How exactly does LSTMCell from TensorFlow operates? - python

I try to reproduce results generated by the LSTMCell from TensorFlow to be sure that I know what it does.
Here is my TensorFlow code:
num_units = 3
lstm = tf.nn.rnn_cell.LSTMCell(num_units = num_units)
timesteps = 7
num_input = 4
X = tf.placeholder("float", [None, timesteps, num_input])
x = tf.unstack(X, timesteps, 1)
outputs, states = tf.contrib.rnn.static_rnn(lstm, x, dtype=tf.float32)
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
x_val = np.random.normal(size = (1, 7, num_input))
res = sess.run(outputs, feed_dict = {X:x_val})
for e in res:
print e
Here is its output:
[[-0.13285545 -0.13569424 -0.23993783]]
[[-0.04818152 0.05927373 0.2558436 ]]
[[-0.13818116 -0.13837864 -0.15348436]]
[[-0.232219 0.08512601 0.05254192]]
[[-0.20371495 -0.14795329 -0.2261929 ]]
[[-0.10371902 -0.0263292 -0.0914975 ]]
[[0.00286371 0.16377522 0.059478 ]]
And here is my own implementation:
n_steps, _ = X.shape
h = np.zeros(shape = self.hid_dim)
c = np.zeros(shape = self.hid_dim)
for i in range(n_steps):
x = X[i,:]
vec = np.concatenate([x, h])
#vec = np.concatenate([h, x])
gs = np.dot(vec, self.kernel) + self.bias
g1 = gs[0*self.hid_dim : 1*self.hid_dim]
g2 = gs[1*self.hid_dim : 2*self.hid_dim]
g3 = gs[2*self.hid_dim : 3*self.hid_dim]
g4 = gs[3*self.hid_dim : 4*self.hid_dim]
I = vsigmoid(g1)
N = np.tanh(g2)
F = vsigmoid(g3)
O = vsigmoid(g4)
c = c*F + I*N
h = O * np.tanh(c)
print h
And here is its output:
[-0.13285543 -0.13569425 -0.23993781]
[-0.01461723 0.08060743 0.30876374]
[-0.13142865 -0.14921292 -0.16898363]
[-0.09892188 0.11739943 0.08772941]
[-0.15569218 -0.15165766 -0.21918869]
[-0.0480604 -0.00918626 -0.06084118]
[0.0963612 0.1876516 0.11888081]
As you might notice I was able to reproduce the first hidden vector, but the second one and all the following ones are different. What am I missing?

i examined this link and your code is almost perfect but you forgot to add forget_bias value(default 1.0) in this line F = vsigmoid(g3) its actualy F = vsigmoid(g3+self.forget_bias) or in your case its 1 F = vsigmoid(g3+1)
here is my imp with numpy:
import numpy as np
import tensorflow as tf
num_units = 3
lstm = tf.nn.rnn_cell.LSTMCell(num_units = num_units)
batch=1
timesteps = 7
num_input = 4
X = tf.placeholder("float", [batch, timesteps, num_input])
x = tf.unstack(X, timesteps, 1)
outputs, states = tf.contrib.rnn.static_rnn(lstm, x, dtype=tf.float32)
sess = tf.Session()
init = tf.global_variables_initializer()
sess.run(init)
x_val = np.reshape(range(28),[batch, timesteps, num_input])
res = sess.run(outputs, feed_dict = {X:x_val})
for e in res:
print(e)
print("\nmy imp\n")
#my impl
def sigmoid(x):
return 1/(1+np.exp(-x))
kernel,bias=sess.run([lstm._kernel,lstm._bias])
f_b_=lstm._forget_bias
c,h=np.zeros([batch,num_input-1]),np.zeros([batch,num_input-1])
for step in range(timesteps):
inpt=np.split(x_val,7,1)[step][0]
lstm_mtrx=np.matmul(np.concatenate([inpt,h],1),kernel)+bias
i,j,f,o=np.split(lstm_mtrx,4,1)
c=sigmoid(f+f_b_)*c+sigmoid(i)*np.tanh(j)
h=sigmoid(o)*np.tanh(c)
print(h)
output:
[[ 0.06964055 -0.06541953 -0.00682676]]
[[ 0.005264 -0.03234607 0.00014838]]
[[ 1.617855e-04 -1.316892e-02 8.596722e-06]]
[[ 3.9425286e-06 -5.1347450e-03 7.5078127e-08]]
[[ 8.7508155e-08 -1.9560163e-03 6.3853928e-10]]
[[ 1.8867894e-09 -7.3784427e-04 5.8551406e-12]]
[[ 4.0385355e-11 -2.7728223e-04 5.3957669e-14]]
my imp
[[ 0.06964057 -0.06541953 -0.00682676]]
[[ 0.005264 -0.03234607 0.00014838]]
[[ 1.61785520e-04 -1.31689185e-02 8.59672610e-06]]
[[ 3.94252745e-06 -5.13474567e-03 7.50781122e-08]]
[[ 8.75080644e-08 -1.95601574e-03 6.38539112e-10]]
[[ 1.88678843e-09 -7.37844070e-04 5.85513438e-12]]
[[ 4.03853841e-11 -2.77282006e-04 5.39576024e-14]]

