def test_epoch(
model: BaseModel,
dataset,
device,
tracker: BaseTracker,
checkpoint: ModelCheckpoint,
voting_runs=1,
tracker_options={},
):
loaders = dataset.test_dataloaders
for loader in loaders:
stage_name = loader.dataset.name
tracker.reset(stage_name)
for i in range(voting_runs):
with Ctq(loader) as tq_test_loader:
for data in tq_test_loader:
with torch.no_grad():
model.set_input(data, device)
model.forward()
tracker.track(model, **tracker_options)
tq_test_loader.set_postfix(**tracker.get_metrics(),
color=COLORS.TEST_COLOR)
tracker.finalise(**tracker_options)
tracker.print_summary()
def test_epoch(
epoch: int,
model: BaseModel,
dataset,
device,
tracker: BaseTracker,
checkpoint: ModelCheckpoint,
visualizer: Visualizer,
debugging,
):
early_break = getattr(debugging, "early_break", False)
model.eval()
loaders = dataset.test_dataloaders
for loader in loaders:
stage_name = loader.dataset.name
tracker.reset(stage_name)
visualizer.reset(epoch, stage_name)
with Ctq(loader) as tq_test_loader:
for data in tq_test_loader:
with torch.no_grad():
model.set_input(data, device)
model.forward()
tracker.track(model)
tq_test_loader.set_postfix(**tracker.get_metrics(),
color=COLORS.TEST_COLOR)
if visualizer.is_active:
visualizer.save_visuals(model.get_current_visuals())
if early_break:
break
tracker.finalise()
metrics = tracker.publish(epoch)
tracker.print_summary()
checkpoint.save_best_models_under_current_metrics(
model, metrics, tracker.metric_func)
def eval_epoch(
epoch: int,
model: BaseModel,
dataset,
device,
tracker: BaseTracker,
checkpoint: ModelCheckpoint,
visualizer: Visualizer,
debugging,
):
early_break = getattr(debugging, "early_break", False)
model.eval()
tracker.reset("val")
visualizer.reset(epoch, "val")
loader = dataset.val_dataloader
with Ctq(loader) as tq_val_loader:
for data in tq_val_loader:
with torch.no_grad():
model.set_input(data, device)
model.forward()
tracker.track(model)
tq_val_loader.set_postfix(**tracker.get_metrics(),
color=COLORS.VAL_COLOR)
if visualizer.is_active:
visualizer.save_visuals(model.get_current_visuals())
if early_break:
break
metrics = tracker.publish(epoch)
tracker.print_summary()
checkpoint.save_best_models_under_current_metrics(model, metrics,
tracker.metric_func)
def eval_epoch(
model: BaseModel,
dataset,
device,
tracker: BaseTracker,
checkpoint: ModelCheckpoint,
voting_runs=1,
tracker_options={},
):
tracker.reset("val")
loader = dataset.val_dataloader
for i in range(voting_runs):
with Ctq(loader) as tq_val_loader:
for data in tq_val_loader:
with torch.no_grad():
model.set_input(data, device)
model.forward()
tracker.track(model, **tracker_options)
tq_val_loader.set_postfix(**tracker.get_metrics(),
color=COLORS.VAL_COLOR)
tracker.finalise(**tracker_options)
tracker.print_summary()