kuhyx/WUT_Computer_Science
1
0
Fork 0
mirror of https://github.com/kuhyx/WUT_Computer_Science.git synced 2026-11-11 21:33:57 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'lab5' into kuchy

Browse Source 
# Conflicts:
#	lab5/code/main.py
This commit is contained in:
Jakub Kliszko 2023-05-16 15:30:43 +02:00
commit d8088a38b4
1 changed files with 36 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
lab5/code/main.py
View File

@ -3,6 +3,7 @@ import torch
from torch import nn from torch import nn
from torch import optim from torch import optim
from torchvision import datasets, transforms from torchvision import datasets, transforms
import matplotlib.pyplot as plt
def set_hyperparameters(): def set_hyperparameters():
@ -39,6 +40,12 @@ def create_data_loaders(train_dataset, test_dataset, hyperparameters):
return train_loader, test_loader return train_loader, test_loader
# Lists to store loss and accuracy values
loss_values = []
train_acc_values = []
val_acc_values = []
def define_model(hyperparameters): def define_model(hyperparameters):
""" Define the multilayer perceptron training_parameters['model'] """ """ Define the multilayer perceptron training_parameters['model'] """
model = nn.Sequential( model = nn.Sequential(
@ -92,11 +99,12 @@ def single_train_iteration(
print( print(
f''' f'''
Epoch [{epoch+1}/{training_parameters['hyperparameters']["num_epochs"]}], Epoch [{epoch+1}/{training_parameters['hyperparameters']["num_epochs"]}],
Step [{batch_idx+1}/ \ Step [{batch_idx+1}/ {len(training_parameters['loaders']['train_loader'])}],
{len(training_parameters['loaders']['train_loader'])}],
Loss: {loss.item():.4f} Loss: {loss.item():.4f}
''' '''
) )
# Append loss value for every learning step
loss_values.append(loss.item())
return data, training_parameters['optimizer'] return data, training_parameters['optimizer']
@ -157,6 +165,7 @@ def calculate_accuracy_epoch(training_parameters, epoch):
train_accuracy = 100 * correct / total train_accuracy = 100 * correct / total
print( print(
f"Accuracy on Train Set after Epoch {epoch+1}: {train_accuracy:.2f}%") f"Accuracy on Train Set after Epoch {epoch+1}: {train_accuracy:.2f}%")
train_acc_values.append(train_accuracy)
def calculate_validation_set_accuracy(training_parameters, epoch): def calculate_validation_set_accuracy(training_parameters, epoch):
@ -175,6 +184,7 @@ def calculate_validation_set_accuracy(training_parameters, epoch):
f"Accuracy on Validation Set after Epoch {epoch+1}: {validation_accuracy:.2f}%" f"Accuracy on Validation Set after Epoch {epoch+1}: {validation_accuracy:.2f}%"
) )
print("---") print("---")
val_acc_values.append(validation_accuracy)
if __name__ == "__main__": if __name__ == "__main__":
@ -191,3 +201,27 @@ if __name__ == "__main__":
TRAINING_PARAMETERS = set_training_parameters( TRAINING_PARAMETERS = set_training_parameters(
HYPERPARAMETERS, LOADERS, MODEL, CRITERION, OPTIMIZER) HYPERPARAMETERS, LOADERS, MODEL, CRITERION, OPTIMIZER)
training_loop(TRAINING_PARAMETERS) training_loop(TRAINING_PARAMETERS)
# Plot the loss value for every learning step
plt.plot(loss_values)
plt.xlabel('Learning Step')
plt.ylabel('Loss')
plt.title('Loss Value')
plt.savefig('loss_value.png')
plt.show()
# Plot the accuracy on train set after each epoch
plt.plot(train_acc_values)
plt.xlabel('Epoch')
plt.ylabel('Train Accuracy')
plt.title('Accuracy on Train Set')
plt.savefig('train_accuracy.png')
plt.show()
# Plot the accuracy on validation set after each epoch
plt.plot(val_acc_values)
plt.xlabel('Epoch')
plt.ylabel('Validation Accuracy')
plt.title('Accuracy on Validation Set')
plt.savefig('validation_accuracy.png')
plt.show()