def test_big_linear_batchnorm_relu_xeloss_momentum():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20), BatchNorm1d(20), ReLU(),
Linear(20, 30), BatchNorm1d(30), ReLU())
mytorch_optimizer = SGD(mytorch_mlp.parameters(), momentum=0.9)
mytorch_criterion = CrossEntropyLoss()
test_step(mytorch_mlp,
mytorch_optimizer,
5,
5,
mytorch_criterion=mytorch_criterion)
return True
def mnist(train_x, train_y, val_x, val_y):
"""Problem 3.1: Initialize objects and start training
You won't need to call this function yourself.
(Data is provided by autograder)
Args:
train_x (np.array): training data (55000, 784)
train_y (np.array): training labels (55000,)
val_x (np.array): validation data (5000, 784)
val_y (np.array): validation labels (5000,)
Returns:
val_accuracies (list(float)): List of accuracies per validation round
(num_epochs,)
"""
# TODO: Initialize an MLP, optimizer, and criterion
# TODO: Call training routine (make sure to write it below)
l = [Linear(784, 20), BatchNorm1d(20), ReLU(), Linear(20, 10)]
model = Sequential(*l)
criterion = CrossEntropyLoss()
optimizer = SGD(model.parameters(), lr=0.1, momentum=0.9)
val_accuracies = train(model,
optimizer,
criterion,
train_x,
train_y,
val_x,
val_y,
num_epochs=3)
return val_accuracies
def test_linear_batchnorm_relu_train_eval():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20), BatchNorm1d(20), ReLU())
mytorch_optimizer = SGD(mytorch_mlp.parameters())
test_step(mytorch_mlp, mytorch_optimizer, 5, 5)
return True
def test_linear_batchnorm_relu_backward_train():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20), BatchNorm1d(20), ReLU())
test_forward_backward(mytorch_mlp)
return True
