How do I explain this TensorFlow tf.nn.conv2d() layer shape? - python

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]

Related

Logits and labels have different first dimensions

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.

tf.layers.conv2d and tf.nn.conv2d Different outputs with same architecture

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

Dimensionality error after applying a dense layer

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.

Changing Tensorflow number of convolutional and pooling layers using MNIST dataset

I am using Windows 10 pro, python 3.6.2rc1, Visual Studio 2017, and Tensorflow. I am working with Tensorflow example in its tutorial in the following link:
https://www.tensorflow.org/tutorials/layers
I have added another layer of convolution and pooling before flattening the last layer (3rd layer) to see if the accuracy changes.
The code I have added is as follows:
## Input Tensor Shape: [batch_size, 7, 7, 64]
## Output Tensor Shape: [batch_size, 7, 7, 64]
conv3 = tf.layers.conv2d(
inputs=pool2,
filters=64,
kernel_size=[3, 3],
padding=1,
activation=tf.nn.relu)
pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], strides=1)
pool3_flat = tf.reshape(pool3, [-1, 7* 7 * 64])
The reason I have changed padding to 1 and stride to 1 is to make sure the size of output is the same as input. But after adding this new layer I get the following warnings and without showing any result the program ends:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
est = Estimator(...) -> est = SKCompat(Estimator(...))
WARNING:tensorflow:From E:\Apps\DA2CNNTest\TFHWDetection WIth More Layers\TFClassification\TFClassification\TFClassification.py:179: calling BaseEstimator.fit (from tensorflow.contrib.learn.python.learn.estimators.estimator) with batch_size is deprecated and will be removed after 2016-12-01.
Instructions for updating:
Estimator is decoupled from Scikit Learn interface by moving into
separate class SKCompat. Arguments x, y and batch_size are only
available in the SKCompat class, Estimator will only accept input_fn.
Example conversion:
est = Estimator(...) -> est = SKCompat(Estimator(...))
The thread 'MainThread' (0x5c8) has exited with code 0 (0x0).
The program '[13468] python.exe' has exited with code 1 (0x1).
Without adding this layer it works properly. In order to solve this problem I changed the conv3 and pool3 as follows:
conv3 = tf.layers.conv2d(
inputs=pool2,
filters=64,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Input Tensor Shape: [batch_size, 7, 7, 64]
# Output Tensor Shape: [batch_size, 3, 3, 64]
pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], strides=2)
pool3_flat = tf.reshape(pool3, [-1, 3* 3 * 64])
but then I got a different error at
nist_classifier.fit(
x=train_data,
y=train_labels,
batch_size=100,
steps=20000,
monitors=[logging_hook])
which is as follows:
tensorflow.python.framework.errors_impl.NotFoundError: Key conv2d_2/bias not found in checkpoint
[[Node: save/RestoreV2_5 = RestoreV2[dtypes=[DT_FLOAT], _device="/job:localhost/replica:0/task:0/cpu:0"](_arg_save/Const_0_0, save/RestoreV2_5/tensor_names, save/RestoreV2_5/shape_and_slices)]]
The error is exactly refering to monitors=[logging_hook].
My whole code is as follow and as you see I have commented the previous one with padding=1.
I really appreciate if you can guide me what my mistake is and why is it so. Moreover, I am correct with the dimension of my inputs and outputs in the 3rd layer?
Complete code:
"""Convolutional Neural Network Estimator for MNIST, built with tf.layers."""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import numpy as np
import tensorflow as tf
from tensorflow.contrib import learn
from tensorflow.contrib.learn.python.learn.estimators import model_fn as model_fn_lib
tf.logging.set_verbosity(tf.logging.INFO)
def cnn_model_fn(features, labels, mode):
"""Model function for CNN."""
input_layer = tf.reshape(features, [-1, 28, 28, 1])
# Input Tensor Shape: [batch_size, 28, 28, 1]
# Output Tensor Shape: [batch_size, 28, 28, 32]
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=32,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Input Tensor Shape: [batch_size, 28, 28, 32]
# Output Tensor Shape: [batch_size, 14, 14, 32]
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[2, 2], strides=2)
# Convolutional Layer #2
# Input Tensor Shape: [batch_size, 14, 14, 32]
# Output Tensor Shape: [batch_size, 14, 14, 64]
conv2 = tf.layers.conv2d(
