zamba.pytorch.layers¶
Classes¶
TimeDistributed (Module)
¶
Applies module over tdim identically for each step, use low_mem to compute one at a time.
NOTE: vendored (with minor adaptations) from fastai: https://github.com/fastai/fastai/blob/4b0785254fdece1a44859956b6e54eedb167a97e/fastai/layers.py#L510-L544
Updates: - super.init() in init - assign attributes in init - inherit from torch.nn.Module rather than fastai.Module
Source code in zamba/pytorch/layers.py
class TimeDistributed(torch.nn.Module):
"""Applies `module` over `tdim` identically for each step, use `low_mem` to compute one at a time.
NOTE: vendored (with minor adaptations) from fastai:
https://github.com/fastai/fastai/blob/4b0785254fdece1a44859956b6e54eedb167a97e/fastai/layers.py#L510-L544
Updates:
- super.__init__() in init
- assign attributes in init
- inherit from torch.nn.Module rather than fastai.Module
"""
def __init__(self, module, low_mem=False, tdim=1):
super().__init__()
self.low_mem = low_mem
self.tdim = tdim
self.module = module
def forward(self, *tensors, **kwargs):
"input x with shape:(bs,seq_len,channels,width,height)"
if self.low_mem or self.tdim != 1:
return self.low_mem_forward(*tensors, **kwargs)
else:
# only support tdim=1
inp_shape = tensors[0].shape
bs, seq_len = inp_shape[0], inp_shape[1]
out = self.module(*[x.view(bs * seq_len, *x.shape[2:]) for x in tensors], **kwargs)
return self.format_output(out, bs, seq_len)
def low_mem_forward(self, *tensors, **kwargs):
"input x with shape:(bs,seq_len,channels,width,height)"
seq_len = tensors[0].shape[self.tdim]
args_split = [torch.unbind(x, dim=self.tdim) for x in tensors]
out = []
for i in range(seq_len):
out.append(self.module(*[args[i] for args in args_split]), **kwargs)
if isinstance(out[0], tuple):
return _stack_tups(out, stack_dim=self.tdim)
return torch.stack(out, dim=self.tdim)
def format_output(self, out, bs, seq_len):
"unstack from batchsize outputs"
if isinstance(out, tuple):
return tuple(out_i.view(bs, seq_len, *out_i.shape[1:]) for out_i in out)
return out.view(bs, seq_len, *out.shape[1:])
def __repr__(self):
return f"TimeDistributed({self.module})"
Attributes¶
T_destination
inherited
¶
dump_patches: bool
inherited
¶
This allows better BC support for :meth:load_state_dict. In
:meth:state_dict, the version number will be saved as in the attribute
_metadata of the returned state dict, and thus pickled. _metadata is a
dictionary with keys that follow the naming convention of state dict. See
_load_from_state_dict on how to use this information in loading.
If new parameters/buffers are added/removed from a module, this number shall
be bumped, and the module's _load_from_state_dict method can compare the
version number and do appropriate changes if the state dict is from before
the change.
Methods¶
__init__(self, module, low_mem = False, tdim = 1)
special
¶
Source code in zamba/pytorch/layers.py
def __init__(self, module, low_mem=False, tdim=1):
super().__init__()
self.low_mem = low_mem
self.tdim = tdim
self.module = module
add_module(self, name: str, module: Optional[Module]) -> None
inherited
¶
Adds a child module to the current module.
The module can be accessed as an attribute using the given name.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
name |
string |
name of the child module. The child module can be accessed from this module using the given name |
required |
module |
Module |
child module to be added to the module. |
required |
Source code in zamba/pytorch/layers.py
def add_module(self, name: str, module: Optional['Module']) -> None:
r"""Adds a child module to the current module.
The module can be accessed as an attribute using the given name.
Args:
name (string): name of the child module. The child module can be
accessed from this module using the given name
module (Module): child module to be added to the module.
"""
if not isinstance(module, Module) and module is not None:
raise TypeError("{} is not a Module subclass".format(
torch.typename(module)))
elif not isinstance(name, torch._six.string_classes):
raise TypeError("module name should be a string. Got {}".format(
torch.typename(name)))
elif hasattr(self, name) and name not in self._modules:
raise KeyError("attribute '{}' already exists".format(name))
elif '.' in name:
raise KeyError("module name can't contain \".\", got: {}".format(name))
elif name == '':
raise KeyError("module name can't be empty string \"\"")
self._modules[name] = module
apply(self: ~T, fn: Callable[[Module], NoneType]) -> ~T
inherited
¶
Applies fn recursively to every submodule (as returned by .children())
as well as self. Typical use includes initializing the parameters of a model
(see also :ref:nn-init-doc).
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
fn |
class: |
required |
Returns:
| Type | Description |
|---|---|
Module |
self |
Example::
>>> @torch.no_grad()
>>> def init_weights(m):
>>> print(m)
>>> if type(m) == nn.Linear:
>>> m.weight.fill_(1.0)
>>> print(m.weight)
>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))
>>> net.apply(init_weights)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[ 1., 1.],
[ 1., 1.]])
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[ 1., 1.],
[ 1., 1.]])
Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
)
Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
)
Source code in zamba/pytorch/layers.py
def apply(self: T, fn: Callable[['Module'], None]) -> T:
r"""Applies ``fn`` recursively to every submodule (as returned by ``.children()``)
as well as self. Typical use includes initializing the parameters of a model
(see also :ref:`nn-init-doc`).
Args:
fn (:class:`Module` -> None): function to be applied to each submodule
Returns:
Module: self
Example::
>>> @torch.no_grad()
>>> def init_weights(m):
>>> print(m)
>>> if type(m) == nn.Linear:
>>> m.weight.fill_(1.0)
>>> print(m.weight)
>>> net = nn.Sequential(nn.Linear(2, 2), nn.Linear(2, 2))
>>> net.apply(init_weights)
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[ 1., 1.],
[ 1., 1.]])
Linear(in_features=2, out_features=2, bias=True)
Parameter containing:
tensor([[ 1., 1.],
[ 1., 1.]])
Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
)
Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
)
"""
for module in self.children():
module.apply(fn)
fn(self)
return self
bfloat16(self: ~T) -> ~T
inherited
¶
Casts all floating point parameters and buffers to bfloat16 datatype.
.. note:: This method modifies the module in-place.
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def bfloat16(self: T) -> T:
r"""Casts all floating point parameters and buffers to ``bfloat16`` datatype.
.. note::
This method modifies the module in-place.
Returns:
Module: self
"""
return self._apply(lambda t: t.bfloat16() if t.is_floating_point() else t)
buffers(self, recurse: bool = True) -> Iterator[torch.Tensor]
inherited
¶
Returns an iterator over module buffers.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
recurse |
bool |
if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module. |
True |
Yields:
| Type | Description |
|---|---|
torch.Tensor |
module buffer |
Example::
>>> for buf in model.buffers():
>>> print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)
Source code in zamba/pytorch/layers.py
def buffers(self, recurse: bool = True) -> Iterator[Tensor]:
r"""Returns an iterator over module buffers.
