model.w[i] = orig
# Actual gradient
logits = model.forward(X)
model.backward(X, logits, Y)
difference = gradient_approximation - model.grad[i, 0]
assert abs(difference) <= epsilon**2,\
f"Calculated gradient is incorrect. " \
f"Approximation: {gradient_approximation}, actual gradient: {model.grad[i,0]}\n" \
f"If this test fails there could be errors in your cross entropy loss function, " \
f"forward function or backward function"
if __name__ == "__main__":
category1, category2 = 2, 3
X_train, Y_train, *_ = utils.load_binary_dataset(category1, category2)
X_train = pre_process_images(X_train)
assert X_train.max() <= 1.0, f"The images (X_train) should be normalized to the range [-1, 1]"
assert X_train.min() < 0 and X_train.min() >= -1, f"The images (X_train) should be normalized to the range [-1, 1]"
assert X_train.shape[1] == 785,\
f"Expected X_train to have 785 elements per image. Shape was: {X_train.shape}"
# Simple test for forward pass. Note that this does not cover all errors!
model = BinaryModel()
logits = model.forward(X_train)
np.testing.assert_almost_equal(
logits.mean(), .5,
err_msg="Since the weights are all 0's, the sigmoid activation should be 0.5")
# Gradient approximation check for 100 images
X_train = X_train[:100]
accuracy_val = calculate_accuracy(
X_val, Y_val, self.model)
return loss, accuracy_train, accuracy_val
if __name__ == "__main__":
# hyperparameters DO NOT CHANGE IF NOT SPECIFIED IN ASSIGNMENT TEXT
num_epochs = 50
learning_rate = 0.05
batch_size = 128
shuffle_dataset = False
early_stopping = True
# Load dataset
category1, category2 = 2, 3
X_train, Y_train, X_val, Y_val = utils.load_binary_dataset(
category1, category2)
X_train = pre_process_images(X_train)
X_val = pre_process_images(X_val)
# ANY PARTS OF THE CODE BELOW THIS CAN BE CHANGED.
# Intialize model
model = BinaryModel()
# Train model
trainer = LogisticTrainer(
model, learning_rate, batch_size, shuffle_dataset,
early_stopping, X_train, Y_train, X_val, Y_val,
)
train_history, val_history = trainer.train(num_epochs)
_val_loss = 0
val_loss[global_step] = _val_loss
train_accuracy[global_step] = calculate_accuracy(
X_train, Y_train, model)
val_accuracy[global_step] = calculate_accuracy(
X_val, Y_val, model)
global_step += 1
return model, train_loss, val_loss, train_accuracy, val_accuracy
# Load dataset
category1, category2 = 2, 3
validation_percentage = 0.1
X_train, Y_train, X_val, Y_val, X_test, Y_test = utils.load_binary_dataset(
category1, category2, validation_percentage)
# hyperparameters
num_epochs = 50
learning_rate = 0.2
batch_size = 128
l2_reg_lambda = 0
model, train_loss, val_loss, train_accuracy, val_accuracy = train(
num_epochs=num_epochs,
learning_rate=learning_rate,
batch_size=batch_size,
l2_reg_lambda=l2_reg_lambda)
print("Final Train Cross Entropy Loss:",
cross_entropy_loss(Y_train, model.forward(pre_process_images(X_train))))
print("Final Test Entropy Loss:",
