def numerical_check(_net, _cfg: Configuration, train_data, test_data, dump_result=False): # pragma: no cover
ctx = _cfg.ctx
batch_size = _cfg.batch_size
_net.initialize(ctx=ctx)
bp_loss_f = get_bp_loss(**_cfg.loss_params)
loss_function = {}
loss_function.update(bp_loss_f)
from longling.ML.MxnetHelper.glue import module
from longling.ML.toolkit import EvalFormatter as Formatter
from longling.ML.toolkit import MovingLoss
from tqdm import tqdm
loss_monitor = MovingLoss(loss_function)
progress_monitor = tqdm
if dump_result:
from longling import config_logging
validation_logger = config_logging(
filename=path_append(_cfg.model_dir, "result.log"),
logger="%s-validation" % _cfg.model_name,
mode="w",
log_format="%(message)s",
)
evaluation_formatter = Formatter(
logger=validation_logger,
dump_file=_cfg.validation_result_file,
)
else:
evaluation_formatter = Formatter()
# train check
trainer = module.Module.get_trainer(
_net, optimizer=_cfg.optimizer,
optimizer_params=_cfg.optimizer_params,
select=_cfg.train_select
)
for epoch in range(_cfg.begin_epoch, _cfg.end_epoch):
for batch_data in progress_monitor(train_data, "Epoch: %s" % epoch):
fit_f(
net=_net, batch_size=batch_size, batch_data=batch_data,
trainer=trainer, bp_loss_f=bp_loss_f,
loss_function=loss_function,
loss_monitor=loss_monitor,
ctx=ctx,
)
if epoch % 1 == 0:
if epoch % 1 == 0:
print(
evaluation_formatter(
epoch=epoch,
loss_name_value=dict(loss_monitor.items()),
eval_name_value=eval_f(_net, test_data, ctx=ctx),
extra_info=None,
dump=True,
)[0]
)
def numerical_check(_net,
_cfg: Configuration,
train_data,
test_data,
dump_result=False,
reporthook=None,
final_reporthook=None): # pragma: no cover
ctx = _cfg.ctx
batch_size = _cfg.batch_size
_net.initialize(ctx=ctx)
bp_loss_f = get_bp_loss(**_cfg.loss_params)
loss_function = {}
loss_function.update(bp_loss_f)
from longling.ML.MxnetHelper.glue import module
from longling.ML.toolkit import EpochEvalFMT as Formatter
from longling.ML.toolkit import MovingLoss
from tqdm import tqdm
loss_monitor = MovingLoss(loss_function)
progress_monitor = tqdm
if dump_result:
from longling import config_logging
validation_logger = config_logging(
filename=path_append(_cfg.model_dir, "result.log"),
logger="%s-validation" % _cfg.model_name,
mode="w",
log_format="%(message)s",
)
evaluation_formatter = Formatter(
logger=validation_logger,
dump_file=_cfg.validation_result_file,
)
else:
evaluation_formatter = Formatter()
# train check
trainer = module.Module.get_trainer(_net,
optimizer=_cfg.optimizer,
optimizer_params=_cfg.optimizer_params,
select=_cfg.train_select)
for epoch in range(_cfg.begin_epoch, _cfg.end_epoch):
for i, batch_data in enumerate(
progress_monitor(train_data, "Epoch: %s" % epoch)):
fit_f(
net=_net,
batch_size=batch_size,
batch_data=batch_data,
trainer=trainer,
bp_loss_f=bp_loss_f,
loss_function=loss_function,
loss_monitor=loss_monitor,
ctx=ctx,
)
if _cfg.lr_params and "update_params" in _cfg.lr_params:
_cfg.logger.info("reset trainer")
lr_params = _cfg.lr_params.pop("update_params")
lr_update_params = dict(batches_per_epoch=i + 1,
lr=_cfg.optimizer_params["learning_rate"],
update_epoch=lr_params.get(
"update_epoch",
_cfg.end_epoch - _cfg.begin_epoch - 1))
lr_update_params.update(lr_params)
trainer = module.Module.get_trainer(
_net,
optimizer=_cfg.optimizer,
optimizer_params=_cfg.optimizer_params,
lr_params=lr_update_params,
select=_cfg.train_select,
logger=_cfg.logger)
if epoch % 1 == 0:
msg, data = evaluation_formatter(iteration=epoch,
loss_name_value=dict(
loss_monitor.items()),
eval_name_value=eval_f(_net,
test_data,
ctx=ctx),
extra_info=None,
dump=dump_result,
keep={"msg", "data"})
print(msg)
if reporthook is not None:
reporthook(data)
if final_reporthook is not None:
final_reporthook()
def numerical_check(_net, _cfg: Configuration, train_data, test_data, dump_result=False,
reporthook=None, final_reporthook=None): # pragma: no cover
ctx = _cfg.ctx
_net = set_device(_net, ctx)
bp_loss_f = get_bp_loss(ctx, **_cfg.loss_params)
loss_function = {}
loss_function.update(bp_loss_f)
from longling.ML.toolkit import EpochEvalFMT as Formatter
from longling.ML.toolkit import MovingLoss
from tqdm import tqdm
loss_monitor = MovingLoss(loss_function)
progress_monitor = tqdm
if dump_result:
from longling import config_logging
validation_logger = config_logging(
filename=path_append(_cfg.model_dir, "result.log"),
logger="%s-validation" % _cfg.model_name,
mode="w",
log_format="%(message)s",
)
evaluation_formatter = Formatter(
logger=validation_logger,
dump_file=_cfg.validation_result_file,
)
else:
evaluation_formatter = Formatter()
# train check
from longling.ML.PytorchHelper.toolkit.optimizer import get_trainer
trainer = get_trainer(
_net, optimizer=_cfg.optimizer,
optimizer_params=_cfg.optimizer_params,
select=_cfg.train_select
)
for epoch in range(_cfg.begin_epoch, _cfg.end_epoch):
for batch_data in progress_monitor(train_data, "Epoch: %s" % epoch):
fit_f(
net=_net, batch_data=batch_data,
trainer=trainer, bp_loss_f=bp_loss_f,
loss_function=loss_function,
loss_monitor=loss_monitor,
)
if epoch % 1 == 0:
msg, data = evaluation_formatter(
epoch=epoch,
loss_name_value=dict(loss_monitor.items()),
eval_name_value=eval_f(_net, test_data, ctx=ctx),
extra_info=None,
dump=dump_result,
)
print(msg)
if reporthook is not None:
reporthook(data)
# optional, whether reset the loss at the end of each epoch
loss_monitor.reset()
if final_reporthook is not None:
final_reporthook()