kuhyx/WUT_Computer_Science
1
0
Fork 0
mirror of https://github.com/kuhyx/WUT_Computer_Science.git synced 2026-07-06 20:43:11 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: add plotting

Browse Source
This commit is contained in:
Jakub Kliszko 2023-05-13 14:21:56 +02:00
parent fa10997a1d
commit fe23eadb1a
1 changed files with 40 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
lab5/code/main.py
View File

@ -2,6 +2,7 @@ import torch
import torch.nn as nn import torch.nn as nn
import torch.optim as optim import torch.optim as optim
from torchvision import datasets, transforms from torchvision import datasets, transforms
import matplotlib.pyplot as plt
# Set random seed for reproducibility # Set random seed for reproducibility
torch.manual_seed(42) torch.manual_seed(42)
@ -43,6 +44,11 @@ criterion = nn.CrossEntropyLoss()
# Optimizer # Optimizer
optimizer = optim.Adam(model.parameters(), lr=learning_rate) optimizer = optim.Adam(model.parameters(), lr=learning_rate)
# Lists to store loss and accuracy values
loss_values = []
train_acc_values = []
val_acc_values = []
# Training loop # Training loop
for epoch in range(num_epochs): for epoch in range(num_epochs):
for batch_idx, (data, targets) in enumerate(train_loader): for batch_idx, (data, targets) in enumerate(train_loader):
@ -58,9 +64,8 @@ for epoch in range(num_epochs):
loss.backward() loss.backward()
optimizer.step() optimizer.step()
# Print loss value for every learning step # Append loss value for every learning step
if (batch_idx+1) % 100 == 0: loss_values.append(loss.item())
print(f'Epoch [{epoch+1}/{num_epochs}], Step [{batch_idx+1}/{len(train_loader)}], Loss: {loss.item():.4f}')
# Calculate accuracy on train set after each epoch # Calculate accuracy on train set after each epoch
correct = 0 correct = 0
@ -73,7 +78,7 @@ for epoch in range(num_epochs):
correct += (predicted == targets).sum().item() correct += (predicted == targets).sum().item()
train_accuracy = 100 * correct / total train_accuracy = 100 * correct / total
print(f'Accuracy on Train Set after Epoch {epoch+1}: {train_accuracy:.2f}%') train_acc_values.append(train_accuracy)
# Calculate accuracy on validation set after each epoch # Calculate accuracy on validation set after each epoch
correct = 0 correct = 0
@ -86,7 +91,28 @@ for epoch in range(num_epochs):
correct += (predicted == targets).sum().item() correct += (predicted == targets).sum().item()
validation_accuracy = 100 * correct / total validation_accuracy = 100 * correct / total
print(f'Accuracy on Validation Set after Epoch {epoch+1}: {validation_accuracy:.2f}%') val_acc_values.append(validation_accuracy)
print('---')
# Conclusions and observations can be included in the report # Print loss value for every learning step
print(f'Epoch [{epoch+1}/{num_epochs}], Loss: {loss_values[-1]:.4f}, Train Accuracy: {train_accuracy:.2f}%, Validation Accuracy: {validation_accuracy:.2f}%')
# Plot the loss value for every learning step
plt.plot(loss_values)
plt.xlabel('Learning Step')
plt.ylabel('Loss')
plt.title('Loss Value')
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.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.show()