How to read next batch in tensorflow automatically? - tensorflow

Question

I have 70 training sample, 10 testing samples, with every sample contains 11*99 elements. I want to use LSTM to classify the testing samples, here is the code:
import tensorflow as tf
import scipy.io as sc
# data read
feature_training = sc.loadmat("feature_training_reshaped.mat")
feature_training_reshaped = feature_training['feature_training_reshaped']
print (feature_training_reshaped.shape)
feature_testing = sc.loadmat("feature_testing_reshaped.mat")
feature_testing_reshaped = feature_testing['feature_testing_reshaped']
print (feature_testing_reshaped.shape)
label_training = sc.loadmat("label_training.mat")
label_training = label_training['aa']
print (label_training.shape)
label_testing = sc.loadmat("label_testing.mat")
label_testing = label_testing['label_testing']
print (label_testing.shape)
a=feature_training_reshaped.reshape([70, 11, 99])
b=feature_testing_reshaped.reshape([10, 11, 99])
print (a.shape)
# hyperparameters
lr = 0.001
training_iters = 1000
batch_size = 70
n_inputs = 99 # MNIST data input (img shape: 11*99)
n_steps = 11 # time steps
n_hidden_units = 128 # neurons in hidden layer
n_classes = 2 # MNIST classes (0-9 digits)
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_classes])
# Define weights
weights = {
# (28, 128)
'in': tf.Variable(tf.random_normal([n_inputs, n_hidden_units])),
# (128, 10)
'out': tf.Variable(tf.random_normal([n_hidden_units, n_classes]))
}
biases = {
# (128, )
'in': tf.Variable(tf.constant(0.1, shape=[n_hidden_units, ])),
# (10, )
'out': tf.Variable(tf.constant(0.1, shape=[n_classes, ]))
}
def RNN(X, weights, biases):
# hidden layer for input to cell
########################################
# all the data in this batch flow into this layer in one time
# transpose the inputs shape from 70batch, 11steps,99inputs
# X ==> (70 batch * 11 steps, 99 inputs)
X = tf.reshape(X, [-1, n_inputs])
# into hidden
# X_in = (70 batch * 11 steps, 99 inputs)
X_in = tf.matmul(X, weights['in']) + biases['in']
# another shape transpose X_in ==> (70 batch, 11 steps, 128 hidden),
X_in = tf.reshape(X_in, [-1, n_steps, n_hidden_units])
# cell
##########################################
# basic LSTM Cell.
lstm_cell = tf.nn.rnn_cell.BasicLSTMCell(n_hidden_units, forget_bias=1.0, state_is_tuple=True)
# lstm cell is divided into two parts (c_state, h_state)
##### TAKE Care, batch_size should be 10 when the testing dataset only has 10 data
_init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32)
print ("_init_state:", _init_state)