inputs=pool1,
filters=64,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Pooling Layer #2
# Input Tensor Shape: [batch_size, 14, 14, 64]
# Output Tensor Shape: [batch_size, 7, 7, 64]
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[2, 2], strides=2)
'''Adding a new layer of conv and pool'''
## Input Tensor Shape: [batch_size, 7, 7, 32]
## Output Tensor Shape: [batch_size, 7, 7, 64]
#conv3 = tf.layers.conv2d(
# inputs=pool2,
# filters=64,
# kernel_size=[3, 3],
# padding=1,
# activation=tf.nn.relu)
## Input Tensor Shape: [batch_size, 7, 7, 64]
## Output Tensor Shape: [batch_size, 7, 7, 64]
#pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], strides=1)
#pool3_flat = tf.reshape(pool3, [-1, 7* 7 * 64])
# Input Tensor Shape: [batch_size, 7, 7, 64]
# Output Tensor Shape: [batch_size, 7, 7, 64]
conv3 = tf.layers.conv2d(
inputs=pool2,
filters=64,
kernel_size=[5, 5],
padding="same",
activation=tf.nn.relu)
# Input Tensor Shape: [batch_size, 7, 7, 64]
# Output Tensor Shape: [batch_size, 3, 3, 64]
pool3 = tf.layers.max_pooling2d(inputs=conv3, pool_size=[2, 2], strides=2)
'''End of manipulation'''
# Input Tensor Shape: [batch_size, 3, 3, 64]
# Output Tensor Shape: [batch_size, 3 * 3 * 64]
pool3_flat = tf.reshape(pool3, [-1, 3* 3 * 64])
# Input Tensor Shape: [batch_size, 3 * 3 * 64]
# Output Tensor Shape: [batch_size, 1024]
# dense(). Constructs a dense layer. Takes number of neurons and activation function as arguments.
dense = tf.layers.dense(inputs=pool3_flat, units=1024, activation=tf.nn.relu)
# Add dropout operation; 0.6 probability that element will be kept
dropout = tf.layers.dropout(
inputs=dense, rate=0.4, training=mode == learn.ModeKeys.TRAIN)
logits = tf.layers.dense(inputs=dropout, units=10)
loss = None
train_op = None
# Calculate Loss (for both TRAIN and EVAL modes)
if mode != learn.ModeKeys.INFER:
onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=10)
loss = tf.losses.softmax_cross_entropy(
onehot_labels=onehot_labels, logits=logits)
# Configure the Training Op (for TRAIN mode)
if mode == learn.ModeKeys.TRAIN:
train_op = tf.contrib.layers.optimize_loss(
loss=loss,
global_step=tf.contrib.framework.get_global_step(),
learning_rate=0.001,
optimizer="SGD")
# Generate Predictions
# The logits layer of our model returns our predictions as raw values in a [batch_size, 10]-dimensional tensor.
predictions = {
"classes": tf.argmax(
input=logits, axis=1),
"probabilities": tf.nn.softmax(
logits, name="softmax_tensor")
}
# Return a ModelFnOps object
return model_fn_lib.ModelFnOps(
mode=mode, predictions=predictions, loss=loss, train_op=train_op)
def main(unused_argv):
# Load training and eval data
mnist = learn.datasets.load_dataset("mnist")
train_data = mnist.train.images # Returns np.array
train_labels = np.asarray(mnist.train.labels, dtype=np.int32)
eval_data = mnist.test.images # Returns np.array
eval_labels = np.asarray(mnist.test.labels, dtype=np.int32)
# Create the Estimator
mnist_classifier = learn.Estimator(
model_fn=cnn_model_fn, model_dir="/tmp/mnist_convnet_model")
# Set up logging for predictions
# Log the values in the "Softmax" tensor with label "probabilities"
tensors_to_log = {"probabilities": "softmax_tensor"}
logging_hook = tf.train.LoggingTensorHook(
tensors=tensors_to_log, every_n_iter=50)
# Train the model
mnist_classifier.fit(
x=train_data,
y=train_labels,
batch_size=100,
steps=20000,
monitors=[logging_hook])
# Configure the accuracy metric for evaluation
#change metrics variable name
metricss = {
"accuracy":
learn.MetricSpec(
metric_fn=tf.metrics.accuracy, prediction_key="classes"),
}
#Evaluate the model and print results
#for i in range(100)
eval_results = mnist_classifier.evaluate(
x=eval_data[0:100], y=eval_labels[0:100], metrics=metricss)
print(eval_results)
if __name__ == "__main__":
tf.app.run()
The error looks like the trained model which is available in the model_dir conflicts with the current graph changes. The Estimator loads checkpoints from the saved model directory and continue training from the previous saved model. So whenever your making changes in the model, you need to delete the old model and start training again.
A simple fix for this would be to define a custom checkpoint directory for the model as follows.
tf.train.generate_checkpoint_state_proto("/tmp/","/tmp/mnist_convnet_model")
This fixes the problem with the MNIST example and also gives you access to a location where you can control checkpoints.

