I am applying dropout to the first layer in the following way :
out = layers.fully_connected(X, num_outputs=hidden[0], activation_fn=None)
out1 = tf.nn.relu(out)
drop_out = tf.nn.dropout(out1, keep_prob) #keep_prob = 0.5
out2 = layers.fully_connected(drop_out, num_outputs=hidden[1], activation_fn=None)
out2 = tf.nn.relu(out2)
out3 = layers.fully_connected(out4, num_outputs=num_actions, activation_fn=None)
But I cannot see dropout in tensorboard computational graph. Do I need to explicitly write a command in the summary to include Dropout layer ?
