I'm trying to create a NN to approximate functions (sine, cos, custom...) but I'm struggling with the format, I don't want to use input-label, but rather, input-output. How do I change it?
I'm following this tutorial
import tensorflow as tf
import random
from math import sin
import numpy as np
n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500
n_inputs = 1 # CHANGES HERE
n_outputs = 1 #CHANGES HERE
batch_size = 100
x = tf.placeholder('float', [None, n_inputs]) #CHANGES HERE
y = tf.placeholder('float', [None, n_outputs]) #CHANGES HERE
def neural_network_model(data):
hidden_layer_1 = {'weights':tf.Variable(tf.random_normal([n_inputs, n_nodes_hl1])),
'biases': tf.Variable(tf.random_normal([n_nodes_hl1]))} #CHANGES HERE
hidden_layer_2 = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))}
hidden_layer_3 = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
'biases': tf.Variable(tf.random_normal([n_nodes_hl2]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_outputs])),
'biases': tf.Variable(tf.random_normal([n_outputs]))} #CHANGES HERE
l1 = tf.add(tf.matmul(data, hidden_layer_1['weights']), hidden_layer_1['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1, hidden_layer_2['weights']), hidden_layer_2['biases'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(l2, hidden_layer_3['weights']), hidden_layer_3['biases'])
l3 = tf.nn.relu(l3)
output = tf.add(tf.matmul(l3, output_layer['weights']), output_layer['biases'])
return output
def train_neural_network(x):
prediction = neural_network_model(x)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
optmizer = tf.train.AdamOptimizer().minimize(cost)
epochs = 10
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(epochs):
loss = 0
for _ in range(batch_size^2): #CHANGES HERE
batch_x, batch_y = generate_input_output(batch_size) #CHANGES HERE
a, c = sess.run([optmizer, cost], feed_dict={x: batch_x, y:batch_y})
loss += c
print("Epoch:", epoch+1, "out of", epochs, "- Loss:", loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
test_x, test_y = generate_input_output(batch_size) #CHANGES HERE
print('Accuracy', accuracy.eval({x:test_x, y:test_y}))
def desired_function(x): #CHANGES HERE
return sin(x)
def generate_input_output(batch_size): #CHANGES HERE
batch_x = [random.uniform(-10, 10) for _ in range(batch_size)]
batch_y = [desired_function(x) for x in batch_x]
batch_x = np.reshape(batch_x, (-1, 1))
batch_y = np.reshape(batch_y, (-1, 1))
return batch_x, batch_y
train_neural_network(x)
Your solution seems very verbose to me. I'll post a much simplified solution, could you point out what part of it you don't understand?
import tensorflow as tf
import numpy as np
n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500
batch_size = 100
x = tf.placeholder('float', [None, 1])
y = tf.placeholder('float', [None, 1])
x1 = tf.contrib.layers.fully_connected(x, n_nodes_hl1)
x2 = tf.contrib.layers.fully_connected(x1, n_nodes_hl2)
x3 = tf.contrib.layers.fully_connected(x2, n_nodes_hl3)
result = tf.contrib.layers.fully_connected(x3, 1,
activation_fn=None)
loss = tf.nn.l2_loss(result - y)
train_op = tf.train.AdamOptimizer().minimize(loss)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(10000):
xpts = np.random.rand(batch_size) * 10
ypts = np.sin(xpts)
_, loss_result = sess.run([train_op, loss],
feed_dict={x: xpts[:, None],
y: ypts[:, None]})
print('iteration {}, loss={}'.format(i, loss_result))
It seems to me that your solution was intended for classification and you have not fully rewrote it for regression, since there are things like softmax_cross_entropy_with_logits left in there, which you certainly don't want in a regression network.
Have not tried it myself, so there might be more things you need to change to get the model to run, but you will definitely want to change this line:
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
to something more like:
cost = tf.reduce_sum(tf.square(prediction - y))
Basically, your cost function is much simpler in this case...you just want to reduce the sum of the squared difference between the network's output and the expected y value.
Related
I followed (sentdex's Youtube video) to create a TensorFlow program and it worked well. I started to tweak some parameters(converting all float32 to float 16 to try to make it faster) in it and got errors. So I tried to debug it with Pycharm. Then I discovered that during debug, even if I was pausing on one line and there was no other process running at the same time, python2.7 keeps occupying more and more memory until it hits 100% and my computer freezes.
