val_stats_handler = StatsHandler(
name='evaluator',
output_transform=lambda x:
None # no need to print loss value, so disable per iteration output
)
val_stats_handler.attach(evaluator)
# for the arrary data format, assume the 3rd item of batch data is the meta_data
prediction_saver = ClassificationSaver(
output_dir='tempdir',
name='evaluator',
batch_transform=lambda batch:
{'filename_or_obj': batch['img.filename_or_obj']},
output_transform=lambda output: output[0].argmax(1))
prediction_saver.attach(evaluator)
# the model was trained by "densenet_training_dict" exmple
CheckpointLoader(load_path='./runs/net_checkpoint_40.pth',
load_dict={
'net': net
}).attach(evaluator)
# create a validation data loader
val_ds = monai.data.Dataset(data=val_files, transform=val_transforms)
val_loader = DataLoader(val_ds,
batch_size=2,
num_workers=4,
pin_memory=torch.cuda.is_available())
state = evaluator.run(val_loader)
# StatsHandler prints loss at every iteration and print metrics at every epoch,
# we don't need to print loss for evaluator, so just print metrics, user can also customize print functions
val_stats_handler = StatsHandler(
name='evaluator',
output_transform=lambda x:
None # no need to print loss value, so disable per iteration output
)
val_stats_handler.attach(evaluator)
# for the arrary data format, assume the 3rd item of batch data is the meta_data
file_saver = SegmentationSaver(
output_path='tempdir',
output_ext='.nii.gz',
output_postfix='seg',
name='evaluator',
batch_transform=lambda x: x[2],
output_transform=lambda output: predict_segmentation(output[0]))
file_saver.attach(evaluator)
# the model was trained by "unet_training_array" exmple
ckpt_saver = CheckpointLoader(load_path='./runs/net_checkpoint_50.pth',
load_dict={'net': net})
ckpt_saver.attach(evaluator)
# sliding window inferene need to input 1 image in every iteration
loader = DataLoader(ds,
batch_size=1,
num_workers=1,
pin_memory=torch.cuda.is_available())
state = evaluator.run(loader)
)
net.to(device)
def _sliding_window_processor(_engine, batch):
net.eval()
img, seg, meta_data = batch
with torch.no_grad():
seg_probs = sliding_window_inference(img, roi_size, sw_batch_size,
lambda x: net(x)[0], device)
return predict_segmentation(seg_probs)
infer_engine = Engine(_sliding_window_processor)
# checkpoint_handler = ModelCheckpoint('./', 'net', n_saved=10, save_interval=3, require_empty=False)
# infer_engine.add_event_handler(event_name=Events.EPOCH_COMPLETED, handler=checkpoint_handler, to_save={'net': net})
SegmentationSaver(output_path='tempdir',
output_ext='.nii.gz',
output_postfix='seg').attach(infer_engine)
CheckpointLoader(load_path='./net_checkpoint_9.pth', load_dict={
'net': net
}).attach(infer_engine)
loader = DataLoader(ds,
batch_size=1,
num_workers=1,
pin_memory=torch.cuda.is_available())
state = infer_engine.run(loader)