machine learning - Someone can explain to me the design of a Convolutional NN with tensorflow (hand written digits)? (input img : 28 x 28 | output : 10 (n_classes)) -

i'm trying started cnn designs, found piece of code try infer design (f.maps size, strides ....).

what i've understoud have : input --> conv5-32 --> maxpool --> conv5-5 --> maxpool --> fc1 --> outputs.

what i'm not getting right input of fc1, why it's 7 7 ?

could please me ? (i'm beginner)

import tensorflow tf  tensorflow.examples.tutorials.mnist import input_data  mnist = input_data.read_data_sets('/tmp/data/', one_hot=true)   #parameters learning_rate = 0.001 training_iters = 200000 batch_size = 28 display_step = 10   #network parameters  n_input = 784 n_output = 10 dropout  = 0.75  #tf grath input x = tf.placeholder(tf.float32, [none,n_input]) y = tf.placeholder(tf.float32, [none, n_output]) keep_prob = tf.placeholder(tf.float32)    # create wrappers simplicity def conv2d(x, w, b, strides=1):     # conv2d wrapper, bias , relu activation     x = tf.nn.conv2d(x, w, strides=[1, strides, strides, 1], padding='same')     x = tf.nn.bias_add(x, b)     return tf.nn.relu(x)   def maxpool2d(x, k=2):     # maxpool2d wrapper     return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],                           padding='same')     # create model def conv_net(x, weights, biases, dropout):     # reshape input picture     x = tf.reshape(x, shape=[-1, 28, 28, 1])      # convolution layer     conv1 = conv2d(x, weights['wc1'], biases['bc1'])     # max pooling (down-sampling)     conv1 = maxpool2d(conv1, k=2)      # convolution layer     conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])     # max pooling (down-sampling)     conv2 = maxpool2d(conv2, k=2)      # connected layer     # reshape conv2 output fit connected layer input     fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])     fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])     fc1 = tf.nn.relu(fc1)     # apply dropout     fc1 = tf.nn.dropout(fc1, dropout)      # output, class prediction     out = tf.add(tf.matmul(fc1, weights['out']), biases['out'])     return out     # store layers weight & bias weights = {     # 5x5 conv, 1 input, 32 outputs     'wc1': tf.variable(tf.random_normal([5, 5, 1, 32])),     # 5x5 conv, 32 inputs, 64 outputs     'wc2': tf.variable(tf.random_normal([5, 5, 32, 5])),     # connected, 7*7*64 inputs, 1024 outputs     'wd1': tf.variable(tf.random_normal([7*7*64, 1024])),     # 1024 inputs, 10 outputs (class prediction)     'out': tf.variable(tf.random_normal([1024, n_classes])) }  biases = {     'bc1': tf.variable(tf.random_normal([32])),     'bc2': tf.variable(tf.random_normal([64])),     'bd1': tf.variable(tf.random_normal([1024])),     'out': tf.variable(tf.random_normal([n_classes])) } 

it's because of max-pooling. divides size of input 2 on each dimension.

so after first max-pooling, 28x28 becomes 14x14, 7x7 after second.