CODEWITHSUNDEEP
pythontensorflowmatplotlib
kitty
kitty

Reputation: 75

How to plot training error , validation error and prediction accuracy over training progress in tensorflow?

I am running Vanilla RNN code on tensorflow in google colab. I want to plot training error, validation error and prediction accuracy over training progress without using tensorboard. I am new to tensorflow. Can anyone please guide me. Here is a part of my code 

       # Model predictions
    cls_prediction = tf.argmax(output_logits, axis=1, name='predictions')

    # Define the loss function, optimizer, and accuracy
    loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=y, logits=output_logits), name='loss')
    optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate, name='Adam-op').minimize(loss)
    correct_prediction = tf.equal(tf.argmax(output_logits, 1), tf.argmax(y, 1), name='correct_pred')
    accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')
init = tf.global_variables_initializer()
sess = tf.InteractiveSession()
sess.run(init)
global_step = 0
# Number of training iterations in each epoch
num_tr_iter = int(len(y_train) / batch_size)
for epoch in range(epochs):
    print('Training epoch: {}'.format(epoch + 1))
    x_train, y_train = randomize(x_train, y_train)
    for iteration in range(num_tr_iter):
        global_step += 1
        start = iteration * batch_size
        end = (iteration + 1) * batch_size
        x_batch, y_batch = get_next_batch(x_train, y_train, start, end)
        x_batch = x_batch.reshape((batch_size, timesteps, num_input))
        # Run optimization op (backprop)
        feed_dict_batch = {x: x_batch, y: y_batch}
        sess.run(optimizer, feed_dict=feed_dict_batch)

        if iteration % display_freq == 0:
            # Calculate and display the batch loss and accuracy
            loss_batch, acc_batch = sess.run([loss, accuracy],
                                             feed_dict=feed_dict_batch)

            print("iter {0:3d}:\t Loss={1:.2f},\tTraining Accuracy={2:.01%}".
                  format(iteration, loss_batch, acc_batch))

    # Run validation after every epoch

    feed_dict_valid = {x: x_valid[:1000].reshape((-1, timesteps, num_input)), y: y_valid[:1000]}
    loss_valid, acc_valid = sess.run([loss, accuracy], feed_dict=feed_dict_valid)
    print('---------------------------------------------------------')
    print("Epoch: {0}, validation loss: {1:.2f}, validation accuracy: {2:.01%}".
          format(epoch + 1, loss_valid, acc_valid))
    print('---------------------------------------------------------')

What changes should I make in the code to get the plots?

Upvotes: 0

Views: 2011

Answers (1)

IanQ
IanQ

Reputation: 2109

One such way would be to store the values in a list, then use something like matplotlib to plot the values

Example code:

import matplotlib.pyplot as plt
plt.plot([1, 2, 3, 4])
plt.ylabel('some numbers')
plt.show()

will plot a straight line. In your case, you'd call plt.plot(list_of_prediction_accuracy) or whatever list you want to visualize

Upvotes: 1

Related Questions