Args:
recurse (bool): if True, then yields buffers of this module
and all submodules. Otherwise, yields only buffers that
are direct members of this module.
Yields:
torch.Tensor: module buffer
Example::
>>> for buf in model.buffers():
>>> print(type(buf), buf.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)
"""
for _, buf in self.named_buffers(recurse=recurse):
yield buf
children(self) -> Iterator[Module]
inherited
¶
Returns an iterator over immediate children modules.
Yields:
| Type | Description |
|---|---|
Module |
a child module |
Source code in zamba/pytorch/layers.py
def children(self) -> Iterator['Module']:
r"""Returns an iterator over immediate children modules.
Yields:
Module: a child module
"""
for name, module in self.named_children():
yield module
cpu(self: ~T) -> ~T
inherited
¶
Moves all model parameters and buffers to the CPU.
.. note:: This method modifies the module in-place.
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def cpu(self: T) -> T:
r"""Moves all model parameters and buffers to the CPU.
.. note::
This method modifies the module in-place.
Returns:
Module: self
"""
return self._apply(lambda t: t.cpu())
cuda(self: ~T, device: Union[int, torch.device] = None) -> ~T
inherited
¶
Moves all model parameters and buffers to the GPU.
This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on GPU while being optimized.
.. note:: This method modifies the module in-place.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
device |
int |
if specified, all parameters will be copied to that device |
None |
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def cuda(self: T, device: Optional[Union[int, device]] = None) -> T:
r"""Moves all model parameters and buffers to the GPU.
This also makes associated parameters and buffers different objects. So
it should be called before constructing optimizer if the module will
live on GPU while being optimized.
.. note::
This method modifies the module in-place.
Args:
device (int, optional): if specified, all parameters will be
copied to that device
Returns:
Module: self
"""
return self._apply(lambda t: t.cuda(device))
double(self: ~T) -> ~T
inherited
¶
Casts all floating point parameters and buffers to double datatype.
.. note:: This method modifies the module in-place.
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def double(self: T) -> T:
r"""Casts all floating point parameters and buffers to ``double`` datatype.
.. note::
This method modifies the module in-place.
Returns:
Module: self
"""
return self._apply(lambda t: t.double() if t.is_floating_point() else t)
eval(self: ~T) -> ~T
inherited
¶
Sets the module in evaluation mode.
This has any effect only on certain modules. See documentations of
particular modules for details of their behaviors in training/evaluation
mode, if they are affected, e.g. :class:Dropout, :class:BatchNorm,
etc.
This is equivalent with :meth:self.train(False) <torch.nn.Module.train>.
See :ref:locally-disable-grad-doc for a comparison between
.eval() and several similar mechanisms that may be confused with it.
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def eval(self: T) -> T:
r"""Sets the module in evaluation mode.
This has any effect only on certain modules. See documentations of
particular modules for details of their behaviors in training/evaluation
mode, if they are affected, e.g. :class:`Dropout`, :class:`BatchNorm`,
etc.
This is equivalent with :meth:`self.train(False) <torch.nn.Module.train>`.
See :ref:`locally-disable-grad-doc` for a comparison between
`.eval()` and several similar mechanisms that may be confused with it.
Returns:
Module: self
"""
return self.train(False)
extra_repr(self) -> str
inherited
¶
Set the extra representation of the module
To print customized extra information, you should re-implement this method in your own modules. Both single-line and multi-line strings are acceptable.
Source code in zamba/pytorch/layers.py
def extra_repr(self) -> str:
r"""Set the extra representation of the module
To print customized extra information, you should re-implement
this method in your own modules. Both single-line and multi-line
strings are acceptable.
"""
return ''
float(self: ~T) -> ~T
inherited
¶
Casts all floating point parameters and buffers to float datatype.
.. note:: This method modifies the module in-place.
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def float(self: T) -> T:
r"""Casts all floating point parameters and buffers to ``float`` datatype.
.. note::
This method modifies the module in-place.
Returns:
Module: self
"""
return self._apply(lambda t: t.float() if t.is_floating_point() else t)
format_output(self, out, bs, seq_len)
¶
unstack from batchsize outputs
Source code in zamba/pytorch/layers.py
def format_output(self, out, bs, seq_len):
"unstack from batchsize outputs"
if isinstance(out, tuple):
return tuple(out_i.view(bs, seq_len, *out_i.shape[1:]) for out_i in out)
return out.view(bs, seq_len, *out.shape[1:])
forward(self, *tensors, **kwargs)
¶
input x with shape:(bs,seq_len,channels,width,height)
Source code in zamba/pytorch/layers.py
def forward(self, *tensors, **kwargs):
"input x with shape:(bs,seq_len,channels,width,height)"
if self.low_mem or self.tdim != 1:
return self.low_mem_forward(*tensors, **kwargs)
else:
# only support tdim=1
inp_shape = tensors[0].shape
bs, seq_len = inp_shape[0], inp_shape[1]
out = self.module(*[x.view(bs * seq_len, *x.shape[2:]) for x in tensors], **kwargs)
return self.format_output(out, bs, seq_len)
get_buffer(self, target: str) -> Tensor
inherited
¶
Returns the buffer given by target if it exists,
otherwise throws an error.
See the docstring for get_submodule for a more detailed
explanation of this method's functionality as well as how to
correctly specify target.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
target |
str |
The fully-qualified string name of the buffer
to look for. (See |
required |
Returns:
| Type | Description |
|---|---|
torch.Tensor |
The buffer referenced by |
Exceptions:
| Type | Description |
|---|---|
AttributeError |
If the target string references an invalid path or resolves to something that is not a buffer |
Source code in zamba/pytorch/layers.py
def get_buffer(self, target: str) -> "Tensor":
"""
Returns the buffer given by ``target`` if it exists,
otherwise throws an error.
See the docstring for ``get_submodule`` for a more detailed
explanation of this method's functionality as well as how to
correctly specify ``target``.
Args:
target: The fully-qualified string name of the buffer
to look for. (See ``get_submodule`` for how to specify a
fully-qualified string.)
Returns:
torch.Tensor: The buffer referenced by ``target``
Raises:
AttributeError: If the target string references an invalid
path or resolves to something that is not a
buffer
"""
module_path, _, buffer_name = target.rpartition(".")
mod: torch.nn.Module = self.get_submodule(module_path)
if not hasattr(mod, buffer_name):
raise AttributeError(mod._get_name() + " has no attribute `"
+ buffer_name + "`")
buffer: torch.Tensor = getattr(mod, buffer_name)
if buffer_name not in mod._buffers:
raise AttributeError("`" + buffer_name + "` is not a buffer")
return buffer
get_extra_state(self) -> Any
inherited
¶
Returns any extra state to include in the module's state_dict.
Implement this and a corresponding :func:set_extra_state for your module
if you need to store extra state. This function is called when building the
module's state_dict().