Tensorflow uses glorot_uniform() function to initialize the lstm kernel, which samples weights from a random uniform distribution. We need to fix a value for the kernel to get reproducible results:
import tensorflow as tf
import numpy as np
np.random.seed(0)
timesteps = 7
num_input = 4
x_val = np.random.normal(size = (1, timesteps, num_input))
num_units = 3
def glorot_uniform(shape):
limit = np.sqrt(6.0 / (shape[0] + shape[1]))
return np.random.uniform(low=-limit, high=limit, size=shape)
kernel_init = glorot_uniform((num_input + num_units, 4 * num_units))
My implementation of the LSTMCell (well, actually it's just slightly rewritten tensorflow's code):
def sigmoid(x):
return 1. / (1 + np.exp(-x))
class LSTMCell():
"""Long short-term memory unit (LSTM) recurrent network cell.
"""
def __init__(self, num_units, initializer=glorot_uniform,
forget_bias=1.0, activation=np.tanh):
"""Initialize the parameters for an LSTM cell.
Args:
num_units: int, The number of units in the LSTM cell.
initializer: The initializer to use for the kernel matrix. Default: glorot_uniform
forget_bias: Biases of the forget gate are initialized by default to 1
in order to reduce the scale of forgetting at the beginning of
the training.
activation: Activation function of the inner states. Default: np.tanh.
"""
# Inputs must be 2-dimensional.
self._num_units = num_units
self._forget_bias = forget_bias
self._activation = activation
self._initializer = initializer
def build(self, inputs_shape):
input_depth = inputs_shape[-1]
h_depth = self._num_units
self._kernel = self._initializer(shape=(input_depth + h_depth, 4 * self._num_units))
self._bias = np.zeros(shape=(4 * self._num_units))
def call(self, inputs, state):
"""Run one step of LSTM.
Args:
inputs: input numpy array, must be 2-D, `[batch, input_size]`.
state: a tuple of numpy arrays, both `2-D`, with column sizes `c_state` and
`m_state`.
Returns:
A tuple containing:
- A `2-D, [batch, output_dim]`, numpy array representing the output of the
LSTM after reading `inputs` when previous state was `state`.
Here output_dim is equal to num_units.
- Numpy array(s) representing the new state of LSTM after reading `inputs` when
the previous state was `state`. Same type and shape(s) as `state`.
"""
num_proj = self._num_units
(c_prev, m_prev) = state
input_size = inputs.shape[-1]
# i = input_gate, j = new_input, f = forget_gate, o = output_gate
lstm_matrix = np.hstack([inputs, m_prev]).dot(self._kernel)
lstm_matrix += self._bias
i, j, f, o = np.split(lstm_matrix, indices_or_sections=4, axis=0)
# Diagonal connections
c = (sigmoid(f + self._forget_bias) * c_prev + sigmoid(i) *
self._activation(j))
m = sigmoid(o) * self._activation(c)
new_state = (c, m)
return m, new_state
X = x_val.reshape(x_val.shape[1:])
cell = LSTMCell(num_units, initializer=lambda shape: kernel_init)
cell.build(X.shape)
state = (np.zeros(num_units), np.zeros(num_units))
for i in range(timesteps):
x = X[i,:]
output, state = cell.call(x, state)
print(output)
Produces output:
[-0.21386017 -0.08401277 -0.25431477]
[-0.22243588 -0.25817422 -0.1612211 ]
[-0.2282134 -0.14207162 -0.35017249]
[-0.23286737 -0.17129192 -0.2706512 ]
[-0.11768674 -0.20717363 -0.13339118]
[-0.0599215 -0.17756104 -0.2028935 ]
[ 0.11437953 -0.19484555 0.05371994]
While your Tensorflow code, if you replace the second line with
lstm = tf.nn.rnn_cell.LSTMCell(num_units = num_units, initializer = tf.constant_initializer(kernel_init))
returns:
[[-0.2138602 -0.08401276 -0.25431478]]
[[-0.22243595 -0.25817424 -0.16122109]]
[[-0.22821338 -0.1420716 -0.35017252]]
[[-0.23286738 -0.1712919 -0.27065122]]
[[-0.1176867 -0.2071736 -0.13339119]]
[[-0.05992149 -0.177561 -0.2028935 ]]
[[ 0.11437953 -0.19484554 0.05371996]]

