def calculate_accuracy(X: np.ndarray, targets: np.ndarray, model: SoftmaxModel) -> float:
"""
Args:
X: images of shape [batch size, 785]
targets: labels/targets of each image of shape: [batch size, 10]
model: model of class SoftmaxModel
Returns:
Accuracy (float)
"""
output = model.forward(X)
predictions = one_hot_encode(np.array([np.argmax(output, axis=1)]).T, 10)
correct_pred = np.count_nonzero(targets*predictions)
total_pred = output.shape[0]
accuracy = correct_pred/total_pred
return accuracy
return model, train_loss, val_loss, train_accuracy, val_accuracy
# Load dataset
validation_percentage = 0.1
X_train, Y_train, X_val, Y_val, X_test, Y_test = utils.load_full_mnist(
validation_percentage)
# Preprocessing
X_train = pre_process_images(X_train)
X_test = pre_process_images(X_test)
X_val = pre_process_images(X_val)
#OneHotencoding of targets
Y_train = one_hot_encode(Y_train, 10)
Y_val = one_hot_encode(Y_val, 10)
Y_test = one_hot_encode(Y_test, 10)
# Hyperparameters
num_epochs = 50
learning_rate = .3
batch_size = 128
l2_reg_lambda = 0.001
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)
global_step += 1
return model, train_loss, val_loss, train_accuracy, val_accuracy
# Load dataset
validation_percentage = 0.1
X_train, Y_train, X_val, Y_val, X_test, Y_test = utils.load_full_mnist(
validation_percentage)
X_train = pre_process_images(X_train)
X_val = pre_process_images(X_val)
X_test = pre_process_images(X_test)
# One-hot encode our targets
Y_train = one_hot_encode(Y_train, NUM_OUTPUTS)
Y_val = one_hot_encode(Y_val, NUM_OUTPUTS)
Y_test = one_hot_encode(Y_test, NUM_OUTPUTS)
# Hyperparameters
num_epochs = 50
learning_rate = .3
batch_size = 128
# Training
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=0)