Spaces:
Sleeping
Sleeping
File size: 4,187 Bytes
d7e58f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 |
from abc import ABCMeta, abstractmethod
from collections import OrderedDict
import torch
import torch.distributed as dist
from mmcv.runner import BaseModule
class BaseArchitecture(BaseModule, metaclass=ABCMeta):
"""Base class for mmhuman3d architecture."""
def __init__(self, init_cfg=None):
super(BaseArchitecture, self).__init__(init_cfg)
@abstractmethod
def forward_train(self, **kwargs):
pass
@abstractmethod
def forward_test(self, **kwargs):
pass
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 information.
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['img_metas']))
return outputs
def val_step(self, data, optimizer=None):
"""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['img_metas']))
return outputs
def forward(self, **kwargs):
if self.training:
return self.forward_train(**kwargs)
else:
return self.forward_test(**kwargs)
|