# You have 2 options for following step.
# 1: tf.nn.rnn(cell, inputs);
# 2: tf.nn.dynamic_rnn(cell, inputs).
# If use option 1, you have to modified the shape of X_in, go and check out this:
# https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/3_NeuralNetworks/recurrent_network.py
# In here, we go for option 2.
# dynamic_rnn receive Tensor (batch, steps, inputs) or (steps, batch, inputs) as X_in.
# Make sure the time_major is changed accordingly.
outputs, final_state = tf.nn.dynamic_rnn(lstm_cell, X_in, initial_state=_init_state, time_major=False)
# outputs size would be a tensor [70,11,128]; size of X_in is (70 batch, 11 steps, 128 hidden)
# final_state size would be [batch_size, outputs],which is [70,128]
print (outputs)
print (final_state)
# hidden layer for output as the final results
#############################################
results = tf.matmul(final_state[1], weights['out']) + biases['out']
# # or
# unpack to list [(batch, outputs)..] * steps
# outputs = tf.unpack(tf.transpose(outputs, [1, 0, 2])) # states is the last outputs
# results = tf.matmul(outputs[-1], weights['out']) + biases['out']
return results
pred = RNN(x, weights, biases)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(pred, y))
train_op = tf.train.AdamOptimizer(lr).minimize(cost)
correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
init = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init)
step = 0
while step * batch_size < training_iters:
# batch_xs, batch_ys = fea.next_batch(batch_size)
# batch_xs = batch_xs.reshape([batch_size, n_steps, n_inputs])
sess.run([train_op], feed_dict={
x: a,
y: label_training,
})
if step % 10 == 0:
print(sess.run(accuracy, feed_dict={
x: b,
y: label_testing,
}))
step += 1
At last, I got the result & error:
(770, 99)
(110, 99)
(70, 2)
(10, 2)
(70, 11, 99)
('_init_state:', LSTMStateTuple(c=<tf.Tensor 'zeros:0' shape=(70, 128) dtype=float32>, h=<tf.Tensor 'zeros_1:0' shape=(70, 128) dtype=float32>))
Tensor("RNN/transpose:0", shape=(70, 11, 128), dtype=float32)
LSTMStateTuple(c=<tf.Tensor 'RNN/while/Exit_2:0' shape=(70, 128) dtype=float32>, h=<tf.Tensor 'RNN/while/Exit_3:0' shape=(70, 128) dtype=float32>)
Traceback (most recent call last):
File "/home/xiangzhang/RNN.py", line 150, in <module>
y: label_testing,
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 717, in run
run_metadata_ptr)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 915, in _run
feed_dict_string, options, run_metadata)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 965, in _do_run
target_list, options, run_metadata)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 985, in _do_call
raise type(e)(node_def, op, message)
tensorflow.python.framework.errors.InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [10,128] vs. shape[1] = [70,128]
[[Node: RNN/while/BasicLSTMCell/Linear/concat = Concat[N=2, T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](RNN/while/BasicLSTMCell/Linear/concat/concat_dim, RNN/while/TensorArrayRead, RNN/while/Identity_3)]]
Caused by op u'RNN/while/BasicLSTMCell/Linear/concat', defined at:
File "/home/xiangzhang/RNN.py", line 128, in <module>
pred = RNN(x, weights, biases)
File "/home/xiangzhang/RNN.py", line 110, in RNN
outputs, final_state = tf.nn.dynamic_rnn(lstm_cell, X_in, initial_state=_init_state, time_major=False)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 836, in dynamic_rnn
dtype=dtype)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 1003, in _dynamic_rnn_loop
swap_memory=swap_memory)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2518, in while_loop
result = context.BuildLoop(cond, body, loop_vars, shape_invariants)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2356, in BuildLoop
pred, body, original_loop_vars, loop_vars, shape_invariants)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/control_flow_ops.py", line 2306, in _BuildLoop
body_result = body(*packed_vars_for_body)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 988, in _time_step
(output, new_state) = call_cell()
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/rnn.py", line 974, in <lambda>
call_cell = lambda: cell(input_t, state)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell.py", line 310, in __call__
concat = _linear([inputs, h], 4 * self._num_units, True)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/rnn_cell.py", line 907, in _linear
res = math_ops.matmul(array_ops.concat(1, args), matrix)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/array_ops.py", line 872, in concat
name=name)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/ops/gen_array_ops.py", line 436, in _concat
values=values, name=name)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 749, in apply_op
op_def=op_def)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2380, in create_op
original_op=self._default_original_op, op_def=op_def)
File "/home/xiangzhang/.local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1298, in __init__
self._traceback = _extract_stack()
InvalidArgumentError (see above for traceback): ConcatOp : Dimensions of inputs should match: shape[0] = [10,128] vs. shape[1] = [70,128]
[[Node: RNN/while/BasicLSTMCell/Linear/concat = Concat[N=2, T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](RNN/while/BasicLSTMCell/Linear/concat/concat_dim, RNN/while/TensorArrayRead, RNN/while/Identity_3)]]
Process finished with exit code 1
I thought the reason maybe is the testing dataset is only 10, less than batch_size=70, so that when I run the testing dataset, the code _init_state = lstm_cell.zero_state(batch_size, dtype=tf.float32) would has the unmatch error.
There are two ways to solve it but I don't know how to implement any of it neither:
change the batch_size value, set it as 70 when training, 10 when testing. But, I don't know how to code it, please tell me how to do?
Or, I can set the batch_size=10 , and automatically read the training dataset ten by ten. Also, I don't know how to read next batch in tensorflow automatically, and the command next_batch in MNIST dataset can not work.
The second solution is particular important, please kindly to help me, thanks very much.