Note that extra state should be pickleable to ensure working serialization of the state_dict. We only provide provide backwards compatibility guarantees for serializing Tensors; other objects may break backwards compatibility if their serialized pickled form changes.
Returns:
| Type | Description |
|---|---|
object |
Any extra state to store in the module's state_dict |
Source code in zamba/pytorch/layers.py
def get_extra_state(self) -> Any:
"""
Returns any extra state to include in the module's state_dict.
Implement this and a corresponding :func:`set_extra_state` for your module
if you need to store extra state. This function is called when building the
module's `state_dict()`.
Note that extra state should be pickleable to ensure working serialization
of the state_dict. We only provide provide backwards compatibility guarantees
for serializing Tensors; other objects may break backwards compatibility if
their serialized pickled form changes.
Returns:
object: Any extra state to store in the module's state_dict
"""
raise RuntimeError(
"Reached a code path in Module.get_extra_state() that should never be called. "
"Please file an issue at https://github.com/pytorch/pytorch/issues/new?template=bug-report.md "
"to report this bug.")
get_parameter(self, target: str) -> Parameter
inherited
¶
Returns the parameter given by target if it exists,
otherwise throws an error.
See the docstring for get_submodule for a more detailed
explanation of this method's functionality as well as how to
correctly specify target.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
target |
str |
The fully-qualified string name of the Parameter
to look for. (See |
required |
Returns:
| Type | Description |
|---|---|
torch.nn.Parameter |
The Parameter referenced by |
Exceptions:
| Type | Description |
|---|---|
AttributeError |
If the target string references an invalid
path or resolves to something that is not an
|
Source code in zamba/pytorch/layers.py
def get_parameter(self, target: str) -> "Parameter":
"""
Returns the parameter given by ``target`` if it exists,
otherwise throws an error.
See the docstring for ``get_submodule`` for a more detailed
explanation of this method's functionality as well as how to
correctly specify ``target``.
Args:
target: The fully-qualified string name of the Parameter
to look for. (See ``get_submodule`` for how to specify a
fully-qualified string.)
Returns:
torch.nn.Parameter: The Parameter referenced by ``target``
Raises:
AttributeError: If the target string references an invalid
path or resolves to something that is not an
``nn.Parameter``
"""
module_path, _, param_name = target.rpartition(".")
mod: torch.nn.Module = self.get_submodule(module_path)
if not hasattr(mod, param_name):
raise AttributeError(mod._get_name() + " has no attribute `"
+ param_name + "`")
param: torch.nn.Parameter = getattr(mod, param_name)
if not isinstance(param, torch.nn.Parameter):
raise AttributeError("`" + param_name + "` is not an "
"nn.Parameter")
return param
get_submodule(self, target: str) -> Module
inherited
¶
Returns the submodule given by target if it exists,
otherwise throws an error.
For example, let's say you have an nn.Module A that
looks like this:
.. code-block::text
A(
(net_b): Module(
(net_c): Module(
(conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
)
(linear): Linear(in_features=100, out_features=200, bias=True)
)
)
(The diagram shows an nn.Module A. A has a nested
submodule net_b, which itself has two submodules net_c
and linear. net_c then has a submodule conv.)
To check whether or not we have the linear submodule, we
would call get_submodule("net_b.linear"). To check whether
we have the conv submodule, we would call
get_submodule("net_b.net_c.conv").
The runtime of get_submodule is bounded by the degree
of module nesting in target. A query against
named_modules achieves the same result, but it is O(N) in
the number of transitive modules. So, for a simple check to see
if some submodule exists, get_submodule should always be
used.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
target |
str |
The fully-qualified string name of the submodule to look for. (See above example for how to specify a fully-qualified string.) |
required |
Returns:
| Type | Description |
|---|---|
torch.nn.Module |
The submodule referenced by |
Exceptions:
| Type | Description |
|---|---|
AttributeError |
If the target string references an invalid
path or resolves to something that is not an
|
Source code in zamba/pytorch/layers.py
def get_submodule(self, target: str) -> "Module":
"""
Returns the submodule given by ``target`` if it exists,
otherwise throws an error.
For example, let's say you have an ``nn.Module`` ``A`` that
looks like this:
.. code-block::text
A(
(net_b): Module(
(net_c): Module(
(conv): Conv2d(16, 33, kernel_size=(3, 3), stride=(2, 2))
)
(linear): Linear(in_features=100, out_features=200, bias=True)
)
)
(The diagram shows an ``nn.Module`` ``A``. ``A`` has a nested
submodule ``net_b``, which itself has two submodules ``net_c``
and ``linear``. ``net_c`` then has a submodule ``conv``.)
To check whether or not we have the ``linear`` submodule, we
would call ``get_submodule("net_b.linear")``. To check whether
we have the ``conv`` submodule, we would call
``get_submodule("net_b.net_c.conv")``.
The runtime of ``get_submodule`` is bounded by the degree
of module nesting in ``target``. A query against
``named_modules`` achieves the same result, but it is O(N) in
the number of transitive modules. So, for a simple check to see
if some submodule exists, ``get_submodule`` should always be
used.
Args:
target: The fully-qualified string name of the submodule
to look for. (See above example for how to specify a
fully-qualified string.)
Returns:
torch.nn.Module: The submodule referenced by ``target``
Raises:
AttributeError: If the target string references an invalid
path or resolves to something that is not an
``nn.Module``
"""
if target == "":
return self
atoms: List[str] = target.split(".")
mod: torch.nn.Module = self
for item in atoms:
if not hasattr(mod, item):
raise AttributeError(mod._get_name() + " has no "
"attribute `" + item + "`")
mod = getattr(mod, item)
if not isinstance(mod, torch.nn.Module):
raise AttributeError("`" + item + "` is not "
"an nn.Module")
return mod
half(self: ~T) -> ~T
inherited
¶
Casts all floating point parameters and buffers to half datatype.
.. note:: This method modifies the module in-place.
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def half(self: T) -> T:
r"""Casts all floating point parameters and buffers to ``half`` datatype.
.. note::
This method modifies the module in-place.
Returns:
Module: self
"""
return self._apply(lambda t: t.half() if t.is_floating_point() else t)
load_state_dict(self, state_dict: OrderedDict[str, Tensor], strict: bool = True)
inherited
¶
Copies parameters and buffers from :attr:state_dict into
this module and its descendants. If :attr:strict is True, then
the keys of :attr:state_dict must exactly match the keys returned
by this module's :meth:~torch.nn.Module.state_dict function.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
state_dict |
dict |
a dict containing parameters and persistent buffers. |
required |
strict |
bool |
whether to strictly enforce that the keys
in :attr: |
True |
Returns:
| Type | Description |
|---|---|
``NamedTuple`` with ``missing_keys`` and ``unexpected_keys`` fields |
|
!!! note
If a parameter or buffer is registered as None and its corresponding key
exists in :attr:state_dict, :meth:load_state_dict will raise a
RuntimeError.
