98 lines
3.7 KiB
Python
98 lines
3.7 KiB
Python
from abc import ABCMeta
|
|
from collections import OrderedDict
|
|
|
|
import torch
|
|
import torch.distributed as dist
|
|
from mmcv.runner import BaseModule
|
|
|
|
__all__ = ["Base3DFusionModel"]
|
|
|
|
|
|
class Base3DFusionModel(BaseModule, metaclass=ABCMeta):
|
|
"""Base class for fusion_models."""
|
|
|
|
def __init__(self, init_cfg=None):
|
|
super().__init__(init_cfg)
|
|
self.fp16_enabled = False
|
|
|
|
def _parse_losses(self, losses):
|
|
"""Parse the raw outputs (losses) of the network.
|
|
|
|
Args:
|
|
losses (dict): Raw output of the network, which usually contain
|
|
losses and other necessary infomation.
|
|
|
|
Returns:
|
|
tuple[Tensor, dict]: (loss, log_vars), loss is the loss tensor \
|
|
which may be a weighted sum of all losses, log_vars contains \
|
|
all the variables to be sent to the logger.
|
|
"""
|
|
log_vars = OrderedDict()
|
|
for loss_name, loss_value in losses.items():
|
|
if isinstance(loss_value, torch.Tensor):
|
|
log_vars[loss_name] = loss_value.mean()
|
|
elif isinstance(loss_value, list):
|
|
log_vars[loss_name] = sum(_loss.mean() for _loss in loss_value)
|
|
else:
|
|
raise TypeError(f"{loss_name} is not a tensor or list of tensors")
|
|
|
|
loss = sum(_value for _key, _value in log_vars.items() if "loss" in _key)
|
|
|
|
log_vars["loss"] = loss
|
|
for loss_name, loss_value in log_vars.items():
|
|
# reduce loss when distributed training
|
|
if dist.is_available() and dist.is_initialized():
|
|
loss_value = loss_value.data.clone()
|
|
dist.all_reduce(loss_value.div_(dist.get_world_size()))
|
|
log_vars[loss_name] = loss_value.item()
|
|
|
|
return loss, log_vars
|
|
|
|
def train_step(self, data, optimizer):
|
|
"""The iteration step during training.
|
|
|
|
This method defines an iteration step during training, except for the
|
|
back propagation and optimizer updating, which are done in an optimizer
|
|
hook. Note that in some complicated cases or models, the whole process
|
|
including back propagation and optimizer updating is also defined in
|
|
this method, such as GAN.
|
|
|
|
Args:
|
|
data (dict): The output of dataloader.
|
|
optimizer (:obj:`torch.optim.Optimizer` | dict): The optimizer of
|
|
runner is passed to ``train_step()``. This argument is unused
|
|
and reserved.
|
|
|
|
Returns:
|
|
dict: It should contain at least 3 keys: ``loss``, ``log_vars``, \
|
|
``num_samples``.
|
|
|
|
- ``loss`` is a tensor for back propagation, which can be a \
|
|
weighted sum of multiple losses.
|
|
- ``log_vars`` contains all the variables to be sent to the
|
|
logger.
|
|
- ``num_samples`` indicates the batch size (when the model is \
|
|
DDP, it means the batch size on each GPU), which is used for \
|
|
averaging the logs.
|
|
"""
|
|
losses = self(**data)
|
|
loss, log_vars = self._parse_losses(losses)
|
|
|
|
outputs = dict(loss=loss, log_vars=log_vars, num_samples=len(data["metas"]))
|
|
|
|
return outputs
|
|
|
|
def val_step(self, data, optimizer):
|
|
"""The iteration step during validation.
|
|
|
|
This method shares the same signature as :func:`train_step`, but used
|
|
during val epochs. Note that the evaluation after training epochs is
|
|
not implemented with this method, but an evaluation hook.
|
|
"""
|
|
losses = self(**data)
|
|
loss, log_vars = self._parse_losses(losses)
|
|
|
|
outputs = dict(loss=loss, log_vars=log_vars, num_samples=len(data["metas"]))
|
|
|
|
return outputs
|