def _evaluate_epoch(axes, tr_loader, val_loader, model, criterion, epoch, stats):
"""
Evaluates the `model` on the train and validation set.
"""
with torch.no_grad():
y_true, y_pred = [], []
correct, total = 0, 0
running_loss = []
for X, y in tr_loader:
output = model(X)
predicted = predictions(output.data)
y_true.append(y)
y_pred.append(predicted)
total += y.size(0)
correct += (predicted == y).sum().item()
running_loss.append(criterion(output, y).item())
train_loss = np.mean(running_loss)
train_acc = correct / total
with torch.no_grad():
y_true, y_pred = [], []
correct, total = 0, 0
running_loss = []
for X, y in val_loader:
output = model(X)
predicted = predictions(output.data)
y_true.append(y)
y_pred.append(predicted)
total += y.size(0)
correct += (predicted == y).sum().item()
running_loss.append(criterion(output, y).item())
val_loss = np.mean(running_loss)
val_acc = correct / total
stats.append([val_acc, val_loss, train_acc, train_loss])
utils.log_cnn_training(epoch, stats)
utils.update_cnn_training_plot(axes, epoch, stats)
def _evaluate_epoch(axes, tr_loader, val_loader, model, criterion, epoch,
stats):
"""
Evaluates the `model` on the train and validation set.
"""
acc_per_class = [0.0, 0.0, 0.0, 0.0, 0.0]
num = [0, 0, 0, 0, 0]
y_true, y_pred = [], []
correct, total = 0, 0
running_loss = []
for X, y in tr_loader:
with torch.no_grad():
output = model(X)
predicted = predictions(output.data)
y_true.append(y)
y_pred.append(predicted)
total += y.size(0)
correct += (predicted == y).sum().item()
running_loss.append(criterion(output, y).item())
train_loss = np.mean(running_loss)
train_acc = correct / total
y_true, y_pred = [], []
correct, total = 0, 0
running_loss = []
for X, y in val_loader:
with torch.no_grad():
output = model(X)
predicted = predictions(output.data)
y_true.append(y)
y_pred.append(predicted)
total += y.size(0)
correct += (predicted == y).sum().item()
for ii in range(5):
for jj in range(y.size(0)):
if predicted[jj] == y[jj] and y[jj] == ii:
acc_per_class[ii] += 1
num[ii] += (y == ii).sum().item()
running_loss.append(criterion(output, y).item())
val_loss = np.mean(running_loss)
for ii in range(5):
acc_per_class[ii] = acc_per_class[ii] / num[ii]
print(acc_per_class)
val_acc = correct / total
stats.append([val_acc, val_loss, train_acc, train_loss])
utils.log_cnn_training(epoch, stats)
utils.update_cnn_training_plot(axes, epoch, stats)