I am trying to add a dense layer after applying dropout to the max pooled convolutional layer output.
I have the following TensorFlow code written in Python. Number of filters is 128 and len(filter_sizes) is 3
pooled_outputs = []
for i, filter_size in enumerate(filter_sizes):
with tf.name_scope("conv-maxpool-%s" % filter_size):
# Convolution Layer
filter_shape = [filter_size, embedding_size, 1, num_filters]
W = tf.Variable(tf.truncated_normal(filter_shape, stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
conv = tf.nn.conv2d(
self.embedded_chars_expanded,
W,
strides=[1, 1, 1, 1],
padding="VALID",
name="conv")
# Applying batch normalization
# h = tf.contrib.layers.batch_norm(conv, center=True, scale=True, is_training=True)
# Apply nonlinearity
h1 = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
# Maxpooling over the outputs
pooled = tf.nn.max_pool(
h1,
ksize=[1, sequence_length - filter_size + 1, 1, 1],
strides=[1, 1, 1, 1],
padding='VALID',
name="pool")
pooled_outputs.append(pooled)
# Combine all the pooled features
num_filters_total = num_filters * len(filter_sizes)
self.h_pool = tf.concat(pooled_outputs, 3)
self.h_pool_flat = tf.reshape(self.h_pool, [-1, num_filters_total])
# Add dropout
with tf.name_scope("dropout"):
#self.h_drop = tf.nn.dropout(dense, self.dropout_keep_prob)
self.h_drop = tf.nn.dropout(self.h_pool_flat, self.dropout_keep_prob)
# Adding dense layer
dense = tf.layers.dense(self.h_drop, units=num_classes, activation=tf.nn.relu)
Facing issues after the application of the dense layer.
Following is the error:
Dimensions must be equal, but are 11 and 384 for 'output/scores/MatMul' (op: 'MatMul') with input shapes: [?,11], [384,11]
Could someone please help me with it?
The error was with the indices of the matrices. I was using the xw_plus_b function provided by tensorflow and using the dimensions of the matrices for multiplication wrong.
Related
My Tensorflow convolutional layer has a shape I did not expect it to have and I do not see the mistake.
I am new to TensorFlow and want to use this function to create a convolutional layer:
def new_conv_layer(input, # The previous layer.
num_input_channels, # Num. channels in prev. layer.
filter_size, # Width and height of each filter.
num_filters, # Number of filters.
use_pooling=True): # Use 2x2 max-pooling.
shape = [filter_size, filter_size, num_input_channels, num_filters]
weights = new_weights(shape=shape)
biases = new_biases(length=num_filters)
layer = tf.nn.conv2d(input=input_,
filters=weights,
strides=[1, 1, 1, 1],
padding='SAME')
layer += biases
if use_pooling:
layer = tf.nn.max_pool(input=layer,
ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1],
padding='SAME')
layer = tf.nn.relu(layer)
return layer, weights
But when I use it with
num_channels = 1
img_size = 28
x_image = tf.reshape(x, [-1, img_size, img_size, num_channels])
# Convolutional Layer 1.
filter_size1 = 5 # Convolution filters are 5 x 5 pixels.
num_filters1 = 16 # There are 16 of these filters.
layer_conv1, weights_conv1 = new_conv_layer(input=x_image,
num_input_channels=num_channels,
filter_size=filter_size1,
num_filters=num_filters1,
use_pooling=True)
layer_conv1
I get this output:
<tf.Tensor 'Relu:0' shape=(None, 392, 392, 16) dtype=float32>
Because my images are of a square 28x28 shape and I apply 2x2 pooling, I would have expected this shape to be (None, 14, 14, 16).
Why is that not the case and how do I fix it?
in my case this line x = tf.compat.v1.placeholder(tf.float32, shape=[None, img_size_flat], name='x') was incorrect!
In particular img_size_flat was not the length of each "stretched" image, as it should have been.
img_size_flat = df.drop('label', axis=1).shape[1]
This was the error I got: InvalidArgumentError (see above for traceback): logits and labels must have the same first dimension, got logits shape [30,5] and labels shape [50]
I'm using a batch size of of 50. The number of outputs for my classification problem is 5.
