I don't understand why my code wouldn't run. I started with the TensorFlow tutorial to classify the images in the mnist data set using a single layer feedforward neural net. Then modified the code to create a multilayer perceptron that maps out 37 inputs to 1 output. The input and output training data are being loaded from Matlab data file (.mat)
Here is my code..
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from scipy.io import loadmat
%matplotlib inline
import tensorflow as tf
from tensorflow.contrib import learn
import sklearn
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from warnings import filterwarnings
filterwarnings('ignore')
sns.set_style('white')
from sklearn import datasets
from sklearn.preprocessing import scale
from sklearn.cross_validation import train_test_split
from sklearn.datasets import make_moons
X = np.array(loadmat("Data/DataIn.mat")['TrainingDataIn'])
Y = np.array(loadmat("Data/DataOut.mat")['TrainingDataOut'])
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=.5)
total_len = X_train.shape[0]
# Parameters
learning_rate = 0.001
training_epochs = 500
batch_size = 10
display_step = 1
dropout_rate = 0.9
# Network Parameters
n_hidden_1 = 19 # 1st layer number of features
n_hidden_2 = 26 # 2nd layer number of features
n_input = X_train.shape[1]
n_classes = 1
# tf Graph input
X = tf.placeholder("float32", [None, 37])
Y = tf.placeholder("float32", [None])
def multilayer_perceptron(X, weights, biases):
# Hidden layer with RELU activation
layer_1 = tf.add(tf.matmul(X, weights['h1']), biases['b1'])
layer_1 = tf.nn.relu(layer_1)
layer_2 = tf.add(tf.matmul(layer_1, weights['h2']), biases['b2'])
layer_2 = tf.nn.relu(layer_2)
# Output layer with linear activation
out_layer = tf.matmul(layer_2, weights['out']) + biases['out']
return out_layer
# Store layers weight & bias
weights = {
'h1': tf.Variable(tf.random_normal([n_input, n_hidden_1], 0, 0.1)),
'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2], 0, 0.1)),
'out': tf.Variable(tf.random_normal([n_hidden_2, n_classes], 0, 0.1))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1], 0, 0.1)),
'b2': tf.Variable(tf.random_normal([n_hidden_2], 0, 0.1)),
'out': tf.Variable(tf.random_normal([n_classes], 0, 0.1))
}
# Construct model
pred = multilayer_perceptron(X, weights, biases)
tf.shape(pred)
tf.shape(Y)
print("Prediction matrix:", pred)
print("Output matrix:", Y)
# Define loss and optimizer
cost = tf.reduce_mean(tf.square(pred-Y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Launch the graph
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
# Training cycle
for epoch in range(training_epochs):
avg_cost = 0.
total_batch = int(total_len/batch_size)
print(total_batch)
# Loop over all batches
for i in range(total_batch-1):
batch_x = X_train[i*batch_size:(i+1)*batch_size]
batch_y = Y_train[i*batch_size:(i+1)*batch_size]
# Run optimization op (backprop) and cost op (to get loss value)
_, c, p = sess.run([optimizer, cost, pred], feed_dict={X: batch_x,
Y: batch_y})
# Compute average loss
avg_cost += c / total_batch
# sample prediction
label_value = batch_y
estimate = p
err = label_value-estimate
print ("num batch:", total_batch)
# Display logs per epoch step
if epoch % display_step == 0:
print ("Epoch:", '%04d' % (epoch+1), "cost=", \
"{:.9f}".format(avg_cost))
print ("[*]----------------------------")
for i in xrange(5):
print ("label value:", label_value[i], \
"estimated value:", estimate[i])
print ("[*]============================")
print ("Optimization Finished!")
# Test model
correct_prediction = tf.equal(tf.argmax(pred), tf.argmax(Y))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float"))
print ("Accuracy:", accuracy.eval({X: X_test, Y: Y_test}))
when I run the code I get error messages:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-4-6b8af9192775> in <module>()
93 # Run optimization op (backprop) and cost op (to get loss value)
94 _, c, p = sess.run([optimizer, cost, pred], feed_dict={X: batch_x,
---> 95 Y: batch_y})
96 # Compute average loss
97 avg_cost += c / total_batch
~\AppData\Local\Continuum\Anaconda3\envs\ann\lib\site-packages\tensorflow\python\client\session.py in run(self, fetches, feed_dict, options, run_metadata)
787 try:
788 result = self._run(None, fetches, feed_dict, options_ptr,
--> 789 run_metadata_ptr)
790 if run_metadata:
791 proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)
~\AppData\Local\Continuum\Anaconda3\envs\ann\lib\site-packages\tensorflow\python\client\session.py in _run(self, handle, fetches, feed_dict, options, run_metadata)
973 'Cannot feed value of shape %r for Tensor %r, '
974 'which has shape %r'
--> 975 % (np_val.shape, subfeed_t.name, str(subfeed_t.get_shape())))
976 if not self.graph.is_feedable(subfeed_t):
977 raise ValueError('Tensor %s may not be fed.' % subfeed_t)
ValueError: Cannot feed value of shape (10, 1) for Tensor 'Placeholder_7:0', which has shape '(?,)'
I've encountered this problem before. The difference is that a Tensor of shape (10, 1) looks like [[1], [2], [3]], while a Tensor of shape (10,) looks like [1, 2, 3].
You should be able to fix it by changing the line
Y = tf.placeholder("float32", [None])
to:
Y = tf.placeholder("float32", [None, 1])