Practical Convolutional Neural Networks

Step 5 – Preparing the TensorFlow graph

We now create the placeholders for the TensorFlow graph:

x = tf.placeholder(tf.float32, shape=[None, img_size_flat], name='x') 
x_image = tf.reshape(x, [-1, img_size, img_size, num_channels]) 
y_true = tf.placeholder(tf.float32, shape=[None, num_classes], name='y_true') 
y_true_cls = tf.argmax(y_true, axis=1)