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)
"""
# TODO: Implement this function (copy from last assignment)
accuracy = 0
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
import numpy as np
import utils
from task2a import one_hot_encode, pre_process_images, SoftmaxModel, gradient_approximation_test
if __name__ == "__main__":
# Simple test on one-hot encoding
Y = np.zeros((1, 1), dtype=int)
Y[0, 0] = 3
Y = one_hot_encode(Y, 10)
assert Y[0, 3] == 1 and Y.sum() == 1, \
f"Expected the vector to be [0,0,0,1,0,0,0,0,0,0], but got {Y}"
X_train, Y_train, *_ = utils.load_full_mnist(0.1)
mean = np.mean(X_train)
std = np.std(X_train)
X_train = pre_process_images(X_train, mean, std)
Y_train = one_hot_encode(Y_train, 10)
assert X_train.shape[1] == 785,\
f"Expected X_train to have 785 elements per image. Shape was: {X_train.shape}"
# Modify your network here
neurons_per_layer = [64, 64, 10]
use_improved_sigmoid = True
use_improved_weight_init = True
model = SoftmaxModel(neurons_per_layer, use_improved_sigmoid,
use_improved_weight_init)
# Gradient approximation check for 100 images
X_train = X_train[:100]
Y_train = Y_train[:100]
for layer_idx, w in enumerate(model.ws):
num_epochs = 50
learning_rate = 0.02
batch_size = 32
neurons_per_layer = [64, 10]
momentum_gamma = .9 # Task 3 hyperparameter
shuffle_data = True
use_improved_sigmoid = False
use_improved_weight_init = False
use_momentum = False
# Load dataset
X_train, Y_train, X_val, Y_val = utils.load_full_mnist()
X_train = pre_process_images(X_train)
X_val = pre_process_images(X_val)
Y_train = one_hot_encode(Y_train, 10)
Y_val = one_hot_encode(Y_val, 10)
######1nd model - network from task 3######
use_improved_sigmoid = True
use_improved_weight_init = True
use_momentum = True
model = SoftmaxModel(neurons_per_layer, use_improved_sigmoid,
use_improved_weight_init)
trainer = SoftmaxTrainer(
momentum_gamma,
use_momentum,
model,
learning_rate,
batch_size,
shuffle_data,