Here is a blog which will answer any conceptual questions related to LSTM's. Seems that there is a lot which goes into building an LSTM from scratch!
Of course, this answer doesn't solve your question but just giving a direction.

Considering Linear Algebra, it's possible to exist a dimension mismatch in the matrix multiplication between I*N (red circle), affecting the output, given that n x m dot m x p will give you a n x p dimensional output.

Related

Neural Network From Scratch - Forward propagation error

I wanna implement the backward propagation concept in python with the next code
class MLP(object):
def __init__(self, num_inputs=3, hidden_layers=[3, 3], num_outputs=2):
self.num_inputs = num_inputs
self.hidden_layers = hidden_layers
self.num_outputs = num_outputs
layers = [num_inputs] + hidden_layers + [num_outputs]
weights = []
bias = []
for i in range(len(layers) - 1):
w = np.random.rand(layers[i], layers[i + 1])
b=np.random.randn(layers[i+1]).reshape(1, layers[i+1])
weights.append(w)
bias.append(b)
self.weights = weights
self.bias = bias
activations = []
for i in range(len(layers)):
a = np.zeros(layers[i])
activations.append(a)
self.activations = activations
def forward_propagate(self, inputs):
activations = inputs
self.activations[0] = activations
for i, w in enumerate(self.weights):
for j, b in enumerate(self.bias):
net_inputs = self._sigmoid((np.dot(activations, w)+b))
self.activations[i + 1] = net_inputs
return activations
def train(self, inputs, targets, epochs, learning_rate):
for i in range(epochs):
sum_errors = 0
for j, input in enumerate(inputs):
target = targets[j]
output = self.forward_propagate(input)
def _sigmoid(self, x):
y = 1.0 / (1 + np.exp(-x))
return y
So I created the next dummy data in order to verify everything is correct
items = np.array([[random()/2 for _ in range(2)] for _ in range(1000)])
targets = np.array([[i[0] + i[1]] for i in items])
mlp = MLP(2, [5], 1)
mlp.train(items, targets, 2, 0.1)
but when I run the code I have the next error
ValueError: shapes (2,) and (5,1) not aligned: 2 (dim 0) != 5 (dim 0)
I understand the error, but how to solve it?
a couple of major problems with forward_propagate:
change net_inputs to activations - otherwise you always compute and return the activations from the first layer
remove for j, b in enumerate(self.bias): - biases from other layers have no business here
use matmul instead of dot
so, something like
for i, w in enumerate(self.weights):
activations = self._sigmoid((np.matmul(activations, w)+self.bias[i]))
self.activations[i + 1] = activations
return activations
Also, be careful to note that this method receives 1D array, which converts to a matrix after the first matmul. Matrixes are stored in self.activations and a matrix is returned from the method.
This might or might not be what you want.

