Writing the following CNN in tensorflow - tensorflow

Question

I am new to this Deep Learning. I have learnt the basics through reading and trying to implement a real network to see how/if it'll really work. I chose Tensorflow in digits and the following network because they give out the exact architecture with training materiel. Steganalysis with DL
I wrote the following code for the architecture in Steganalysis with DL by looking at networks existing networks in digits and Tensorflow documentation.
from model import Tower
from utils import model_property
import tensorflow as tf
import tensorflow.contrib.slim as slim
import utils as digits
class UserModel(Tower):
#model_property
def inference(self):
x = tf.reshape(self.x, shape=[-1, self.input_shape[0], self.input_shape[1], self.input_shape[2]])
with slim.arg_scope([slim.conv2d, slim.fully_connected],
weights_initializer=tf.contrib.layers.xavier_initializer(),
weights_regularizer=slim.l2_regularizer(0.0001)):
conv1 = tf.layers.conv2d(inputs=x, filters=64, kernel_size=7, padding='same', strides=2, activation=tf.nn.relu)
rnorm1 = tf.nn.local_response_normalization(input=conv1)
conv2 = tf.layers.conv2d(inputs=rnorm1, filters=16, kernel_size=5, padding='same', strides=1, activation=tf.nn.relu)
rnorm2 = tf.nn.local_response_normalization(input=conv2)
flatten = tf.contrib.layers.flatten(rnorm2)
fc1 = tf.contrib.layers.fully_connected(inputs=flatten, num_outputs=1000, activation_fn=tf.nn.relu)
fc2 = tf.contrib.layers.fully_connected(inputs=fc1, num_outputs=1000, activation_fn=tf.nn.relu)
fc3 = tf.contrib.layers.fully_connected(inputs=fc2, num_outputs=2)
sm = tf.nn.softmax(fc3)
return fc3
#model_property
def loss(self):
model = self.inference
loss = digits.classification_loss(model, self.y)
accuracy = digits.classification_accuracy(model, self.y)
self.summaries.append(tf.summary.scalar(accuracy.op.name, accuracy))
return loss
I tried running it but the accuracy is pretty low. Could someone tell me if I've done it completely wrong or what's wrong with it and tell me how to properly code it?
UPDATE: Thank you Nessuno! With the fix you mentioned I came up with this code:
from model import Tower
from utils import model_property
import tensorflow as tf
import tensorflow.contrib.slim as slim
import utils as digits
class UserModel(Tower):
#model_property
def inference(self):
x = tf.reshape(self.x, shape=[-1, self.input_shape[0], self.input_shape[1], self.input_shape[2]])
with slim.arg_scope([slim.conv2d, slim.fully_connected],
weights_initializer=tf.contrib.layers.xavier_initializer(),
weights_regularizer=slim.l2_regularizer(0.00001)):
conv1 = tf.layers.conv2d(inputs=x, filters=64, kernel_size=7, padding='Valid', strides=2, activation=tf.nn.relu)
rnorm1 = tf.nn.local_response_normalization(input=conv1)
conv2 = tf.layers.conv2d(inputs=rnorm1, filters=16, kernel_size=5, padding='Valid', strides=1, activation=tf.nn.relu)
rnorm2 = tf.nn.local_response_normalization(input=conv2)
flatten = tf.contrib.layers.flatten(rnorm2)
fc1 = tf.contrib.layers.fully_connected(inputs=flatten, num_outputs=1000, activation_fn=tf.nn.relu)
fc2 = tf.contrib.layers.fully_connected(inputs=fc1, num_outputs=1000, activation_fn=tf.nn.relu)
fc3 = tf.contrib.layers.fully_connected(inputs=fc2, num_outputs=2, activation_fn=None)
return fc3
#model_property
def loss(self):
model = self.inference
loss = digits.classification_loss(model, self.y)
accuracy = digits.classification_accuracy(model, self.y)
self.summaries.append(tf.summary.scalar(accuracy.op.name, accuracy))
return loss
Solver type is SGD. Learning rate is 0.001. I am shuffling training data.I have increased training data to 6000 (3000 per category, 20% from that is reserved for validation). I downloaded the training data from this link. But I am only getting the following graph. I think this is overfitting. Do you have any suggestions to improve the validation accuracy?

Answer 1

In NVIDIA digits, classification_loss, exactly as in tensorflow tf.nn.softmax_cross_entropy_with_logits expects as input a linear layer of neuron.
Instead, you're passing as input sm = tf.nn.softmax(fc3), hence you're applying the softmax operation 2 times and this is the reasong of your low accuracy.
In order to solve this issue, just change the model output layer to
fc3 = slim.fully_connected(fc2, 2, activation_fn=None, scope='fc3')
return fc3