val_acc)
plotter.plot('attention_auc', 'val', 'Attention AUC', epoch, val_auc)
plotter.plot('attention_f1', 'val', 'Attention F1', epoch, val_f1)
plotter.save(['Tutorial Plots Attention'])
time_elapsed = time.time() - since
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
return model
# In[24]:
if __name__ == "__main__":
# model_ft = Resnet_Classifier()
model_ft = Attention(path="model34")
model_ft = model_ft.to(device)
# for param in model_ft.parameters():
# print(param.requires_grad)
# print(param,size())
criterion = nn.CrossEntropyLoss(
weight=torch.Tensor([1.0 / 165.0, 1.0 / 122.0]).to(device))
optimizer_ft = optim.Adam(model_ft.parameters(), lr=0.0001)
scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=10, gamma=0.1)
# model_ft = train_model(model_ft, criterion, optimizer_ft, scheduler, num_epochs=200)
global plotter
plotter = utils.VisdomLinePlotter(env_name='Tutorial Plots Resnet')
# In[ ]:
def run(args):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
n_worker = 2
n_epoch = args.epochs
torch.manual_seed(args.seed)
torch.cuda.manual_seed(args.seed) # backward pass
print('Load Train and Test Set')
train_loader = DataLoader(MnistBags(target_number=args.target_number,
min_target_count=args.min_target_count,
mean_bag_length=args.mean_bag_length,
var_bag_length=args.var_bag_length,
scale=args.scale,
num_bag=args.num_bags_train,
seed=args.seed,
train=True),
batch_size=args.batchsize,
shuffle=True,
num_workers=n_worker,
pin_memory=torch.cuda.is_available())
test_loader = DataLoader(MnistBags(target_number=args.target_number,
min_target_count=args.min_target_count,
mean_bag_length=args.mean_bag_length,
var_bag_length=args.var_bag_length,
scale=args.scale,
num_bag=args.num_bags_test,
seed=args.seed,
train=False),
batch_size=args.batchsize,
shuffle=False,
num_workers=n_worker,
pin_memory=torch.cuda.is_available())
# resume checkpoint
checkpoint = load_ckpt()
if checkpoint:
print('Resume training ...')
start_epoch = checkpoint.epoch
model = checkpoint.model
else:
print('Grand new training ...')
start_epoch = 0
model = Attention()
# put model to multiple GPUs if available
if torch.cuda.device_count() > 1:
print("Let's use ", torch.cuda.device_count(), " GPUs!")
model = nn.DataParallel(model)
model = model.to(device)
optimizer = optim.Adam(model.parameters(),
lr=args.lr,
betas=(0.9, 0.999),
weight_decay=args.reg)
if checkpoint:
try:
optimizer.load_state_dict(checkpoint.optimizer)
except:
print(
'[WARNING] optimizer not restored from last checkpoint, continue without previous state'
)
# free checkpoint reference
del checkpoint
log_dir = os.path.join('logs', args.logname)
n_cv_epoch = 1 #2
with SummaryWriter(log_dir) as writer:
print('\nTraining started ...')
for epoch in range(start_epoch + 1,
n_epoch + start_epoch + 1): # 1 base
train(model, optimizer, train_loader, epoch, writer)
if epoch % n_cv_epoch == 0:
with torch.no_grad():
test(model, optimizer, test_loader, epoch, writer)
save_ckpt(model, optimizer, epoch)
print('\nTraining finished ...')