Is it that TensorFlow should not be debugged this way? Or is it that something else is wrong?
import tensorflow as tf
import time
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
n_node_hl1 = 500
n_node_hl2 = 500
n_node_hl3 = 500
n_classes = 10
batch_size = 100
x = tf.placeholder(tf.float16, [None, 784])
y = tf.placeholder(tf.float16)
def neural_network_model(data):
hidden_1_layer = {'weights': tf.Variable(tf.random_normal([784,, n_node_hl1], dtype=tf.float16)),
'bias': tf.Variable(tf.random_normal([n_node_hl1], dtype=tf.float16))}
hidden_2_layer = {'weights': tf.Variable(tf.random_normal([n_node_hl1, n_node_hl2], dtype=tf.float16)),
'bias': tf.Variable(tf.random_normal([n_node_hl1], dtype=tf.float16))}
hidden_3_layer = {'weights': tf.Variable(tf.random_normal([n_node_hl2, n_node_hl3], dtype=tf.float16)),
'bias': tf.Variable(tf.random_normal([n_node_hl1], dtype=tf.float16))}
output_layer = {'weights': tf.Variable(tf.random_normal([n_node_hl3, n_classes], dtype=tf.float16)),
'bias': tf.Variable(tf.random_normal([n_classes], dtype=tf.float16))}
l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['bias'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['bias'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(l2, hidden_3_layer['weights']), hidden_3_layer['bias'])
l3 = tf.nn.relu(l3)
output = tf.add(tf.matmul(l3, output_layer['weights']), output_layer['bias'])
return output
def train_neural_network(x, y):
prediction = neural_network_model(x)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y))
optimizer = tf.train.AdamOptimizer(learning_rate=0.005).minimize(cost)
hm_epochs = 10
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
for _ in range(int(mnist.train.num_examples/batch_size)):
epoch_x, epoch_y = mnist.train.next_batch(batch_size)
epoch_x = epoch_x.astype(np.float16)
epoch_y = epoch_y.astype(np.float16)
_, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
epoch_loss = c
print('Epoch', epoch, 'completed out of', hm_epochs, 'loss:', epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, tf.float16))
print('Accuracy: ', accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
file_writer = tf.summary.FileWriter('/home/ramon/PycharmProjects/test/graph', sess.graph)
t = time.time()
train_neural_network(x, y)
print(time.time()-t)
Thanks for the edit and suggestion. I didn't post the code in the first place because I want people to focus on the debugging question and see if they have similar experience instead of focusing on my code because I'm pretty sure there's something wrong with my code(but that should not affect the debugging behavior of Pycharm).
After playing with tensorflow, I finally was able to make my code run but the loss seem to go in the negative, even with few epochs. Why is this happening? I made simple neural nets with numpy only and never had this problem, can someone explain what am I doing wrong?
here is the input file if anyone wants to test it: input file
additional information: the labels arent onehot array, is my loss function the correct one since it isnt onehot array? I followed a tutorial that used onehot array labels.
import tensorflow as tf
import numpy as np
data = np.load("test_data.npz")
trng_input = np.array(data['Input'], dtype=np.float64)
trng_output = np.array(data['Output'], dtype=np.float64)
nhl1 = 12
nhl2 = 8
n_classes = 4
x = tf.placeholder(dtype=tf.float64, shape=[len(trng_input),24])
y = tf.placeholder(dtype=tf.float64, shape=[len(trng_output),n_classes])
def NN(data):
hl1 = {"weights":tf.Variable(tf.random_normal([24, nhl1], dtype=tf.float64)),
"biases":tf.Variable(tf.random_normal([nhl1], dtype=tf.float64))}
hl2 = {"weights":tf.Variable(tf.random_normal([nhl1, nhl2], dtype=tf.float64)),
"biases":tf.Variable(tf.random_normal([nhl2], dtype=tf.float64))}
output_layer = {"weights":tf.Variable(tf.random_normal([nhl2, n_classes], dtype=tf.float64)),
"biases":tf.Variable(tf.random_normal([n_classes], dtype=tf.float64))}
l1 = tf.add(tf.matmul(data, hl1["weights"]), hl1["biases"])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1, hl2["weights"]), hl2["biases"])
l2 = tf.nn.relu(l2)
output = tf.add(tf.matmul(l2, output_layer["weights"]), output_layer["biases"])
output = tf.nn.relu(output)
return output
def train(data, epochs):
prediction = NN(data)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=prediction, labels=y))
optimizer = tf.train.AdamOptimizer().minimize(cost)
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for epoch in range(epochs):
_, c = sess.run([optimizer, cost], feed_dict={x: trng_input, y: trng_output})
if not epoch % 20:
print(F"Epoch {epoch} completed out of {epochs}. Loss:{c}")
correct = tf.equal(tf.argmax(prediction,1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct,"float"))
Eval = accuracy.eval({x:trng_input, y:trng_output})
print(F"Accuracy:{Eval}")
train(trng_input, 200)
I have recently started working with tensorflow and this is like my second piece of code and I am stuck while designing this neural network. I am not able to increment the batch size and this problem has been persisting for quite a while.
