fix: change sigmoid with softmax and add some comments

utils/forward_pass.py

 from utils.sigmoid import sigmoid
 import numpy as np
+from scipy.special import softmax
 
 def forward_pass(w1, b1, w2, b2, data):
-    # compute the forward pass of the MLP with sigmoid activations
+    # compute the forward pass of the MLP with sigmoid activations for the hidden layer and softmax for the output layer
     z1 = np.matmul(data, w1) + b1
     a1 = sigmoid(z1)
     z2 = np.matmul(a1, w2) + b2
-    a2 = sigmoid(z2)
+    a2 = softmax(z2, axis=1)
     return a1, a2
\ No newline at end of file

utils/mlp_training.py

@@ -6,16 +6,19 @@ from utils.learn_once_cross_entropy import learn_once_cross_entropy
 
 
 def train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, num_epochs, batch_size, n_classes):
-    # train the MLP for num_epochs epochs, using batches of size batch_size
+    # train the MLP for num_epochs epochs, using batches of size batch_size and return the train accuracies, losses and weights
     losses = []
+    train_accuracies = []
     for epoch in range(num_epochs):
         for i in tqdm.tqdm(range(0, data_train.shape[0], batch_size)):
             data = data_train[i:i+batch_size]
             targets = one_hot(labels_train[i:i+batch_size], n_classes)
             w1, b1, w2, b2, loss = learn_once_cross_entropy(w1, b1, w2, b2, data, targets, learning_rate)
         losses.append(loss)
-        print(f'epoch={epoch}, loss={loss}')
-    return losses, w1, b1, w2, b2
+        train_accuracy = test_mlp(w1, b1, w2, b2, data_train, labels_train)
+        train_accuracies.append(train_accuracy)
+        print(f'epoch={epoch}, loss={loss}, train_accuracy={train_accuracy}')
+    return train_accuracies, losses, w1, b1, w2, b2
 
 def test_mlp(w1, b1, w2, b2, data_test, labels_test):
     # test the MLP on data_test, and return the accuracy
@@ -37,6 +40,6 @@ def run_mlp_training(data_train, labels_train, data_test, labels_test, d_h, lear
     d_in = data_train.shape[1]
     d_out = np.max(labels_train) + 1
     w1, b1, w2, b2 = initialize_mlp(d_in, d_h, d_out)
-    losses, w1, b1, w2, b2 = train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, num_epochs, batch_size, n_classes)
+    train_accuracies, losses, w1, b1, w2, b2 = train_mlp(w1, b1, w2, b2, data_train, labels_train, learning_rate, num_epochs, batch_size, n_classes)
     test_accuracy = test_mlp(w1, b1, w2, b2, data_test, labels_test)
-    return losses, test_accuracy
+    return losses, test_accuracy, train_accuracies
\ No newline at end of file

utils/process_image.py

@@ -5,10 +5,11 @@ def plot_image_with_label(img, label):
     plt.title(label)
     plt.show()
 
-def save_plot_as_image(X, Y, y_label, x_label, save_path):
+def save_plot_as_image(X, Y, y_label, x_label, title, save_path):
     # plot and save image as png
     plt.figure(figsize=(10,5))
     plt.plot(X, Y)
+    plt.title(title)
     plt.ylabel(y_label)
     plt.xlabel(x_label)
     plt.savefig(save_path)