Source code in zamba/pytorch/layers.py
def load_state_dict(self, state_dict: 'OrderedDict[str, Tensor]',
strict: bool = True):
r"""Copies parameters and buffers from :attr:`state_dict` into
this module and its descendants. If :attr:`strict` is ``True``, then
the keys of :attr:`state_dict` must exactly match the keys returned
by this module's :meth:`~torch.nn.Module.state_dict` function.
Args:
state_dict (dict): a dict containing parameters and
persistent buffers.
strict (bool, optional): whether to strictly enforce that the keys
in :attr:`state_dict` match the keys returned by this module's
:meth:`~torch.nn.Module.state_dict` function. Default: ``True``
Returns:
``NamedTuple`` with ``missing_keys`` and ``unexpected_keys`` fields:
* **missing_keys** is a list of str containing the missing keys
* **unexpected_keys** is a list of str containing the unexpected keys
Note:
If a parameter or buffer is registered as ``None`` and its corresponding key
exists in :attr:`state_dict`, :meth:`load_state_dict` will raise a
``RuntimeError``.
"""
missing_keys: List[str] = []
unexpected_keys: List[str] = []
error_msgs: List[str] = []
# copy state_dict so _load_from_state_dict can modify it
metadata = getattr(state_dict, '_metadata', None)
state_dict = state_dict.copy()
if metadata is not None:
# mypy isn't aware that "_metadata" exists in state_dict
state_dict._metadata = metadata # type: ignore[attr-defined]
def load(module, prefix=''):
local_metadata = {} if metadata is None else metadata.get(prefix[:-1], {})
module._load_from_state_dict(
state_dict, prefix, local_metadata, True, missing_keys, unexpected_keys, error_msgs)
for name, child in module._modules.items():
if child is not None:
load(child, prefix + name + '.')
load(self)
del load
if strict:
if len(unexpected_keys) > 0:
error_msgs.insert(
0, 'Unexpected key(s) in state_dict: {}. '.format(
', '.join('"{}"'.format(k) for k in unexpected_keys)))
if len(missing_keys) > 0:
error_msgs.insert(
0, 'Missing key(s) in state_dict: {}. '.format(
', '.join('"{}"'.format(k) for k in missing_keys)))
if len(error_msgs) > 0:
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
self.__class__.__name__, "\n\t".join(error_msgs)))
return _IncompatibleKeys(missing_keys, unexpected_keys)
low_mem_forward(self, *tensors, **kwargs)
¶
input x with shape:(bs,seq_len,channels,width,height)
Source code in zamba/pytorch/layers.py
def low_mem_forward(self, *tensors, **kwargs):
"input x with shape:(bs,seq_len,channels,width,height)"
seq_len = tensors[0].shape[self.tdim]
args_split = [torch.unbind(x, dim=self.tdim) for x in tensors]
out = []
for i in range(seq_len):
out.append(self.module(*[args[i] for args in args_split]), **kwargs)
if isinstance(out[0], tuple):
return _stack_tups(out, stack_dim=self.tdim)
return torch.stack(out, dim=self.tdim)
modules(self) -> Iterator[Module]
inherited
¶
Returns an iterator over all modules in the network.
Yields:
| Type | Description |
|---|---|
Module |
a module in the network |
!!! note
Duplicate modules are returned only once. In the following
example, l will be returned only once.
Example::
>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
print(idx, '->', m)
0 -> Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)
Source code in zamba/pytorch/layers.py
def modules(self) -> Iterator['Module']:
r"""Returns an iterator over all modules in the network.
Yields:
Module: a module in the network
Note:
Duplicate modules are returned only once. In the following
example, ``l`` will be returned only once.
Example::
>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.modules()):
print(idx, '->', m)
0 -> Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
)
1 -> Linear(in_features=2, out_features=2, bias=True)
"""
for _, module in self.named_modules():
yield module
named_buffers(self, prefix: str = '', recurse: bool = True) -> Iterator[Tuple[str, torch.Tensor]]
inherited
¶
Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
prefix |
str |
prefix to prepend to all buffer names. |
'' |
recurse |
bool |
if True, then yields buffers of this module and all submodules. Otherwise, yields only buffers that are direct members of this module. |
True |
Yields:
| Type | Description |
|---|---|
(string, torch.Tensor) |
Tuple containing the name and buffer |
Example::
>>> for name, buf in self.named_buffers():
>>> if name in ['running_var']:
>>> print(buf.size())
Source code in zamba/pytorch/layers.py
def named_buffers(self, prefix: str = '', recurse: bool = True) -> Iterator[Tuple[str, Tensor]]:
r"""Returns an iterator over module buffers, yielding both the
name of the buffer as well as the buffer itself.
Args:
prefix (str): prefix to prepend to all buffer names.
recurse (bool): if True, then yields buffers of this module
and all submodules. Otherwise, yields only buffers that
are direct members of this module.
Yields:
(string, torch.Tensor): Tuple containing the name and buffer
Example::
>>> for name, buf in self.named_buffers():
>>> if name in ['running_var']:
>>> print(buf.size())
"""
gen = self._named_members(
lambda module: module._buffers.items(),
prefix=prefix, recurse=recurse)
for elem in gen:
yield elem
named_children(self) -> Iterator[Tuple[str, Module]]
inherited
¶
Returns an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
Yields:
| Type | Description |
|---|---|
(string, Module) |
Tuple containing a name and child module |
Example::
>>> for name, module in model.named_children():
>>> if name in ['conv4', 'conv5']:
>>> print(module)
Source code in zamba/pytorch/layers.py
def named_children(self) -> Iterator[Tuple[str, 'Module']]:
r"""Returns an iterator over immediate children modules, yielding both
the name of the module as well as the module itself.
Yields:
(string, Module): Tuple containing a name and child module
Example::
>>> for name, module in model.named_children():
>>> if name in ['conv4', 'conv5']:
>>> print(module)
"""
memo = set()
for name, module in self._modules.items():
if module is not None and module not in memo:
memo.add(module)
yield name, module
named_modules(self, memo: Optional[Set[Module]] = None, prefix: str = '', remove_duplicate: bool = True)
inherited
¶
Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
memo |
Optional[Set[Module]] |
a memo to store the set of modules already added to the result |
None |
prefix |
str |
a prefix that will be added to the name of the module |
'' |
remove_duplicate |
bool |
whether to remove the duplicated module instances in the result |
True |
Yields:
| Type | Description |
|---|---|
(string, Module) |
Tuple of name and module |
!!! note
Duplicate modules are returned only once. In the following
example, l will be returned only once.
Example::
>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.named_modules()):
print(idx, '->', m)
0 -> ('', Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
))
1 -> ('0', Linear(in_features=2, out_features=2, bias=True))
Source code in zamba/pytorch/layers.py
def named_modules(self, memo: Optional[Set['Module']] = None, prefix: str = '', remove_duplicate: bool = True):
r"""Returns an iterator over all modules in the network, yielding
both the name of the module as well as the module itself.