import numpy as np
import pandas as pd
import tensorflow as tf
import math
#importing the data and preprocessing it
dataset = pd.read_csv('C:\\Users\\Geeks_Sid\\Documents\\Deep-Learning-A-Z\Deep Learning A-Z\\Volume 1 - Supervised Deep Learning\\Part 1 - Artificial Neural Networks (ANN)\\Section 4 - Building an ANN\\Artificial_Neural_Networks\\Churn_Modelling.csv')
X = dataset.iloc[:, 3:13].values
y = dataset.iloc[:, 13].values
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X_1 = LabelEncoder()
X[:, 1] = labelencoder_X_1.fit_transform(X[:, 1])
labelencoder_X_2 = LabelEncoder()
X[:, 2] = labelencoder_X_2.fit_transform(X[:, 2])
onehotencoder = OneHotEncoder(categorical_features = [1])
X = onehotencoder.fit_transform(X).toarray()
#creating a train test split
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)
# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)
# Creating layers for Neural network
n_nodes_hl1 = 1000
n_nodes_hl2 = 1000
n_nodes_hl3 = 1000
n_classes = 1
batch_size = 50
x = tf.placeholder('float', [None, 11])
y = tf.placeholder('float')
def neural_network_model(data):
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([11, n_nodes_hl1])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
hidden_3_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes])),}
l1 = tf.add(tf.matmul(data,hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1,hidden_2_layer['weights']), hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(l2,hidden_3_layer['weights']), hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)
output = tf.matmul(l3,output_layer['weights']) + output_layer['biases']
print("I was in neural netowrk m")
return output
def train_neural_network(x):
prediction = neural_network_model(x)
# OLD VERSION:
#cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
# NEW:
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
# OLD:
for epoch in range(hm_epochs):
epoch_loss = 0
current = 0
for _ in range(80):
currentprev = current
current += 100
epoch_x, epoch_y = tuple(X_train[:,currentprev:current]) ,tuple(y_train[:,currentprev:current])
_, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
epoch_loss += c
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:X_test, y:y_test}))
#sess.run(tf.initialize_all_variables())
# NEW:
sess.run(tf.global_variables_initializer())
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
train_neural_network(x)
I am dealing with the error that looks like this.
train_neural_network(x)
I was in neural netowrk m
Traceback (most recent call last):
File "<ipython-input-8-7c7cbdae9b34>", line 1, in <module>
train_neural_network(x)
File "<ipython-input-7-b7e263fe7976>", line 20, in train_neural_network
epoch_x, epoch_y = tuple(X_train[:,currentprev:current]) ,tuple(y_train[:,currentprev:current])
IndexError: too many indices for array
I am trying a replicate a code of tensorflow MNIST dataset classification where they used this following piece of code. I hope you're able to compare this code with mine. If there are any corrections, please do help me
def train_neural_network(x):
prediction = neural_network_model(x)
# OLD VERSION:
#cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
# NEW:
cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(logits=prediction, labels=y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
config = tf.ConfigProto()
config.gpu_options.allow_growth = True
with tf.Session(config=config) as sess:
# OLD:
#sess.run(tf.initialize_all_variables())
# NEW:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
epoch_loss = 0
for _ in range(int(mnist.train.num_examples/batch_size)):
epoch_x, epoch_y = mnist.train.next_batch(batch_size)
_, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
epoch_loss += c
print('Epoch', epoch, 'completed out of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:mnist.test.images, y:mnist.test.labels}))
As you can see, my code is quite similar to the one for MNIST but i am not able to return a particular tuple which is at this piece of code.
epoch_x, epoch_y = mnist.train.next_batch(batch_size)
_, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y: epoch_y})
A thanks in advance. if you feel the question is repetitive, i want to explain that i couldn't find others relevant.
I don't understand very well the reshaping you're performing on your data, nor the original format of it but here y = dataset.iloc[:, 13].values it seems that y is a 1D-array while here tuple(y_train[:,currentprev:current] you are accessing it like a 2D matrix and the error is telling you that you are using too many (2) indices to index a 1D array.
I have been struggling with understanding the data passed into tensor flow.
I wanted to use tensor flow for classification. I have a dataframe, with 5 features(columns) my Xs and 89 rows (datapoints). I have a target variable 'y' in the 6th column with 5 classes.
entire dataframe is of shape 89 X 6.
