def train():
"""
Performs training and evaluation of MLP model.
TODO:
Implement training and evaluation of MLP model. Evaluate your model on the whole test set each eval_freq iterations.
"""
### DO NOT CHANGE SEEDS!
# Set the random seeds for reproducibility
np.random.seed(42)
## Prepare all functions
# Get number of units in each hidden layer specified in the string such as 100,100
if FLAGS.dnn_hidden_units:
dnn_hidden_units = FLAGS.dnn_hidden_units.split(",")
dnn_hidden_units = [
int(dnn_hidden_unit_) for dnn_hidden_unit_ in dnn_hidden_units
]
else:
dnn_hidden_units = []
########################
# PUT YOUR CODE HERE #
#######################
data = cifar10_utils.get_cifar10(FLAGS.data_dir)
n_inputs = 3 * 32 * 32
n_classes = 10
model = MLP(n_inputs, dnn_hidden_units, n_classes)
loss_fn = CrossEntropyModule()
max_accuracy = 0.0
start_time = time.perf_counter()
for step in range(1, FLAGS.max_steps + 1):
x, targets = data['train'].next_batch(FLAGS.batch_size)
input = x.reshape((FLAGS.batch_size, -1))
predictions = model.forward(input)
gradient = loss_fn.backward(predictions, targets)
model.backward(gradient)
model.step(FLAGS.learning_rate)
if step == 1 or step % FLAGS.eval_freq == 0:
training_loss = loss_fn.forward(predictions, targets)
test_predictions = model.forward(data['test'].images.reshape(
data['test'].num_examples, -1))
test_loss = loss_fn.forward(test_predictions, data['test'].labels)
test_acc = accuracy(test_predictions, data['test'].labels)
if test_acc > max_accuracy:
max_accuracy = test_acc
print(
"step %d/%d: training loss: %.3f test loss: %.3f accuracy: %.1f%%"
% (step, FLAGS.max_steps, training_loss, test_loss,
test_acc * 100))
time_taken = time.perf_counter() - start_time
print("Done. Scored %.1f%% in %.1f seconds." %
(max_accuracy * 100, time_taken))
def train():
"""
Performs training and evaluation of MLP model.
TODO:
Implement training and evaluation of MLP model. Evaluate your model on the whole test set each eval_freq iterations.
"""
### DO NOT CHANGE SEEDS!
# Set the random seeds for reproducibility
np.random.seed(42)
## Prepare all functions
# Get number of units in each hidden layer specified in the string such as 100,100
if FLAGS.dnn_hidden_units:
dnn_hidden_units = FLAGS.dnn_hidden_units.split(",")
dnn_hidden_units = [
int(dnn_hidden_unit_) for dnn_hidden_unit_ in dnn_hidden_units
]
else:
dnn_hidden_units = []
# Preparation for training
print('- Init parameters')
data = cifar10_utils.get_cifar10(FLAGS.data_dir)
train_data = data['train']
test_data = data['test']
w, h, d = train_data.images[0].shape
n_classes = train_data.labels[0].shape[0]
criterion = CrossEntropyModule()
model = MLP(w * h * d, dnn_hidden_units, n_classes)
train_losses = []
test_losses = []
accuracies = []
print('- Start training')
for step in range(FLAGS.max_steps):
x_batch, x_labels = train_data.next_batch(FLAGS.batch_size)
x = x_batch.reshape((FLAGS.batch_size, -1))
predictions = model.forward(x)
gradient = criterion.backward(predictions, x_labels)
model.backward(gradient)
model.step(FLAGS.learning_rate)
if step % FLAGS.eval_freq == 0 or step == FLAGS.max_steps - 1:
print(' - Step: {}'.format(step))
loss = criterion.forward(predictions, x_labels)
out_test = model.forward(
test_data.images.reshape(test_data.num_examples, -1))
test_loss = criterion.forward(out_test, test_data.labels)
acc = accuracy(out_test, test_data.labels)
train_losses.append(loss)
test_losses.append(test_loss)
accuracies.append(acc)
# Save stuff
print(accuracies[-1])