def create_predictor(
self, transformation: Transformation, trained_network: HybridBlock
) -> Predictor:
prediction_network = DeepStatePredictionNetwork(
num_sample_paths=self.num_sample_paths,
num_layers=self.num_layers,
num_cells=self.num_cells,
cell_type=self.cell_type,
past_length=self.past_length,
prediction_length=self.prediction_length,
issm=self.issm,
dropout_rate=self.dropout_rate,
cardinality=self.cardinality,
embedding_dimension=self.embedding_dimension,
scaling=self.scaling,
params=trained_network.collect_params(),
)
copy_parameters(trained_network, prediction_network)
return RepresentableBlockPredictor(
input_transform=transformation,
prediction_net=prediction_network,
batch_size=self.trainer.batch_size,
freq=self.freq,
prediction_length=self.prediction_length,
ctx=self.trainer.ctx,
)
def create_predictor(self, transformation: Transformation,
trained_network: HybridBlock) -> Predictor:
prediction_splitter = self._create_instance_splitter("test")
prediction_network = DeepStatePredictionNetwork(
num_layers=self.num_layers,
num_cells=self.num_cells,
cell_type=self.cell_type,
past_length=self.past_length,
prediction_length=self.prediction_length,
issm=self.issm,
dropout_rate=self.dropout_rate,
cardinality=self.cardinality,
embedding_dimension=self.embedding_dimension,
scaling=self.scaling,
num_parallel_samples=self.num_parallel_samples,
noise_std_bounds=self.noise_std_bounds,
prior_cov_bounds=self.prior_cov_bounds,
innovation_bounds=self.innovation_bounds,
params=trained_network.collect_params(),
)
copy_parameters(trained_network, prediction_network)
return RepresentableBlockPredictor(
input_transform=transformation + prediction_splitter,
prediction_net=prediction_network,
batch_size=self.batch_size,
freq=self.freq,
prediction_length=self.prediction_length,
ctx=self.trainer.ctx,
)
def create_predictor(self, transformation: Transformation,
trained_network: HybridBlock) -> Predictor:
prediction_network = GaussianProcessPredictionNetwork(
prediction_length=self.prediction_length,
context_length=self.context_length,
cardinality=self.cardinality,
num_samples=self.num_eval_samples,
params=trained_network.collect_params(),
kernel_output=self.kernel_output,
params_scaling=self.params_scaling,
ctx=self.trainer.ctx,
float_type=self.float_type,
max_iter_jitter=self.max_iter_jitter,
jitter_method=self.jitter_method,
sample_noise=self.sample_noise,
)
copy_parameters(net_source=trained_network,
net_dest=prediction_network)
return RepresentableBlockPredictor(
input_transform=transformation,
prediction_net=prediction_network,
batch_size=self.trainer.batch_size,
freq=self.freq,
prediction_length=self.prediction_length,
ctx=self.trainer.ctx,
float_type=self.float_type,
)
def create_predictor(self, transformation: Transformation,
trained_network: HybridBlock) -> Predictor:
prediction_splitter = self._create_instance_splitter("test")
prediction_network = NBEATSPredictionNetwork(
prediction_length=self.prediction_length,
context_length=self.context_length,
num_stacks=self.num_stacks,
widths=self.widths,
num_blocks=self.num_blocks,
num_block_layers=self.num_block_layers,
expansion_coefficient_lengths=self.expansion_coefficient_lengths,
sharing=self.sharing,
stack_types=self.stack_types,
params=trained_network.collect_params(),
scale=self.scale,
)
return RepresentableBlockPredictor(
input_transform=transformation + prediction_splitter,
prediction_net=prediction_network,
batch_size=self.batch_size,
freq=self.freq,
prediction_length=self.prediction_length,
ctx=self.trainer.ctx,
)
def __init__(self, nn: HybridBlock, freq: int):
"""
:param nn: Model to plot parameters of.
:param freq: Plotting frequency.
"""
self._params = nn.collect_params()
self._freq = freq
self._last_call = 0
def print_summary(net: gluon.HybridBlock, ipt_shape=(1, 3, 416, 416)):
ctx = net.collect_params().list_ctx()[0]
ipt = mx.random.uniform(shape=ipt_shape, ctx=ctx)
net.summary(ipt)
table = compute_net_params(net)
logging.info("Parameter Statistics\n" + table.table)
if wandb.run:
headers = table.table_data[0]
data = table.table_data[1:]
wandb_table = wandb.Table(columns=headers, data=data)
wandb.log({"Parameters Statistics": wandb_table}, commit=False)
def build_optimizer(cfg: dict, net: gluon.HybridBlock):
lrs = build_lr_scheduler(cfg.pop('lr_scheduler', None))
cfg['optimizer_params']['lr_scheduler'] = lrs
net.backbone.collect_params().setattr('lr_mult',
cfg.pop('backbone_lr_mult', 1.0))
net.backbone.collect_params().setattr('wd_mult',
cfg.pop('backbone_wd_mult', 1.0))
if cfg.pop('no_wd', False):
net.collect_params('.*beta|.*gamma|.*bias').setattr('wd_mult', 0.0)
opt = cfg.pop('type', 'sgd')
optimizer_params = cfg.pop('optimizer_params', {})
if amp._amp_initialized:
cfg['update_on_kvstore'] = False
trainer = gluon.Trainer(net.collect_params(),
opt,
optimizer_params=optimizer_params,
**cfg)
if amp._amp_initialized:
amp.init_trainer(trainer)
return trainer
def create_predictor(self, transformation: Transformation,
trained_network: HybridBlock) -> Predictor:
prediction_network = SimpleFeedForwardPredictionNetwork(
num_hidden_dimensions=self.num_hidden_dimensions,
prediction_length=self.prediction_length,
context_length=self.context_length,
distr_output=self.distr_output,
batch_normalization=self.batch_normalization,
mean_scaling=self.mean_scaling,
params=trained_network.collect_params(),
num_parallel_samples=self.num_parallel_samples,
)
return RepresentableBlockPredictor(
input_transform=transformation,
prediction_net=prediction_network,
batch_size=self.trainer.batch_size,
freq=self.freq,
prediction_length=self.prediction_length,
ctx=self.trainer.ctx,
)
def __init__(self, name: str, model: gluon.HybridBlock,
input_shapes: List[List[int]]):
self._name = name
self._sym = self._get_onnx_sym(model, len(input_shapes))
self._param_dict = model.collect_params()
self._input_shapes = input_shapes