Further is the code I have been trying to implement.
import tensorflow as tf
from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X1, y1, test_size=0.3, random_state=45)
#making target variable column in dummy
i = ['tumor'] #6th column name is 'tumor'
y_train1 = pd.get_dummies(y_train, columns = i, drop_first = False)
y_test1 = pd.get_dummies(y_test, columns = i, drop_first = False)
# I am passing target variable as dataframe of dummy variables of my classes. is it correct? Should I split Y variable into dummy variables?
n_nodes_hl1 = 50
n_nodes_hl2 = 50
n_nodes_hl3 = 50
n_classes = 5
batch_size = 10
x = tf.placeholder('float', [None, len(X_train)]) #height X width, part where I am struggling.
y = tf.placeholder('float')
def neural_network_model(data):
#matching the placeholder's dimension len(X_train) for layer 1
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([len(X_train), n_nodes_hl1])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
hidden_3_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes]))}
#input data * weights + biases
l1 = tf.add(tf.matmul(data,hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1,hidden_2_layer['weights']), hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(l2,hidden_3_layer['weights']), hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)
output = tf.matmul(l3, output_layer['weights']) + output_layer['biases']
return output
def train_neural_network(x):
prediction = neural_network_model(x)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction, y))
optimizer = tf.train.AdamOptimizer().minimize(cost) #default learning rate = 0.001
hm_epochs = 5
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for epoch in range(hm_epochs):
epoch_loss = 0
i=0
while i <len(X_train):
start = i
end = i + batch_size
batch_x = np.array(X_train[start:end])
batch_y = np.array(y_train1[start:end])
_,c = sess.run([optimizer, cost], feed_dict = {x:batch_x , y:batch_y})
epoch_loss += c
i += batch_size
print ('Epoch', epoch, 'completed out of', hm_epochs, 'loss:', epoch_loss)
correct = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct,'float'))
print ('accuracy:', accuracy.eval({x:X_test, y:y_test1}))
train_neural_network(X_train)
With the X_train shape as 62X5, the error is
Argument must be a dense tensor.
[62 rows x 5 columns] - got shape [62, 5], but wanted [].
Can someone please explain about passing data to tensor-flow or placeholder and dimensionality? Thank you.
I'm new to tensorflow and am following a tutorial. I am getting an error that says:
InvalidArgumentError (see above for traceback): Matrix size-compatible: In[0]: [100,784], In[1]: [500,10]
[[Node: MatMul_3 = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false, _device="/job:localhost/replica:0/task:0/cpu:0"](_recv_Placeholder_0, Variable_6/read)]]
Here is my code:
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
n_nodes_hl1 = 500
n_nodes_hl2 = 500
n_nodes_hl3 = 500
n_classes = 10
batch_size = 100
x = tf.placeholder('float') #this second parameter makes sure that the image fed in is 28*28
y = tf.placeholder('float')
def neural_network_model(data):
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([784, n_nodes_hl1])), 'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])), 'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
hidden_3_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])), 'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])), 'biases':tf.Variable(tf.random_normal([n_classes]))}
# input_data * weights + biases
l1 = tf.add(tf.matmul(data, hidden_1_layer['weights']), hidden_1_layer['biases'])
# activation function
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']), hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(data, hidden_3_layer['weights']), hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)
output = tf.matmul(data, output_layer['weights']) + output_layer['biases']
return output
def train_neural_network(x):
prediction = neural_network_model(x)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction, y))
#learning rate = 0.001
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
with tf.Session() as sess:
sess.run(tf.initialize_all_variables())
for epoch in range(hm_epochs):
epoch_loss = 0
for _ in range(int(mnist.train.num_examples/batch_size)):
epoch_x, epoch_y = mnist.train.next_batch(batch_size)
_, c = sess.run([optimizer, cost], feed_dict={x:epoch_x,y:epoch_y})//THIS IS THE LINE WHERE THE ERROR 0CCURS
epoch_loss += c
print 'Epoch ' + epoch + ' completed out of ' + hm_epoch + ' loss: ' + epoch_loss
correct = tf.equal(tf.argmax(prediction,1), tf.argmax(y,1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print 'Accuracy: ' + accuracy.eval({x:mnist.test.images, y:mnist.test.labels})
train_neural_network(x)
I have marked the line where the error occurs what am I doing wrong and how can I fix it?
Stack overflow wants me to write more, it says that there is not enough details and too much code. I honestly don't understand tensorflow well enough to add any more details. I'm hoping someone can just help me with this. I think the problem is that optimizer and cost have different dimensions, but I don't understand why or what I should do about it.
One error lies in this line
l2 = tf.add(tf.matmul(data, hidden_2_layer['weights']), hidden_2_layer['biases'])
Your second weights variable has dimensions 500 x 500, but your data variable was fed with data 100x784 so multiplication is incompatible. Make this,
l2 = tf.add(tf.matmul(l1, hidden_2_layer['weights']), hidden_2_layer['biases'])
Also make the corresponding change for l3 and output.
Always specify a shape for the placeholder, like this,
x = tf.placeholder(tf.float32, shape=(None, 784))
This will allow you to catch such errors while building the graph and TensorFlow will be able to pinpoint these errors.