from delira.data_loading import DataManager, SequentialSampler
if __name__ == '__main__':
# PARAMETERS TO CHANGE
# TODO: Change paths and create suitable Dataset
checkpoint_path = ""
data_path = ""
save_path = ""
dset = None
checkpoint_path = os.path.expanduser(checkpoint_path)
data_path = os.path.expanduser(data_path)
save_path = os.path.expanduser(save_path)
transforms = Compose([RangeTransform((-1, 1))])
model = UNetTorch(3, 1, norm_layer="Instance", per_class=False)
model.load_state_dict(torch.load(checkpoint_path)["model"])
model.eval()
if torch.cuda.is_available():
device = torch.device("cuda")
else:
device = torch.device("cpu")
model.to(device)
dmgr = DataManager(dset, 1, 4, transforms, sampler_cls=SequentialSampler)
predictor = Predictor(model,
from functools import partial
from delira.data_loading import DataManager, SequentialSampler
from delira_unet import UNetTorch
from delira import set_debug_mode
if __name__ == "__main__":
checkpoint_path = ""
data_path = ""
save_path = ""
set_debug_mode(True)
transforms = Compose([
CopyTransform("data", "data_orig"),
# HistogramEqualization(),
RangeTransform((-1, 1)),
# AddGridTransform(),
])
img_size = (1024, 256)
thresh = 0.5
print("Load Model")
torch.jit.loat(checkpoint_path)
model.eval()
if torch.cuda.is_available():
device = torch.device("cuda")
else:
device = torch.device("cpu")
def train(model_cls,
model_kwargs: dict,
outpath: str,
data_path,
exp_name=None,
batchsize=64,
num_epochs=1500,
checkpoint_freq=10,
additional_losses: dict = None,
dset_type="mnist",
key_mapping=None,
create_optim_fn=None):
if exp_name is None:
exp_name = model_cls.__name__
if additional_losses is None:
additional_losses = {}
if create_optim_fn is None:
create_optim_fn = create_optims
outpath = os.path.expanduser(outpath)
losses = {"adversarial": AdversarialLoss()}
losses.update(additional_losses)
params = Parameters(
fixed_params={
"model": {
**model_kwargs
},
"training": {
"num_epochs": num_epochs,
"batchsize": batchsize,
"losses": losses,
"val_metrics": {},
"optimizer_cls": torch.optim.Adam,
"optimizer_params": {
"lr": 0.001,
"betas": (0.5, 0.9995)
},
"scheduler_cls": None,
"scheduler_params": {}
}
})
data = setup_data(data_path, params.nested_get("batchsize"), 4,
RangeTransform(), RangeTransform(), dset_type)
exp = PyTorchExperiment(params,
model_cls,
params.nested_get("num_epochs"),
name=exp_name,
save_path=outpath,
key_mapping=key_mapping,
optim_builder=create_optim_fn,
checkpoint_freq=checkpoint_freq,
gpu_ids=[0])
model = exp.run(data["train"], data["val"])
weight_dir = os.path.join(exp.save_path, "checkpoints", "run_00")
return model, weight_dir