Args:
memo: a memo to store the set of modules already added to the result
prefix: a prefix that will be added to the name of the module
remove_duplicate: whether to remove the duplicated module instances in the result
or not
Yields:
(string, Module): Tuple of name and module
Note:
Duplicate modules are returned only once. In the following
example, ``l`` will be returned only once.
Example::
>>> l = nn.Linear(2, 2)
>>> net = nn.Sequential(l, l)
>>> for idx, m in enumerate(net.named_modules()):
print(idx, '->', m)
0 -> ('', Sequential(
(0): Linear(in_features=2, out_features=2, bias=True)
(1): Linear(in_features=2, out_features=2, bias=True)
))
1 -> ('0', Linear(in_features=2, out_features=2, bias=True))
"""
if memo is None:
memo = set()
if self not in memo:
if remove_duplicate:
memo.add(self)
yield prefix, self
for name, module in self._modules.items():
if module is None:
continue
submodule_prefix = prefix + ('.' if prefix else '') + name
for m in module.named_modules(memo, submodule_prefix, remove_duplicate):
yield m
named_parameters(self, prefix: str = '', recurse: bool = True) -> Iterator[Tuple[str, torch.nn.parameter.Parameter]]
inherited
¶
Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
prefix |
str |
prefix to prepend to all parameter names. |
'' |
recurse |
bool |
if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module. |
True |
Yields:
| Type | Description |
|---|---|
(string, Parameter) |
Tuple containing the name and parameter |
Example::
>>> for name, param in self.named_parameters():
>>> if name in ['bias']:
>>> print(param.size())
Source code in zamba/pytorch/layers.py
def named_parameters(self, prefix: str = '', recurse: bool = True) -> Iterator[Tuple[str, Parameter]]:
r"""Returns an iterator over module parameters, yielding both the
name of the parameter as well as the parameter itself.
Args:
prefix (str): prefix to prepend to all parameter names.
recurse (bool): if True, then yields parameters of this module
and all submodules. Otherwise, yields only parameters that
are direct members of this module.
Yields:
(string, Parameter): Tuple containing the name and parameter
Example::
>>> for name, param in self.named_parameters():
>>> if name in ['bias']:
>>> print(param.size())
"""
gen = self._named_members(
lambda module: module._parameters.items(),
prefix=prefix, recurse=recurse)
for elem in gen:
yield elem
parameters(self, recurse: bool = True) -> Iterator[torch.nn.parameter.Parameter]
inherited
¶
Returns an iterator over module parameters.
This is typically passed to an optimizer.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
recurse |
bool |
if True, then yields parameters of this module and all submodules. Otherwise, yields only parameters that are direct members of this module. |
True |
Yields:
| Type | Description |
|---|---|
Parameter |
module parameter |
Example::
>>> for param in model.parameters():
>>> print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)
Source code in zamba/pytorch/layers.py
def parameters(self, recurse: bool = True) -> Iterator[Parameter]:
r"""Returns an iterator over module parameters.
This is typically passed to an optimizer.
Args:
recurse (bool): if True, then yields parameters of this module
and all submodules. Otherwise, yields only parameters that
are direct members of this module.
Yields:
Parameter: module parameter
Example::
>>> for param in model.parameters():
>>> print(type(param), param.size())
<class 'torch.Tensor'> (20L,)
<class 'torch.Tensor'> (20L, 1L, 5L, 5L)
"""
for name, param in self.named_parameters(recurse=recurse):
yield param
register_backward_hook(self, hook: Callable[[Module, Union[Tuple[torch.Tensor, ...], torch.Tensor], Union[Tuple[torch.Tensor, ...], torch.Tensor]], Union[NoneType, torch.Tensor]]) -> RemovableHandle
inherited
¶
Registers a backward hook on the module.
This function is deprecated in favor of :meth:~torch.nn.Module.register_full_backward_hook and
the behavior of this function will change in future versions.
Returns:
| Type | Description |
|---|---|
class: |
Source code in zamba/pytorch/layers.py
def register_backward_hook(
self, hook: Callable[['Module', _grad_t, _grad_t], Union[None, Tensor]]
) -> RemovableHandle:
r"""Registers a backward hook on the module.
This function is deprecated in favor of :meth:`~torch.nn.Module.register_full_backward_hook` and
the behavior of this function will change in future versions.
Returns:
:class:`torch.utils.hooks.RemovableHandle`:
a handle that can be used to remove the added hook by calling
``handle.remove()``
"""
if self._is_full_backward_hook is True:
raise RuntimeError("Cannot use both regular backward hooks and full backward hooks on a "
"single Module. Please use only one of them.")
self._is_full_backward_hook = False
handle = hooks.RemovableHandle(self._backward_hooks)
self._backward_hooks[handle.id] = hook
return handle
register_buffer(self, name: str, tensor: Optional[torch.Tensor], persistent: bool = True) -> None
inherited
¶
Adds a buffer to the module.
This is typically used to register a buffer that should not to be
considered a model parameter. For example, BatchNorm's running_mean
is not a parameter, but is part of the module's state. Buffers, by
default, are persistent and will be saved alongside parameters. This
behavior can be changed by setting :attr:persistent to False. The
only difference between a persistent buffer and a non-persistent buffer
is that the latter will not be a part of this module's
:attr:state_dict.
Buffers can be accessed as attributes using given names.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
name |
string |
name of the buffer. The buffer can be accessed from this module using the given name |
required |
tensor |
Tensor or None |
buffer to be registered. If |
required |
persistent |
bool |
whether the buffer is part of this module's
:attr: |
True |
Example::
>>> self.register_buffer('running_mean', torch.zeros(num_features))
Source code in zamba/pytorch/layers.py
def register_buffer(self, name: str, tensor: Optional[Tensor], persistent: bool = True) -> None:
r"""Adds a buffer to the module.
This is typically used to register a buffer that should not to be
considered a model parameter. For example, BatchNorm's ``running_mean``
is not a parameter, but is part of the module's state. Buffers, by
default, are persistent and will be saved alongside parameters. This
behavior can be changed by setting :attr:`persistent` to ``False``. The
only difference between a persistent buffer and a non-persistent buffer
is that the latter will not be a part of this module's
:attr:`state_dict`.
Buffers can be accessed as attributes using given names.
Args:
name (string): name of the buffer. The buffer can be accessed
from this module using the given name
tensor (Tensor or None): buffer to be registered. If ``None``, then operations
that run on buffers, such as :attr:`cuda`, are ignored. If ``None``,
the buffer is **not** included in the module's :attr:`state_dict`.
persistent (bool): whether the buffer is part of this module's
:attr:`state_dict`.