Gaussian-Likelihood with tensorflow

This is a TensorFlow code to calculate Maximum log-likelihood from this link.
import tensorflow as tf
import numpy as np
EPS=1e-8
def gaussian_likelihood(x, mu, log_std):
pre_sum = -0.5 * (((x-mu)/(tf.exp(log_std)+EPS))**2 + 2*log_std + np.log(2*np.pi))
return tf.reduce_sum(pre_sum, axis=1)
if __name__ == '__main__':
sess = tf.Session()
dim = 2
x = tf.placeholder(tf.float32, shape=(None, dim))
mu = tf.placeholder(tf.float32, shape=(None, dim))
log_std = tf.placeholder(tf.float32, shape=(dim,))
true_gaussian_likelihood = gaussian_likelihood(x, mu, log_std)
batch_size = 5
feed_dict = {x: np.random.rand(batch_size, dim),
mu: np.random.rand(batch_size, dim),
log_std: np.random.rand(dim)}
true_result = sess.run(true_gaussian_likelihood,
feed_dict=feed_dict)
print(true_result)
In the last line of gaussian_likelihood function, why it has summed just over axis=1? I think the result of max-likelihood is a probability that is calculated over all samples(here batch_size=5 for simplicity) and should be just one number. But what I got as the max-likelihood is an array with (5,) dimension like below:
[-3.0391085 -3.0107908 -2.966611 -2.9552155 -3.027913 ]
Plus, these numbers aren't in the range [0,1] as the probability values should be. Is this a mistake of OpenAI tean who provided this code?

Splitting ndarray gives unexpected results (TensorFlow RNN tutorial)

