def test_linear_xeloss_backward():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20))
mytorch_optimizer = SGD(mytorch_mlp.parameters())
mytorch_criterion = CrossEntropyLoss()
test_forward_backward(mytorch_mlp, 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
mnist_model = Sequential(Linear(784, 20), ReLU(), Linear(20, 10))
#mnist_model = Sequential(Linear(784,20),BatchNorm1d(20),ReLU(),Linear(20,10))
creterion = CrossEntropyLoss()
mdl_optimizer = SGD(mnist_model.parameters(), momentum=0.9, lr=0.1)
# TODO: Call training routine (make sure to write it below)
val_accuracies = train(mnist_model, mdl_optimizer, creterion, train_x,
train_y, val_x, val_y)
return val_accuracies
def test_linear_adam():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20))
mytorch_optimizer = Adam(mytorch_mlp.parameters())
mytorch_criterion = CrossEntropyLoss()
return test_step(mytorch_mlp,
mytorch_optimizer,
5,
5,
mytorch_criterion=mytorch_criterion)
def test_big_model_step():
np.random.seed(11785)
# run a big model
model = Sequential(Linear(10, 15), ReLU(), Dropout(p=0.2),
Linear(15, 20), ReLU(), Dropout(p=0.1))
x, y = generate_dataset_for_mytorch_model(model, 4)
x, y = Tensor(x), Tensor(y)
criterion = CrossEntropyLoss()
optimizer = Adam(model.parameters(), lr=1e-3, betas=(0.9, 0.999), eps=1e-08)
# check output correct
out = model(x)
test_out = load_numpy_array('autograder/hw1_bonus_autograder/outputs/big_output.npy')
if not assertions_all(out.data, test_out, "test_big_model_step_out", 1e-5, 1e-6):
return False
# run backward
loss = criterion(out, y)
loss.backward()
# check params are correct (sorry this is ugly)
assert model[0].weight.grad is not None, "Linear layer must have gradient."
assert model[0].weight.grad.grad is None, "Final gradient tensor must not have its own gradient"
assert model[0].weight.grad.grad_fn is None, "Final gradient tensor must not have its own grad function"
assert model[0].weight.requires_grad, "Weight tensor must have requires_grad==True"
assert model[0].weight.is_parameter, "Weight tensor must be marked as a parameter tensor"
assert model[3].weight.grad is not None, "Linear layer must have gradient."
assert model[3].weight.grad.grad is None, "Final gradient tensor must not have its own gradient"
assert model[3].weight.grad.grad_fn is None, "Final gradient tensor must not have its own grad function"
assert model[3].weight.requires_grad, "Weight tensor must have requires_grad==True"
assert model[3].weight.is_parameter, "Weight tensor must be marked as a parameter tensor"
# check gradient for linear layer at idx 0 is correct
test_grad = load_numpy_array('autograder/hw1_bonus_autograder/outputs/big_grad.npy')
if not assertions_all(model[0].weight.grad.data, test_grad, "test_big_model_grad_0", 1e-5, 1e-6):
return False
# check gradient for linear layer at idx 3 is correct
test_grad = load_numpy_array('autograder/hw1_bonus_autograder/outputs/big_grad_3.npy')
if not assertions_all(model[3].weight.grad.data, test_grad, "test_big_model_grad_3", 1e-5, 1e-6):
return False
# weight update with adam
optimizer.step()
# check updated weight values
assert model[0].weight.requires_grad, "Weight tensor must have requires_grad==True"
assert model[0].weight.is_parameter, "Weight tensor must be marked as a parameter tensor"
test_weights_3 = load_numpy_array('autograder/hw1_bonus_autograder/outputs/big_weight_update_3.npy')
test_weights_0 = load_numpy_array('autograder/hw1_bonus_autograder/outputs/big_weight_update_0.npy')
return assertions_all(model[0].weight.data, test_weights_0, "test_big_weight_update_0", 1e-5, 1e-6) and \
assertions_all(model[3].weight.data, test_weights_3, "test_big_weight_update_3", 1e-5, 1e-6)
def test_big_linear_relu_xeloss_momentum():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20), ReLU(), Linear(20, 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 test_big_linear_bn_relu_xeloss_train_eval():
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())
mytorch_criterion = CrossEntropyLoss()
test_step(mytorch_mlp,
mytorch_optimizer,
5,
5,
mytorch_criterion=mytorch_criterion)
return True
def test_big_model_adam():
np.random.seed(11785)
# mytorch_mlp = Sequential(Linear(10, 20), BatchNorm1d(20), ReLU(),
# Linear(20, 30), BatchNorm1d(30), ReLU())
mytorch_mlp = Sequential(Linear(10, 20), ReLU(), Linear(20, 30), ReLU())
mytorch_optimizer = Adam(mytorch_mlp.parameters())
mytorch_criterion = CrossEntropyLoss()
return test_step(mytorch_mlp,
mytorch_optimizer,
5,
5,
mytorch_criterion=mytorch_criterion)
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_big_linear_relu_step():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20), ReLU(), Linear(20, 30), ReLU())
mytorch_optimizer = SGD(mytorch_mlp.parameters())
test_step(mytorch_mlp, mytorch_optimizer, 5, 5)
return True
def test_linear_momentum():
np.random.seed(11785)
mytorch_mlp = Sequential(Linear(10, 20), ReLU())
mytorch_optimizer = SGD(mytorch_mlp.parameters(), momentum=0.9)
test_step(mytorch_mlp, mytorch_optimizer, 5, 0)
return True