Example::
>>> self.register_buffer('running_mean', torch.zeros(num_features))
"""
if persistent is False and isinstance(self, torch.jit.ScriptModule):
raise RuntimeError("ScriptModule does not support non-persistent buffers")
if '_buffers' not in self.__dict__:
raise AttributeError(
"cannot assign buffer before Module.__init__() call")
elif not isinstance(name, torch._six.string_classes):
raise TypeError("buffer name should be a string. "
"Got {}".format(torch.typename(name)))
elif '.' in name:
raise KeyError("buffer name can't contain \".\"")
elif name == '':
raise KeyError("buffer name can't be empty string \"\"")
elif hasattr(self, name) and name not in self._buffers:
raise KeyError("attribute '{}' already exists".format(name))
elif tensor is not None and not isinstance(tensor, torch.Tensor):
raise TypeError("cannot assign '{}' object to buffer '{}' "
"(torch Tensor or None required)"
.format(torch.typename(tensor), name))
else:
self._buffers[name] = tensor
if persistent:
self._non_persistent_buffers_set.discard(name)
else:
self._non_persistent_buffers_set.add(name)
register_forward_hook(self, hook: Callable[..., NoneType]) -> RemovableHandle
inherited
¶
Registers a forward hook on the module.
The hook will be called every time after :func:forward has computed an output.
It should have the following signature::
hook(module, input, output) -> None or modified output
The input contains only the positional arguments given to the module.
Keyword arguments won't be passed to the hooks and only to the forward.
The hook can modify the output. It can modify the input inplace but
it will not have effect on forward since this is called after
:func:forward is called.
Returns:
| Type | Description |
|---|---|
class: |
Source code in zamba/pytorch/layers.py
def register_forward_hook(self, hook: Callable[..., None]) -> RemovableHandle:
r"""Registers a forward hook on the module.
The hook will be called every time after :func:`forward` has computed an output.
It should have the following signature::
hook(module, input, output) -> None or modified output
The input contains only the positional arguments given to the module.
Keyword arguments won't be passed to the hooks and only to the ``forward``.
The hook can modify the output. It can modify the input inplace but
it will not have effect on forward since this is called after
:func:`forward` is called.
Returns:
:class:`torch.utils.hooks.RemovableHandle`:
a handle that can be used to remove the added hook by calling
``handle.remove()``
"""
handle = hooks.RemovableHandle(self._forward_hooks)
self._forward_hooks[handle.id] = hook
return handle
register_forward_pre_hook(self, hook: Callable[..., NoneType]) -> RemovableHandle
inherited
¶
Registers a forward pre-hook on the module.
The hook will be called every time before :func:forward is invoked.
It should have the following signature::
hook(module, input) -> None or modified input
The input contains only the positional arguments given to the module.
Keyword arguments won't be passed to the hooks and only to the forward.
The hook can modify the input. User can either return a tuple or a
single modified value in the hook. We will wrap the value into a tuple
if a single value is returned(unless that value is already a tuple).
Returns:
| Type | Description |
|---|---|
class: |
Source code in zamba/pytorch/layers.py
def register_forward_pre_hook(self, hook: Callable[..., None]) -> RemovableHandle:
r"""Registers a forward pre-hook on the module.
The hook will be called every time before :func:`forward` is invoked.
It should have the following signature::
hook(module, input) -> None or modified input
The input contains only the positional arguments given to the module.
Keyword arguments won't be passed to the hooks and only to the ``forward``.
The hook can modify the input. User can either return a tuple or a
single modified value in the hook. We will wrap the value into a tuple
if a single value is returned(unless that value is already a tuple).
Returns:
:class:`torch.utils.hooks.RemovableHandle`:
a handle that can be used to remove the added hook by calling
``handle.remove()``
"""
handle = hooks.RemovableHandle(self._forward_pre_hooks)
self._forward_pre_hooks[handle.id] = hook
return handle
register_full_backward_hook(self, hook: Callable[[Module, Union[Tuple[torch.Tensor, ...], torch.Tensor], Union[Tuple[torch.Tensor, ...], torch.Tensor]], Union[NoneType, torch.Tensor]]) -> RemovableHandle
inherited
¶
Registers a backward hook on the module.
The hook will be called every time the gradients with respect to module inputs are computed. The hook should have the following signature::
hook(module, grad_input, grad_output) -> tuple(Tensor) or None
The :attr:grad_input and :attr:grad_output are tuples that contain the gradients
with respect to the inputs and outputs respectively. The hook should
not modify its arguments, but it can optionally return a new gradient with
respect to the input that will be used in place of :attr:grad_input in
subsequent computations. :attr:grad_input will only correspond to the inputs given
as positional arguments and all kwarg arguments are ignored. Entries
in :attr:grad_input and :attr:grad_output will be None for all non-Tensor
arguments.
For technical reasons, when this hook is applied to a Module, its forward function will receive a view of each Tensor passed to the Module. Similarly the caller will receive a view of each Tensor returned by the Module's forward function.
.. warning :: Modifying inputs or outputs inplace is not allowed when using backward hooks and will raise an error.
Returns:
| Type | Description |
|---|---|
class: |
Source code in zamba/pytorch/layers.py
def register_full_backward_hook(
self, hook: Callable[['Module', _grad_t, _grad_t], Union[None, Tensor]]
) -> RemovableHandle:
r"""Registers a backward hook on the module.
The hook will be called every time the gradients with respect to module
inputs are computed. The hook should have the following signature::
hook(module, grad_input, grad_output) -> tuple(Tensor) or None
The :attr:`grad_input` and :attr:`grad_output` are tuples that contain the gradients
with respect to the inputs and outputs respectively. The hook should
not modify its arguments, but it can optionally return a new gradient with
respect to the input that will be used in place of :attr:`grad_input` in
subsequent computations. :attr:`grad_input` will only correspond to the inputs given
as positional arguments and all kwarg arguments are ignored. Entries
in :attr:`grad_input` and :attr:`grad_output` will be ``None`` for all non-Tensor
arguments.
For technical reasons, when this hook is applied to a Module, its forward function will
receive a view of each Tensor passed to the Module. Similarly the caller will receive a view
of each Tensor returned by the Module's forward function.
.. warning ::
Modifying inputs or outputs inplace is not allowed when using backward hooks and
will raise an error.
Returns:
:class:`torch.utils.hooks.RemovableHandle`:
a handle that can be used to remove the added hook by calling
``handle.remove()``
"""
if self._is_full_backward_hook is False:
raise RuntimeError("Cannot use both regular backward hooks and full backward hooks on a "
"single Module. Please use only one of them.")
self._is_full_backward_hook = True
handle = hooks.RemovableHandle(self._backward_hooks)
self._backward_hooks[handle.id] = hook
return handle
register_parameter(self, name: str, param: Optional[torch.nn.parameter.Parameter]) -> None
inherited
¶
Adds a parameter to the module.
The parameter can be accessed as an attribute using given name.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
name |
string |
name of the parameter. The parameter can be accessed from this module using the given name |
required |
param |
Parameter or None |
parameter to be added to the module. If
|
required |
Source code in zamba/pytorch/layers.py
def register_parameter(self, name: str, param: Optional[Parameter]) -> None:
r"""Adds a parameter to the module.
The parameter can be accessed as an attribute using given name.
Args:
name (string): name of the parameter. The parameter can be accessed
from this module using the given name
param (Parameter or None): parameter to be added to the module. If
``None``, then operations that run on parameters, such as :attr:`cuda`,
are ignored. If ``None``, the parameter is **not** included in the
module's :attr:`state_dict`.