I am following a tutorial on rnn's in TensorFlow but I have a question concerning the input formats.
They are taking raw_x (one hot vector) and basically first cutting that up in pieces of length 200 (batch_size) to form data_x. That is good.
Then they further cut up data_x in pieces of length 5 (num_step, or graph width) with:
for i in range(epoch_size):
x = data_x[:, i * num_steps:(i + 1) * num_steps]
y = data_y[:, i * num_steps:(i + 1) * num_steps]
yield (x, y)
However, if I look in the data, the slices of x do not match data_x. The first one does, but then they diverge.
Am I misunderstanding the above code? I would like to understand how x is being created or what it is supposed to look like.
I had expected the second item to be 0 1 0 1 0.
Also, I thought an epoch is when you go through the data completely, from this it seems that they split up the data in 1000 parts (epoch size)?
If it helps, this is my full code. I am trying to figure out what is going on in x. at line 48:
import numpy as np
import tensorflow as tf
# %matplotlib inline
import matplotlib.pyplot as plt
# Global config variables
num_steps = 5 # number of truncated backprop steps ('n' in the discussion above)
batch_size = 200
num_classes = 2
state_size = 4
learning_rate = 0.1
def gen_data(size=1000000):
print('generating data');
X = np.array(np.random.choice(2, size=(size,)))
Y = []
for i in range(size):
threshold = 0.5
if X[i-3] == 1:
threshold += 0.5
if X[i-8] == 1:
threshold -= 0.25
if np.random.rand() > threshold:
Y.append(0)
else:
Y.append(1)
return X, np.array(Y)
# adapted from https://github.com/tensorflow/tensorflow/blob/master/tensorflow/models/rnn/ptb/reader.py
def gen_batch(raw_data, batch_size, num_steps):
print('generating batches');
raw_x, raw_y = raw_data
data_length = len(raw_x)
# partition raw data into batches and stack them vertically in a data matrix
batch_partition_length = data_length // batch_size
data_x = np.zeros([batch_size, batch_partition_length], dtype=np.int32)
data_y = np.zeros([batch_size, batch_partition_length], dtype=np.int32)
for i in range(batch_size):
data_x[i] = raw_x[batch_partition_length * i:batch_partition_length * (i + 1)]
data_y[i] = raw_y[batch_partition_length * i:batch_partition_length * (i + 1)]
# further divide batch partitions into num_steps for truncated backprop
epoch_size = batch_partition_length // num_steps
for i in range(epoch_size):
x = data_x[:, i * num_steps:(i + 1) * num_steps]
y = data_y[:, i * num_steps:(i + 1) * num_steps]
yield (x, y)
def gen_epochs(n, num_steps):
for i in range(n):
yield gen_batch(gen_data(), batch_size, num_steps)
"""
Placeholders
"""
x = tf.placeholder(tf.int32, [batch_size, num_steps], name='input_placeholder')
y = tf.placeholder(tf.int32, [batch_size, num_steps], name='labels_placeholder')
init_state = tf.zeros([batch_size, state_size])
"""
RNN Inputs
"""
# Turn our x placeholder into a list of one-hot tensors:
# rnn_inputs is a list of num_steps tensors with shape [batch_size, num_classes]
x_one_hot = tf.one_hot(x, num_classes)
rnn_inputs = tf.unstack(x_one_hot, axis=1)
"""
Definition of rnn_cell
This is very similar to the __call__ method on Tensorflow's BasicRNNCell. See:
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/rnn_cell.py
"""
with tf.variable_scope('rnn_cell'):
W = tf.get_variable('W', [num_classes + state_size, state_size])
b = tf.get_variable('b', [state_size], initializer=tf.constant_initializer(0.0))
def rnn_cell(rnn_input, state):
with tf.variable_scope('rnn_cell', reuse=True):
W = tf.get_variable('W', [num_classes + state_size, state_size])
b = tf.get_variable('b', [state_size], initializer=tf.constant_initializer(0.0))
return tf.tanh(tf.matmul(tf.concat(axis=1, values=[rnn_input, state]), W) + b)
"""
Adding rnn_cells to graph
This is a simplified version of the "rnn" function from Tensorflow's api. See:
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/rnn.py
"""
state = init_state
rnn_outputs = []
for rnn_input in rnn_inputs:
state = rnn_cell(rnn_input, state)
rnn_outputs.append(state)
final_state = rnn_outputs[-1]
"""
Predictions, loss, training step
Losses and total_loss are simlar to the "sequence_loss_by_example" and "sequence_loss"
functions, respectively, from Tensorflow's api. See:
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/python/ops/seq2seq.py
"""
#logits and predictions
with tf.variable_scope('softmax'):
W = tf.get_variable('W', [state_size, num_classes])
b = tf.get_variable('b', [num_classes], initializer=tf.constant_initializer(0.0))
logits = [tf.matmul(rnn_output, W) + b for rnn_output in rnn_outputs]
predictions = [tf.nn.softmax(logit) for logit in logits]
# Turn our y placeholder into a list labels
y_as_list = [tf.squeeze(i, axis=[1]) for i in tf.split(axis=1, num_or_size_splits=num_steps, value=y)]
#losses and train_step
losses = [tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logit,labels=label) for \
logit, label in zip(logits, y_as_list)]
total_loss = tf.reduce_mean(losses)
train_step = tf.train.AdagradOptimizer(learning_rate).minimize(total_loss)
"""
Function to train the network
"""
def train_network(num_epochs, num_steps, state_size=4, verbose=True):
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
training_losses = []
for idx, epoch in enumerate(gen_epochs(num_epochs, num_steps)):
training_loss = 0
training_state = np.zeros((batch_size, state_size))
if verbose:
print("\nEPOCH", idx)
for step, (X, Y) in enumerate(epoch):
tr_losses, training_loss_, training_state, _ = \
sess.run([losses,
total_loss,
final_state,
train_step],
feed_dict={x:X, y:Y, init_state:training_state})
training_loss += training_loss_
if step % 100 == 0 and step > 0:
if verbose:
print("Average loss at step", step,
"for last 250 steps:", training_loss/100)
training_losses.append(training_loss/100)
training_loss = 0
return training_losses
training_losses = train_network(1,num_steps)
plt.plot(training_losses)
Seems like the batches are actually transposed.
So the first elements of the x-matrix (200 x 5) will fit the first 5 elements of x_raw.
Then only in the next iteration, the next 5-10 elements of x_raw will be in the first elements (again) of x.