I have no idea where the 30 in the logits shape is coming from. This is my architecture:
with tf.name_scope("pool3"):
pool3 = tf.nn.max_pool(conv2, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding="VALID")
pool3_flat = tf.reshape(pool3, shape=[-1, 24000]) # must be a multiple of the input
pool3_flat_drop = tf.layers.dropout(pool3_flat, conv2_dropout_rate, training=training)
with tf.name_scope("fc1"):
flattened = tf.layers.flatten(pool3_flat_drop)
fc1 = tf.layers.dense(flattened , n_fc1, activation=tf.nn.relu, name="fc1")
fc1_drop = tf.layers.dropout(fc1, fc1_dropout_rate, training=training)
with tf.name_scope("output"):
# n_outputs = number of possible classes
logits = tf.layers.dense(fc1_drop, n_outputs, name="output")
Y_proba = tf.nn.softmax(logits, name="Y_proba")
with tf.name_scope("train"):
xentropy = tf.nn.sparse_softmax_cross_entropy_with_logits(logits=logits, labels=y)
Also here is how I declared my placeholders
with tf.name_scope('inputs'):
X = tf.placeholder(tf.float32, shape=[None, n_inputs], name='X')
X_reshaped = tf.reshape(X, shape=[-1, height, width, channels]) # make applicable to convolutional
y = tf.placeholder(tf.int32, shape=[None], name='y')
training = tf.placeholder_with_default(False, shape=[], name='training')
I think it is caused by pool3_flat = tf.reshape(pool3, shape=[-1, 24000])
You are supposed to check whether the 24000 is right.
Note: I read the similar thread here, but it doesn't cover my use case.
I'm building a GAN and am converting my discriminator design from using tf.nn.conv2d (following some example code) to tf.layers.conv2d. Both designs use the same inputs, kernel sizes, strides, yet I'm getting different results between the two.
Both versions should be 28x28x1 input -> conv2d with a 5x5 kernel, 2 stride, 16 layers, leaky relu -> conv2d with a 3x3 kernel, 2 stride, 32 layers, leaky relu -> flatten to 7*7*32 -> 256 neuron dense network with leaky relu -> 1 value output.
I've checked the weight initialization. tf.layers.conv2d defaults to
xaiver init as shown here.
layers version:
def discriminator(x):
# Reshape to a 28x28 image with one layer of depth (greyscale)
x = tf.reshape(x, shape=[-1, 28, 28, 1])
with tf.variable_scope('discriminator', reuse=tf.AUTO_REUSE) as scope:
# Defaults to Xavier init for weights and Zeros for bias
disc_conv1 = tf.layers.conv2d(
inputs = x,
filters = 16,
kernel_size=5,
strides=2,
padding="same",
activation=tf.nn.leaky_relu
)
disc_conv2 = tf.layers.conv2d(
inputs = disc_conv1,
filters = 32,
kernel_size=3,
strides=2,
padding="same",
activation=tf.nn.leaky_relu
)
disc_conv2 = tf.reshape(disc_conv2, shape=[-1, 7 * 7 * 32])
disc_h1 = tf.layers.dense(disc_conv2, units=hidden1_dim, activation=tf.nn.leaky_relu)
disc_logits = tf.layers.dense(disc_h1, units=1)
disc_out = tf.nn.sigmoid(disc_logits)
return disc_logits, disc_out
nn version:
DC_D_W1 = tf.get_variable('DC_D_W1', shape=[5, 5, 1, 16], initializer=tf.contrib.layers.xavier_initializer())
DC_D_b1 = tf.get_variable('2', initializer=tf.zeros(shape=[16]))
DC_D_W2 = tf.get_variable('3', shape=[3, 3, 16, 32], initializer=tf.contrib.layers.xavier_initializer())
DC_D_b2 = tf.get_variable('4', initializer=tf.zeros(shape=[32]))
DC_D_W3 = tf.get_variable('5', shape=[7 * 7 * 32, 256], initializer=tf.contrib.layers.xavier_initializer())
DC_D_b3 = tf.get_variable('6', initializer=tf.zeros(shape=[256]))
DC_D_W4 = tf.get_variable('7', shape= [256, 1], initializer=tf.contrib.layers.xavier_initializer())
DC_D_b4 = tf.get_variable('8', initializer=tf.zeros(shape=[1]))
theta_DC_D = [DC_D_W1, DC_D_b1, DC_D_W2, DC_D_b2, DC_D_W3, DC_D_b3, DC_D_W4, DC_D_b4]
def discriminator(x):
x = tf.reshape(x, shape=[-1, 28, 28, 1])
conv1 = tf.nn.leaky_relu(tf.nn.conv2d(x, DC_D_W1, strides=[1, 2, 2, 1], padding='SAME') + DC_D_b1)
conv2 = tf.nn.leaky_relu(tf.nn.conv2d(conv1, DC_D_W2, strides=[1, 2, 2, 1], padding='SAME') + DC_D_b2)
conv2 = tf.reshape(conv2, shape=[-1, 7 * 7 * 32])
h = tf.nn.leaky_relu(tf.matmul(conv2, DC_D_W3) + DC_D_b3)
logit = tf.matmul(h, DC_D_W4) + DC_D_b4
prob = tf.nn.sigmoid(logit)
return logit, prob
What dimensions are required in tf.nn.conv1d ? and how to perform max pooling afterwards?
