def test_lambda_lr(self, lr_mock):
state = {torchbearer.OPTIMIZER: 'optimizer'}
scheduler = StepLR(10, gamma=0.4, last_epoch=-4, step_on_batch='batch')
scheduler.on_start(state)
lr_mock.assert_called_once_with('optimizer', 10, gamma=0.4, last_epoch=-4)
self.assertTrue(scheduler._step_on_batch == 'batch')
def test_lambda_lr(self, lr_mock):
state = {torchbearer.OPTIMIZER: 'optimizer', torchbearer.EPOCH: 0}
scheduler = StepLR(step_size=10, gamma=0.4, step_on_batch=True)
scheduler.on_start(state)
lr_mock.assert_called_once_with('optimizer',
step_size=10,
gamma=0.4,
last_epoch=-1)
self.assertTrue(scheduler._step_on_batch)
testset = SVHN(".", split='test', download=True, transform=transform)
valset = SVHN(".", split='extra', download=True, transform=transform)
# create data loaders
trainloader = DataLoader(trainset, batch_size=128, shuffle=True)
testloader = DataLoader(testset, batch_size=128, shuffle=True)
valloader = DataLoader(valset, batch_size=128, shuffle=True)
# build the model
model = SimpleCNN()
# define the loss function and the optimiser
loss_function = nn.CrossEntropyLoss()
live_loss_plot = LiveLossPlot(draw_once=True)
optimiser = optim.Adam(model.parameters(), lr=0.001)
scheduler = StepLR(step_size=10, gamma=0.5)
device = "cuda:0" if torch.cuda.is_available() else "cpu"
trial = Trial(model, optimiser, loss_function, callbacks=[scheduler, live_loss_plot], metrics=['loss', 'accuracy']).to(device)
trial.with_generators(trainloader, val_generator=valloader, test_generator=testloader)
history = trial.run(verbose=1, epochs=30)#
results = trial.evaluate(data_key=torchbearer.TEST_DATA)
print(results)
# build the model
model = SimpleCNN()
# define the loss function and the optimiser
loss_function = nn.CrossEntropyLoss()
live_loss_plot = LiveLossPlot(draw_once=True)