Why does my TensorFlow Neural Network for XOR only have an accuracy of around 0.5?

I Wrote a Neural Network in TensorFlow for the XOR input. I have used 1 hidden layer with 2 units and softmax classification. The input is of the form <1, x_1, x_2, zero, one> , where
1 is the bias
x_1 and x_2 are either between 0 and 1 for all the combination {00, 01, 10, 11}. Selected to be normally distributed around 0 or 1
zero: is 1 if the output is zero
one: is 1 if the output is one
The accuracy is always around 0.5. What has gone wrong? Is the architecture of the neural network wrong, or is there something with the code?
import tensorflow as tf
import numpy as np
from random import randint
DEBUG=True
def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.01))
def model(X, weight_hidden, weight_output):
# [1,3] x [3,n_hiddent_units] = [1,n_hiddent_units]
hiddern_units_output = tf.nn.sigmoid(tf.matmul(X, weight_hidden))
# [1,n_hiddent_units] x [n_hiddent_units, 2] = [1,2]
return hiddern_units_output
#return tf.matmul(hiddern_units_output, weight_output)
def getHiddenLayerOutput(X, weight_hidden):
hiddern_units_output = tf.nn.sigmoid(tf.matmul(X, weight_hidden))
return hiddern_units_output
total_inputs = 100
zeros = tf.zeros([total_inputs,1])
ones = tf.ones([total_inputs,1])
around_zeros = tf.random_normal([total_inputs,1], mean=0, stddev=0.01)
around_ones = tf.random_normal([total_inputs,1], mean=1, stddev=0.01)
batch_size = 10
n_hiddent_units = 2
X = tf.placeholder("float", [None, 3])
Y = tf.placeholder("float", [None, 2])
weight_hidden = init_weights([3, n_hiddent_units])
weight_output = init_weights([n_hiddent_units, 2])
hiddern_units_output = getHiddenLayerOutput(X, weight_hidden)
py_x = model(X, weight_hidden, weight_output)
#cost = tf.square(Y - py_x)
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y))
train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost)
with tf.Session() as sess:
tf.global_variables_initializer().run()
trX_0_0 = sess.run(tf.concat([ones, around_zeros, around_zeros, ones, zeros], axis=1))
trX_0_1 = sess.run(tf.concat([ones, around_zeros, around_ones, zeros, ones], axis=1))
trX_1_0 = sess.run(tf.concat([ones, around_ones, around_zeros, zeros, ones], axis=1))
trX_1_1 = sess.run(tf.concat([ones, around_ones, around_ones, ones, zeros], axis=1))
trX = sess.run(tf.concat([trX_0_0, trX_0_1, trX_1_0, trX_1_1], axis=0))
trX = sess.run(tf.random_shuffle(trX))
print(trX)
for i in range(10):
for start, end in zip(range(0, len(trX), batch_size), range(batch_size, len(trX) + 1, batch_size)):
trY = tf.identity(trX[start:end,3:5])
trY = sess.run(tf.reshape(trY,[batch_size, 2]))
sess.run(train_op, feed_dict={ X: trX[start:end,0:3], Y: trY })
start_index = randint(0, (total_inputs*4)-batch_size)
y_0 = sess.run(py_x, feed_dict={X: trX[start_index:start_index+batch_size,0:3]})
print("iteration :",i, " accuracy :", np.mean(np.absolute(trX[start_index:start_index+batch_size,3:5]-y_0)),"\n")
Check the comments section for the updated code
The problem was with the randomly assigned weights. Here is the modified version, obtained after a series of trail-and-error.

