how store train_loss and valid_loss separably from epoch_loss? - slice

Question

I am trying to store the train_loss and valid_loss separably from epoch_loss as epoch_loss is return back the two loss values(first is train loss and second is valid loss). the epoch_loss is a float64 object. I tried to convert it to a numpy array and then access to the each slice but again return me two values.
this is snippet
criterion = nn.NLLLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001) # 1e-3
# Decay LR by a factor of 0.1 every 4 epochs.
#step size: Period of learning rate decay.
#gamma = Multiplicative factor of learning rate decay. Default: 0.1, should
float
scheduler = lr_scheduler.StepLR(optimizer, step_size=2, gamma=0.1)
def train_model(model, criterion, optimizer, scheduler, num_epochs=4):
since = time.time()
best_model_wts = copy.deepcopy(model.state_dict())
best_acc = 0.0
for epoch in range(num_epochs): # loop over the dataset multiple times
print('Epoch {}/{}'.format(epoch, num_epochs - 1))
print('-' * 30)
# Each epoch has a training and validation phase
for phase in ['train', 'valid']:
if phase == 'train':
scheduler.step()
model.train() # Set model to training mode
else:
model.eval() # Set model to evaluate mode
train_loss = 0.0
total_train = 0
correct_train = 0
#iterate over data
for t_image, mask, image_paths, target_paths in dataLoaders[phase]:
# get the inputs
t_image = t_image.to(device)
mask = mask.to(device)
# zeroes the gradient buffers of all parameters
optimizer.zero_grad()
# forward
# track history if only in train
with torch.set_grad_enabled(phase == 'train'):
outputs = model(t_image)
_, predicted = torch.max(outputs.data, 1)
loss = criterion(outputs, mask) # calculate the loss
# backward + optimize only if in training phase
if phase == 'train':
loss.backward() # back propagation
optimizer.step() # update gradients
# accuracy
train_loss += loss.item()
total_train += mask.nelement() # number of pixel in the batch
correct_train += predicted.eq(mask.data).sum().item() # sum all precited pixel values
epoch_loss = train_loss / len(dataLoaders[phase].dataset)
epoch_acc = (correct_train / total_train)
print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))
#deep copy the model
if phase == 'valid' and epoch_acc > best_acc:
best_acc = epoch_acc
best_model_wts = copy.deepcopy(model.state_dict())
print()
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
print('Best val Acc: {:4f}'.format(best_acc))
torch.save(model.state_dict(), 'train_valid_exp1.pth')
# load best model weights
model.load_state_dict(best_model_wts)