"""
if '_parameters' not in self.__dict__:
raise AttributeError(
"cannot assign parameter before Module.__init__() call")
elif not isinstance(name, torch._six.string_classes):
raise TypeError("parameter name should be a string. "
"Got {}".format(torch.typename(name)))
elif '.' in name:
raise KeyError("parameter name can't contain \".\"")
elif name == '':
raise KeyError("parameter name can't be empty string \"\"")
elif hasattr(self, name) and name not in self._parameters:
raise KeyError("attribute '{}' already exists".format(name))
if param is None:
self._parameters[name] = None
elif not isinstance(param, Parameter):
raise TypeError("cannot assign '{}' object to parameter '{}' "
"(torch.nn.Parameter or None required)"
.format(torch.typename(param), name))
elif param.grad_fn:
raise ValueError(
"Cannot assign non-leaf Tensor to parameter '{0}'. Model "
"parameters must be created explicitly. To express '{0}' "
"as a function of another Tensor, compute the value in "
"the forward() method.".format(name))
else:
self._parameters[name] = param
requires_grad_(self: ~T, requires_grad: bool = True) -> ~T
inherited
¶
Change if autograd should record operations on parameters in this module.
This method sets the parameters' :attr:requires_grad attributes
in-place.
This method is helpful for freezing part of the module for finetuning or training parts of a model individually (e.g., GAN training).
See :ref:locally-disable-grad-doc for a comparison between
.requires_grad_() and several similar mechanisms that may be confused with it.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
requires_grad |
bool |
whether autograd should record operations on
parameters in this module. Default: |
True |
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def requires_grad_(self: T, requires_grad: bool = True) -> T:
r"""Change if autograd should record operations on parameters in this
module.
This method sets the parameters' :attr:`requires_grad` attributes
in-place.
This method is helpful for freezing part of the module for finetuning
or training parts of a model individually (e.g., GAN training).
See :ref:`locally-disable-grad-doc` for a comparison between
`.requires_grad_()` and several similar mechanisms that may be confused with it.
Args:
requires_grad (bool): whether autograd should record operations on
parameters in this module. Default: ``True``.
Returns:
Module: self
"""
for p in self.parameters():
p.requires_grad_(requires_grad)
return self
set_extra_state(self, state: Any)
inherited
¶
This function is called from :func:load_state_dict to handle any extra state
found within the state_dict. Implement this function and a corresponding
:func:get_extra_state for your module if you need to store extra state within its
state_dict.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
state |
dict |
Extra state from the |
required |
Source code in zamba/pytorch/layers.py
def set_extra_state(self, state: Any):
"""
This function is called from :func:`load_state_dict` to handle any extra state
found within the `state_dict`. Implement this function and a corresponding
:func:`get_extra_state` for your module if you need to store extra state within its
`state_dict`.
Args:
state (dict): Extra state from the `state_dict`
"""
raise RuntimeError(
"Reached a code path in Module.set_extra_state() that should never be called. "
"Please file an issue at https://github.com/pytorch/pytorch/issues/new?template=bug-report.md "
"to report this bug.")
share_memory(self: ~T) -> ~T
inherited
¶
See :meth:torch.Tensor.share_memory_
Source code in zamba/pytorch/layers.py
def share_memory(self: T) -> T:
r"""See :meth:`torch.Tensor.share_memory_`"""
return self._apply(lambda t: t.share_memory_())
state_dict(self, destination = None, prefix = '', keep_vars = False)
inherited
¶
Returns a dictionary containing a whole state of the module.
Both parameters and persistent buffers (e.g. running averages) are
included. Keys are corresponding parameter and buffer names.
Parameters and buffers set to None are not included.
Returns:
| Type | Description |
|---|---|
dict |
a dictionary containing a whole state of the module |
Example::
>>> module.state_dict().keys()
['bias', 'weight']
Source code in zamba/pytorch/layers.py
def state_dict(self, destination=None, prefix='', keep_vars=False):
r"""Returns a dictionary containing a whole state of the module.
Both parameters and persistent buffers (e.g. running averages) are
included. Keys are corresponding parameter and buffer names.
Parameters and buffers set to ``None`` are not included.
Returns:
dict:
a dictionary containing a whole state of the module
Example::
>>> module.state_dict().keys()
['bias', 'weight']
"""
if destination is None:
destination = OrderedDict()
destination._metadata = OrderedDict()
destination._metadata[prefix[:-1]] = local_metadata = dict(version=self._version)
self._save_to_state_dict(destination, prefix, keep_vars)
for name, module in self._modules.items():
if module is not None:
module.state_dict(destination, prefix + name + '.', keep_vars=keep_vars)
for hook in self._state_dict_hooks.values():
hook_result = hook(self, destination, prefix, local_metadata)
if hook_result is not None:
destination = hook_result
return destination
to(self, *args, **kwargs)
inherited
¶
Moves and/or casts the parameters and buffers.
This can be called as
.. function:: to(device=None, dtype=None, non_blocking=False) :noindex:
.. function:: to(dtype, non_blocking=False) :noindex:
.. function:: to(tensor, non_blocking=False) :noindex:
.. function:: to(memory_format=torch.channels_last) :noindex:
Its signature is similar to :meth:torch.Tensor.to, but only accepts
floating point or complex :attr:dtype\ s. In addition, this method will
only cast the floating point or complex parameters and buffers to :attr:dtype
(if given). The integral parameters and buffers will be moved
:attr:device, if that is given, but with dtypes unchanged. When
:attr:non_blocking is set, it tries to convert/move asynchronously
with respect to the host if possible, e.g., moving CPU Tensors with
pinned memory to CUDA devices.
See below for examples.
.. note:: This method modifies the module in-place.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
device |
class: |
required | |
dtype |
class: |
required | |
tensor |
torch.Tensor |
Tensor whose dtype and device are the desired dtype and device for all parameters and buffers in this module |
required |
memory_format |
class: |
required |
Returns:
| Type | Description |
|---|---|
Module |
self |
Examples::
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
[-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
[-0.5113, -0.2325]], dtype=torch.float64)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
[-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
[-0.5112, -0.2324]], dtype=torch.float16)
>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j, 0.2382+0.j],
[ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
[0.6122+0.j, 0.1150+0.j],
[0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)
Source code in zamba/pytorch/layers.py
def to(self, *args, **kwargs):
r"""Moves and/or casts the parameters and buffers.
This can be called as
.. function:: to(device=None, dtype=None, non_blocking=False)
:noindex:
.. function:: to(dtype, non_blocking=False)
:noindex:
.. function:: to(tensor, non_blocking=False)
:noindex:
.. function:: to(memory_format=torch.channels_last)
:noindex:
Its signature is similar to :meth:`torch.Tensor.to`, but only accepts
floating point or complex :attr:`dtype`\ s. In addition, this method will
only cast the floating point or complex parameters and buffers to :attr:`dtype`
(if given). The integral parameters and buffers will be moved
:attr:`device`, if that is given, but with dtypes unchanged. When
:attr:`non_blocking` is set, it tries to convert/move asynchronously
with respect to the host if possible, e.g., moving CPU Tensors with
pinned memory to CUDA devices.