Simple Binary Classification Using Theano Error

I got an error when trying to create a simple binary classification for XOR case using Theano. It said dimension mismatch, but I can't find out what variable cause that.
and the strange part, my program is works when I change the number of neuron in the last layer. When I change to use 2 neuron in the last layer, and change that layer to softmax layer, and also use the negative log likelihood (multiclass classification style), this program is works fine.
This is my full code:
import numpy as np
import theano
import theano.tensor as T
class HiddenLayer(object):
def __init__(self, input, nIn, nOut, is_last, W=None):
self.input = input
W_val = np.random.randn(nIn,nOut)*0.001
b_val = np.zeros((nOut,))
self.W = theano.shared(np.asarray(W_val,dtype=theano.config.floatX),
name='W',borrow=True)
self.b = theano.shared(np.asarray(b_val,dtype=theano.config.floatX),
name='b',borrow=True)
self.z = T.dot(input,self.W) + self.b
if(is_last==0):
self.output = T.switch(self.z < 0 , 0 ,self.z)
else:
self.output = T.nnet.sigmoid(self.z)
self.y_pred = self.output > 0.5
self.params = [self.W, self.b]
def cost_function(self,y):
return -T.mean(y*T.log(self.output)+(1-y)*T.log(1-self.output))
def errors(self,y):
return T.mean(T.neq(self.y_pred,y))
alfa = 1
epoch = 1000
neu = 5
inpx = np.array([[1,0],[1,1],[0,0],[0,1]])
inpy = np.array([1,0,0,1])
x = T.fmatrix('x')
y = T.ivector('y')
layer0 = HiddenLayer(
input = x,
nIn = 2,
nOut = neu,
is_last=0
)
layer1 = HiddenLayer(
input = layer0.output,
nIn = neu,
nOut = 1,
is_last=1
)
params = layer0.params + layer1.params
cost = layer1.cost_function(y)
grads = T.grad(cost, params)
updates = [(param_i, param_i - alfa * grad_i) for param_i, grad_i in zip(params, grads)]
eror = layer1.errors(y)
train_model = theano.function([x,y], [eror,cost],updates=updates,allow_input_downcast=True)
test_model = theano.function([x,y],[eror,layer1.y_pred],allow_input_downcast=True)
for i in xrange(epoch):
etr,ctr = train_model(inpx, inpy)
if i%(epoch/10)==0:
print etr,ctr
et,pt = test_model(inpx,inpy)
print pt
and the error:
ValueError: Input dimension mis-match. (input[0].shape[1] = 1, input[1].shape[1] = 4)
Apply node that caused the error: Elemwise{neq,no_inplace}(sigmoid.0, DimShuffle{x,0}.0)
Toposort index: 41
Inputs types: [TensorType(float32, matrix), TensorType(int32, row)]
Inputs shapes: [(4L, 1L), (1L, 4L)]
Inputs strides: [(4L, 4L), (16L, 4L)]
Inputs values: [array([[ 0.94264328],
[ 0.99725735],
[ 0.5 ],
[ 0.95675617]], dtype=float32), array([[1, 0, 0, 1]])]
Outputs clients: [[Shape(Elemwise{neq,no_inplace}.0), Sum{acc_dtype=int64}(Elemwise{neq,no_inplace}.0)]]
Thank you in advance for any help.
Your problem is with your y and inpy variables: what you are trying to do is to have y be the expected output of the network. Your network is given a dataset with 4 elements, each having 2 features, you thus have 4 rows in your input matrix, and 2 columns. You are thus expected to have 4 elements in your predicted output, that is 4 rows in your y or inpy matrix, but you are using a vector, which in theano is a row vector and thus has only one row. You need either to transpose your y vector when computing the cost, or to define your y variable as a matrix, and thus to have inpy as a (4,1) matrix instead of a (4,) vector (once again, vectors are row vectors in theano).
Hope this helps,
Best

Categories

Resources