def find_minimum(model: models.ModelWrapper,
optim_config: config.OptimConfig) -> dict:
optimiser = optim_config.algorithm_type(
model.parameters(),
**optim_config.algorithm_args) # type: optim.Optimizer
# Scheduler
if optim_config.scheduler_type is not None:
scheduler = optim_config.scheduler_type(optimiser,
**optim_config.scheduler_args)
else:
scheduler = None
# Initialise
model.initialise_randomly()
if optim_config.eval_config is not None:
model.adapt_to_config(optim_config.eval_config)
# Optimise
for _ in helper.pbar(range(optim_config.nsteps), "Find mimimum"):
model.apply(gradient=True)
if scheduler is not None:
scheduler.step()
optimiser.step()
# todo tensorboard logging or similar
result = {
"coords": model.get_coords().to("cpu"),
}
# Analyse
analysis = model.analyse()
logger.debug(f"Found minimum: {analysis}.")
result.update(analysis)
return result
def _test_model(self, nn_model):
loss_model = CompareModel(nn_model, NLLLoss())
data_model = DataModel(loss_model, {
"train": self.train_mnist,
"test": self.test_mnist
})
model = ModelWrapper(data_model)
model.adapt_to_config(EvalConfig(1024))
if cuda.is_available():
pass # model.to("cuda")
analysis = model.analyse()
for offset, data, size, is_buffer in model.iterate_params_buffers():
print(size)
for key, value in analysis.items():
if "error" in key:
self.assertLess(self.random_error * 0.9, value, f"Random {key} too low")
self.assertGreater(self.random_error * 1.1, value, f"Random {key} too high")
print(nn_model.__class__.__name__, analysis)