lstm_outputs, input_size, output_size):
'''
Output layer for the lstm netowrk
Input(s): lstm_outputs - outputs from the RNN part of the network
input_size - in this case it is RNN size (number of neuros in RNN layer)
output_size - number of neuros for the output layer == number of classes
Output(s) - logits,
'''
outputs = lstm_outputs[:, -1, :]
weights = tf.Variable(tf.random_uniform([input_size, output_size]), name='rnn_out_weights')
bias = tf.Variable(tf.zeros([output_size]), name='rnn_out_bias')
output_layer = tf.matmul(outputs, weights) + bias
return output_layer
def loss_optimizer(rnn_out, targets, learning_rate):
'''
Function used to calculate loss and minimize it
Input(s): rnn_out - logits from the fully_connected layer
targets - targets used to train network
learning_rate/step_size
Output(s): optimizer - optimizer of choice
loss - calculated loss function
'''
loss = tf.nn.softmax_cross_entropy_with_logits(logits=rnn_out, labels=targets)
optimizer = tf.train.AdamOptimizer(learning_rate).minimize(loss)
return optimizer, loss
class PixelRNN(object):
def __init__(self, learning_rate=0.001, batch_size=10, classes=4, img_size = (129, 251), lstm_size=64,
number_of_layers=1, dropout_rate=0.6,clip_rate=None):
'''
PixelRNN - call this class to create whole model
Input(s): learning_rate - how fast are we going to move towards global minima
batch_size - how many samples do we feed at ones
classes - number of classes that we are trying to recognize
img_size - width and height of a single image
lstm_size - number of neurons in a LSTM layer
number_of_layers - number of RNN layers in the PixelRNN
dropout_rate - % of cells in a layer that we are stopping gradients to flow through
'''
#This placeholders are just for images
self.inputs = tf.placeholder(tf.float32, [None, img_size[0], img_size[1]], name='inputs')
self.targets = tf.placeholder(tf.int32, [None, classes], name='targets')
cell, init_state = LSTM_layer(lstm_size, number_of_layers, batch_size, dropout_rate)
outputs, states = tf.nn.dynamic_rnn(cell, self.inputs, initial_state=init_state)
rnn_out = rnn_output(outputs, lstm_size, classes)
self.opt, self.cost = loss_optimizer(rnn_out, self.targets, learning_rate)
predictions = tf.nn.softmax(rnn_out)
currect_pred = tf.equal(tf.cast(tf.round(tf.argmax(predictions, 1)), tf.int32), tf.cast(tf.argmax(self.targets, 1), tf.int32))
self.accuracy = tf.reduce_mean(tf.cast(currect_pred, tf.float32))
self.predictions = tf.argmax(tf.nn.softmax(rnn_out), 1)
tf.reset_default_graph()
model = PixelRNN()
num_examples=271
batch_size=10
buffer_size=271
num_cpu_cores=4
dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
dataset = dataset.shuffle(buffer_size, reshuffle_each_iteration=True).repeat()
#dataset = dataset.apply(tf.data.batch( batch_size=batch_size, num_parallel_batches=num_cpu_cores))
dataset = dataset.batch(10) # apply batch to dataset
iterator = dataset.make_one_shot_iterator() # create iterator
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for ii in tqdm(range(num_examples // batch_size)):
batch = iterator.get_next() #run iterator
images = batch[0]
targets = batch[1]
c, _, a = sess.run([model.cost, model.opt, model.accuracy],feed_dict={model.inputs: images, model.targets:targets})
epoch_loss.append(c)
training_accuracy.append(a)
print("Epoch: {}/{}".format(i, epochs), " | Current loss: {}".format(np.mean(epoch_loss)),
" | Training accuracy: {:.4f}%".format(np.mean(training_accuracy)))
當我按照建議進行操作時,出現以下錯誤-
TypeError:供稿的值不能是tf.Tensor對象。 可接受的feed值包括Python標量,字符串,列表,numpy ndarrays或TensorHandles。作為參考,張量對象是Tensor(“ IteratorGetNext:0”,shape =(?, 129,251),dtype = float32),該對象已傳遞給使用鍵Tensor(“ inputs:0”,shape =(?, 129,251),dtype = float32)的feed。
無法找出問題出在哪里
如果您的數據集為numpy數組或圖像文件列表,請使用from_tensor_slices
。 定義解析函數,如果使用文件名列表,則使用read_file
和decode_image
,否則只需應用任何預處理
def parse_image(filename, label):
file = tf.read_file(filename)
image = tf.image.decode_image(file)
#do any image/label preprocessing here
return image, label
然后定義數據集對象。 通常,將數據集的長度用作混洗緩沖區,但這可能取決於大小。 重復功能將控制時期(無值傳遞=不定迭代)。 如果不需要任何預處理,則將dataset.apply
行替換為dataset = dataset.batch(batch_size)
dataset = tf.data.Dataset.from_tensor_slices((x_train, y_train))
dataset = dataset_train.shuffle(buffer_size, reshuffle_each_iteration=True).repeat()
dataset = dataset.apply(tf.data.batch( batch_size=batch_size, num_parallel_batches=num_cpu_cores))
創建迭代器。 通常,如果僅輸入數組不會引起2GB graphdef限制,則無需使用feed dict。
iterator = dataset.make_one_shot_iterator()
batch = iterator.get_next()
編輯:您需要從數據集創建迭代器,這是整體結構:
dataset = dataset.batch(10) # apply batch to dataset
iterator = dataset.make_one_shot_iterator() # create iterator
batch = iterator.get_next() #run iterator
images = batch[0]
targets = batch[1]
logits = Model_function(images)
loss = loss_function(logits, targets)
train_op = optimizer.minimize()
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(steps):
sess.run(train_op)
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.