Tensorflow CNN - Dense layer as Softmax layer input

I'm trying to replicate the CNN described in
https://pdfs.semanticscholar.org/3b57/85ca3c29c963ae396c2f94ba1a805c787cc8.pdf
and I'm stuck at the last layer. I've modeled the cnn like this
# Model function for CNN
def cnn_model_fn(features, labels, mode):
# Input Layer
# Reshape X to 4-D tensor: [batch_size, width, height, channels]
# Taxes images are 150x150 pixels, and have one color channel
input_layer = tf.reshape(features, [-1, 150, 150, 1])
# Convolutional Layer #1
# Input Tensor Shape: [batch_size, 150, 150, 1]
# Output Tensor Shape: [batch_size, 144, 144, 20]
conv1 = tf.layers.conv2d(
inputs=input_layer,
filters=20,
kernel_size=[7, 7],
padding="valid",
activation=tf.nn.relu)
# Pooling Layer #1
# Input Tensor Shape: [batch_size, 144, 144, 20]
# Output Tensor Shape: [batch_size, 36, 36, 20]
pool1 = tf.layers.max_pooling2d(inputs=conv1, pool_size=[4, 4], strides=4)
# Convolutional Layer #2
# Input Tensor Shape: [batch_size, 36, 36, 20]
# Output Tensor Shape: [batch_size, 32, 32, 50]
conv2 = tf.layers.conv2d(
inputs=pool1,
filters=50,
kernel_size=[5, 5],
padding="valid",
activation=tf.nn.relu)
# Pooling Layer #2
# Input Tensor Shape: [batch_size, 32, 32, 50]
# Output Tensor Shape: [batch_size, 8, 8, 50]
pool2 = tf.layers.max_pooling2d(inputs=conv2, pool_size=[4, 4], strides=4)
# Flatten tensor into a batch of vectors
# Input Tensor Shape: [batch_size, 8, 8, 50]
# Output Tensor Shape: [batch_size, 8 * 8 * 50]
pool2_flat = tf.reshape(pool2, [-1, 8 * 8 * 50])
# Dense Layer #1
# Densely connected layer with 1000 neurons
# Input Tensor Shape: [batch_size, 8 * 8 * 50]
# Output Tensor Shape: [batch_size, 1000]
dense1 = tf.layers.dense(inputs=pool2_flat, units=1000, activation=tf.nn.relu)
# Dense Layer #2
# Densely connected layer with 1000 neurons
# Input Tensor Shape: [batch_size, 1000]
# Output Tensor Shape: [batch_size, 1000]
dense2 = tf.layers.dense(inputs=dense1, units=1000, activation=tf.nn.relu)
# Add dropout operation; 0.5 probability that element will be kept
dropout = tf.layers.dropout(
inputs=dense2, rate=0.5, training=mode == learn.ModeKeys.TRAIN)
# Logits layer
# Input Tensor Shape: [batch_size, 1000]
# Output Tensor Shape: [batch_size, 4]
logits = tf.layers.dense(inputs=dropout, units=nClass)
loss = None
train_op = None
# Calculate Loss (for both TRAIN and EVAL modes)
if mode != learn.ModeKeys.INFER:
onehot_labels = tf.one_hot(indices=tf.cast(labels, tf.int32), depth=nClass)
loss = tf.losses.softmax_cross_entropy(
onehot_labels=onehot_labels, logits=logits)
# Configure the Training Op (for TRAIN mode)
if mode == learn.ModeKeys.TRAIN:
train_op = tf.contrib.layers.optimize_loss(
loss=loss,
global_step=tf.contrib.framework.get_global_step(),
learning_rate=0.001,
optimizer="SGD")
# Generate Predictions
predictions = {
"classes": tf.argmax(
input=logits, axis=1)
}
# Return a ModelFnOps object
return model_fn_lib.ModelFnOps(
mode=mode, predictions=predictions, loss=loss, train_op=train_op)
but the final accuracy is really poor (0.25). So I realized that actually the paper states that the last layer is a softmax layer. So i tried changed my logits layer to
logits = tf.layers.softmax(dropout)
but when I run it, it says
ValueError: Shapes (?, 1000) and (?, 4) are incompatible
So, what I'm missing here?
The original one was correct. The softmax activation is applied while calculating the loss with tf.losses.softmax_cross_entropy. If you want to calculate it separately you should add it after the logits calculation, but without replacing it as you did.
logits = tf.layers.dense(inputs=dropout, units=nClass)
softmax = tf.layers.softmax(logits)
Or you can combine both in one, but I wouldn't recommend it. It is better to calculate the softmax with the loss.
logits = tf.layers.dense(inputs=dropout, units=nClass, activation=tf.layers.softmax)
Your classifier is not doing better than random, so I would say that the problem lays somewhere else, maybe in the data loading and preprocessing.

Categories