See below for examples.
.. note::
This method modifies the module in-place.
Args:
device (:class:`torch.device`): the desired device of the parameters
and buffers in this module
dtype (:class:`torch.dtype`): the desired floating point or complex dtype of
the parameters and buffers in this module
tensor (torch.Tensor): Tensor whose dtype and device are the desired
dtype and device for all parameters and buffers in this module
memory_format (:class:`torch.memory_format`): the desired memory
format for 4D parameters and buffers in this module (keyword
only argument)
Returns:
Module: self
Examples::
>>> linear = nn.Linear(2, 2)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
[-0.5113, -0.2325]])
>>> linear.to(torch.double)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1913, -0.3420],
[-0.5113, -0.2325]], dtype=torch.float64)
>>> gpu1 = torch.device("cuda:1")
>>> linear.to(gpu1, dtype=torch.half, non_blocking=True)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
[-0.5112, -0.2324]], dtype=torch.float16, device='cuda:1')
>>> cpu = torch.device("cpu")
>>> linear.to(cpu)
Linear(in_features=2, out_features=2, bias=True)
>>> linear.weight
Parameter containing:
tensor([[ 0.1914, -0.3420],
[-0.5112, -0.2324]], dtype=torch.float16)
>>> linear = nn.Linear(2, 2, bias=None).to(torch.cdouble)
>>> linear.weight
Parameter containing:
tensor([[ 0.3741+0.j, 0.2382+0.j],
[ 0.5593+0.j, -0.4443+0.j]], dtype=torch.complex128)
>>> linear(torch.ones(3, 2, dtype=torch.cdouble))
tensor([[0.6122+0.j, 0.1150+0.j],
[0.6122+0.j, 0.1150+0.j],
[0.6122+0.j, 0.1150+0.j]], dtype=torch.complex128)
"""
device, dtype, non_blocking, convert_to_format = torch._C._nn._parse_to(*args, **kwargs)
if dtype is not None:
if not (dtype.is_floating_point or dtype.is_complex):
raise TypeError('nn.Module.to only accepts floating point or complex '
'dtypes, but got desired dtype={}'.format(dtype))
if dtype.is_complex:
warnings.warn(
"Complex modules are a new feature under active development whose design may change, "
"and some modules might not work as expected when using complex tensors as parameters or buffers. "
"Please file an issue at https://github.com/pytorch/pytorch/issues/new?template=bug-report.md "
"if a complex module does not work as expected.")
def convert(t):
if convert_to_format is not None and t.dim() in (4, 5):
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None,
non_blocking, memory_format=convert_to_format)
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
return self._apply(convert)
to_empty(self: ~T, *, device: Union[str, torch.device]) -> ~T
inherited
¶
Moves the parameters and buffers to the specified device without copying storage.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
device |
class: |
required |
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def to_empty(self: T, *, device: Union[str, device]) -> T:
r"""Moves the parameters and buffers to the specified device without copying storage.
Args:
device (:class:`torch.device`): The desired device of the parameters
and buffers in this module.
Returns:
Module: self
"""
return self._apply(lambda t: torch.empty_like(t, device=device))
train(self: ~T, mode: bool = True) -> ~T
inherited
¶
Sets the module in training mode.
This has any effect only on certain modules. See documentations of
particular modules for details of their behaviors in training/evaluation
mode, if they are affected, e.g. :class:Dropout, :class:BatchNorm,
etc.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
mode |
bool |
whether to set training mode ( |
True |
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def train(self: T, mode: bool = True) -> T:
r"""Sets the module in training mode.
This has any effect only on certain modules. See documentations of
particular modules for details of their behaviors in training/evaluation
mode, if they are affected, e.g. :class:`Dropout`, :class:`BatchNorm`,
etc.
Args:
mode (bool): whether to set training mode (``True``) or evaluation
mode (``False``). Default: ``True``.
Returns:
Module: self
"""
if not isinstance(mode, bool):
raise ValueError("training mode is expected to be boolean")
self.training = mode
for module in self.children():
module.train(mode)
return self
type(self: ~T, dst_type: Union[torch.dtype, str]) -> ~T
inherited
¶
Casts all parameters and buffers to :attr:dst_type.
.. note:: This method modifies the module in-place.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
dst_type |
type or string |
the desired type |
required |
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def type(self: T, dst_type: Union[dtype, str]) -> T:
r"""Casts all parameters and buffers to :attr:`dst_type`.
.. note::
This method modifies the module in-place.
Args:
dst_type (type or string): the desired type
Returns:
Module: self
"""
return self._apply(lambda t: t.type(dst_type))
xpu(self: ~T, device: Union[int, torch.device] = None) -> ~T
inherited
¶
Moves all model parameters and buffers to the XPU.
This also makes associated parameters and buffers different objects. So it should be called before constructing optimizer if the module will live on XPU while being optimized.
.. note:: This method modifies the module in-place.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
device |
int |
if specified, all parameters will be copied to that device |
None |
Returns:
| Type | Description |
|---|---|
Module |
self |
Source code in zamba/pytorch/layers.py
def xpu(self: T, device: Optional[Union[int, device]] = None) -> T:
r"""Moves all model parameters and buffers to the XPU.
This also makes associated parameters and buffers different objects. So
it should be called before constructing optimizer if the module will
live on XPU while being optimized.
.. note::
This method modifies the module in-place.
Arguments:
device (int, optional): if specified, all parameters will be
copied to that device
Returns:
Module: self
"""
return self._apply(lambda t: t.xpu(device))
zero_grad(self, set_to_none: bool = False) -> None
inherited
¶
Sets gradients of all model parameters to zero. See similar function
under :class:torch.optim.Optimizer for more context.
Parameters:
| Name | Type | Description | Default |
|---|---|---|---|
set_to_none |
bool |
instead of setting to zero, set the grads to None.
See :meth: |
False |
Source code in zamba/pytorch/layers.py
def zero_grad(self, set_to_none: bool = False) -> None:
r"""Sets gradients of all model parameters to zero. See similar function
under :class:`torch.optim.Optimizer` for more context.
Args:
set_to_none (bool): instead of setting to zero, set the grads to None.
See :meth:`torch.optim.Optimizer.zero_grad` for details.
"""
if getattr(self, '_is_replica', False):
warnings.warn(
"Calling .zero_grad() from a module created with nn.DataParallel() has no effect. "
"The parameters are copied (in a differentiable manner) from the original module. "
"This means they are not leaf nodes in autograd and so don't accumulate gradients. "
"If you need gradients in your forward method, consider using autograd.grad instead.")
for p in self.parameters():
if p.grad is not None:
if set_to_none:
p.grad = None
else:
if p.grad.grad_fn is not None:
p.grad.detach_()
else:
p.grad.requires_grad_(False)
p.grad.zero_()