A simple example snip:
filter = tf.zeros([3, 16, 16])
W = tf.Variable(tf.truncated_normal(filter, stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[num_filters]), name="b")
conv = tf.nn.conv1d(
input_values,
W,
strides=2,
padding="VALID",
name="conv")
# nonlinearity operation
h = tf.nn.relu(tf.nn.bias_add(conv, b), name="relu")
# Maxpooling over the outputs
pooled = tf.nn.max_pool(
h,
ksize=[1, sequence_length - filter_size + 1, 1, 1],
strides=[1, 1, 1, 1],
padding='VALID',
name="pool")
pooled_outputs.append(pooled)
Check this answer as well.
Looking at the tensorflow page: https://github.com/tensorflow/models/tree/master/inception
They show an image with their architecture, specifically their 'inception' modules which contain in parallel:
conv layer of 1x1
conv layer of 3x3
conv layer of 5x5
ave pooling + 1x1 conv
Followed by an 'concat' layer.
How can I create this in tensorflow?
I figured I could do something along the lines of this to create the parallel operations:
start_layer = input_data
filter = tf.Variable(tf.truncated_normal([1,1,channels,filter_count], stddev=0.1)
one_by_one = tf.nn.conv2d(start_layer, filter, strides=[1,1,1,1], padding='SAME')
filter = tf.Variable(tf.truncated_normal([3,3,channels,filter_count], stddev=0.1)
three_by_three = tf.nn.conv2d(start_layer, filter, strides=[1,1,1,1], padding='SAME')
filter = tf.Variable(tf.truncated_normal([5,5,channels,filter_count], stddev=0.1)
five_by_five = tf.nn.conv2d(start_layer, filter, strides=[1,1,1,1], padding='SAME')
filter = tf.Variable(tf.truncated_normal([1,1,channels,filter_count], stddev=0.1)
pooling = tf.nn.avg_pool(start_layer, filter, strides=[1,2,2,1], padding='SAME')
filter = tf.Variable(tf.truncated_normal([1,1,channels,filter_count], stddev=0.1)
pooling = tf.nn.conv2d(pooling, filter, strides=[1,1,1,1], padding='SAME')
#connect one_by_one, three_by_three, five_by_five, pooling into an concat layer
But how do I combine the 4 operations into an concat layer?
I did something very similar to what you did, and then finished it off with tf.concat(). Note the axis=3 which matches my 4d tensors and concats to the 4th dimension (index 3).
Documentation for it is here.
My final code ended up something like this:
def inception2d(x, in_channels, filter_count):
# bias dimension = 3*filter_count and then the extra in_channels for the avg pooling
bias = tf.Variable(tf.truncated_normal([3*filter_count + in_channels], mu, sigma)),
# 1x1
one_filter = tf.Variable(tf.truncated_normal([1, 1, in_channels, filter_count], mu, sigma))
one_by_one = tf.nn.conv2d(x, one_filter, strides=[1, 1, 1, 1], padding='SAME')
# 3x3
three_filter = tf.Variable(tf.truncated_normal([3, 3, in_channels, filter_count], mu, sigma))
three_by_three = tf.nn.conv2d(x, three_filter, strides=[1, 1, 1, 1], padding='SAME')
# 5x5
five_filter = tf.Variable(tf.truncated_normal([5, 5, in_channels, filter_count], mu, sigma))
five_by_five = tf.nn.conv2d(x, five_filter, strides=[1, 1, 1, 1], padding='SAME')
# avg pooling
pooling = tf.nn.avg_pool(x, ksize=[1, 3, 3, 1], strides=[1, 1, 1, 1], padding='SAME')
x = tf.concat([one_by_one, three_by_three, five_by_five, pooling], axis=3) # Concat in the 4th dim to stack
x = tf.nn.bias_add(x, bias)
return tf.nn.relu(x)