Convolutional GRU¶
CGRU¶
-
class
mdgru.model_pytorch.crnn.cgru.
CGRUCell
(num_input, num_units, kw)[source]¶ Bases:
mdgru.model_pytorch.crnn.CRNNCell
Convolutional gated recurrent unit.
This class processes n-d data along the last dimension using a gated recurrent unit, which uses n-1 d convolutions on its path along that last dimension to gather context from input and last state to produce the new state. Property defaults contains defaults for all properties of a CGRUCell that are the same for one MDGRU.
Parameters: kw (dict containing the following options.) – - put_r_back [default: False] Place reset gate at its original location, as in the original GRU
- use_dropconnect_on_state [default: False] Apply dropconnect regularization also to the proposal, not only the gates
- gate [default: built-in method sigmoid of type object at 0x7fc76941b980] Gate activation function to use
- start_state [default: None]
-
_all_buffers
(memo=None)¶
-
_apply
(fn)¶
-
_defaults
= {'gate': {'value': <built-in method sigmoid of type object at 0x7fc76941b980>, 'help': 'Gate activation function to use'}, 'put_r_back': {'value': False, 'help': 'Place reset gate at its original location, as in the original GRU'}, 'start_state': None, 'use_dropconnect_on_state': {'value': False, 'help': 'Apply dropconnect regularization also to the proposal, not only the gates'}}¶
-
_get_dropconnect
(t, keep_rate_training, keep_rate_testing=1)¶ Creates factors to be applied to filters to achieve either Bernoulli or Gaussian dropconnect.
-
_get_name
()¶
-
_load_from_state_dict
(state_dict, prefix, strict, missing_keys, unexpected_keys, error_msgs)¶ Copies parameters and buffers from
state_dict
into only this module, but not its descendants. This is called on every submodule inload_state_dict()
. Metadata saved for this module in inputstate_dict
is atstate_dict._metadata[prefix]
. Subclasses can achieve class-specific backward compatible loading using the version number atstate_dict._metadata[prefix]["version"]
.Note
state_dict
is not the same object as the inputstate_dict
toload_state_dict()
. So it can be modified.Parameters: - state_dict (dict) – a dict containing parameters and persistent buffers.
- prefix (str) – the prefix for parameters and buffers used in this module
- strict (bool) – whether to strictly enforce that the keys in
state_dict
withprefix
match the names of parameters and buffers in this module - missing_keys (list of str) – if
strict=False
, add missing keys to this list - unexpected_keys (list of str) – if
strict=False
, add unexpected keys to this list - error_msgs (list of str) – error messages should be added to this
list, and will be reported together in
load_state_dict()
-
_slow_forward
(*input, **kwargs)¶
-
_tracing_name
(tracing_state)¶
-
_version
= 1¶
-
add_module
(name, module)¶ Adds a child module to the current module.
The module can be accessed as an attribute using the given name.
Parameters: - name (string) – name of the child module. The child module can be accessed from this module using the given name
- parameter (Module) – child module to be added to the module.
-
apply
(fn)¶ 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 torch-nn-init).Parameters: fn ( Module
-> None) – function to be applied to each submoduleReturns: Module – self Example:
>>> def init_weights(m): print(m) if type(m) == nn.Linear: m.weight.data.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) )
-
children
()¶ Returns an iterator over immediate children modules.
Yields: Module – a child module
-
cpu
()¶ Moves all model parameters and buffers to the CPU.
Returns: Module – self
-
cuda
(device=None)¶ 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.
Parameters: device (int, optional) – if specified, all parameters will be copied to that device Returns: Module – self
-
double
()¶ Casts all floating point parameters and buffers to
double
datatype.Returns: Module – self
-
dump_patches
= False¶
-
eval
()¶ 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.
Dropout
,BatchNorm
, etc.
-
extra_repr
()¶ Set the extra representation of the module
To print customized extra information, you should reimplement this method in your own modules. Both single-line and multi-line strings are acceptable.
-
float
()¶ Casts all floating point parameters and buffers to float datatype.
Returns: Module – self
-
half
()¶ Casts all floating point parameters and buffers to
half
datatype.Returns: Module – self
-
load_state_dict
(state_dict, strict=True)¶ Copies parameters and buffers from
state_dict
into this module and its descendants. Ifstrict
isTrue
, then the keys ofstate_dict
must exactly match the keys returned by this module’sstate_dict()
function.Parameters:
-
modules
()¶ 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 (2 -> 2) (1): Linear (2 -> 2) ) 1 -> Linear (2 -> 2)
-
named_children
()¶ 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)
-
named_modules
(memo=None, prefix='')¶ Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
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 (2 -> 2) (1): Linear (2 -> 2) )) 1 -> ('0', Linear (2 -> 2))
-
named_parameters
(memo=None, prefix='')¶ Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself
Yields: (string, Parameter) – Tuple containing the name and parameter Example:
>>> for name, param in self.named_parameters(): >>> if name in ['bias']: >>> print(param.size())
-
output_size
¶
-
parameters
()¶ Returns an iterator over module parameters.
This is typically passed to an optimizer.
Yields: Parameter – module parameter Example:
>>> for param in model.parameters(): >>> print(type(param.data), param.size()) <class 'torch.FloatTensor'> (20L,) <class 'torch.FloatTensor'> (20L, 1L, 5L, 5L)
-
register_backward_hook
(hook)¶ 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) -> Tensor or None
The
grad_input
andgrad_output
may be tuples if the module has multiple inputs or outputs. The hook should not modify its arguments, but it can optionally return a new gradient with respect to input that will be used in place ofgrad_input
in subsequent computations.Returns: torch.utils.hooks.RemovableHandle
– a handle that can be used to remove the added hook by callinghandle.remove()
-
register_buffer
(name, tensor)¶ Adds a persistent 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 persistent state.Buffers can be accessed as attributes using given names.
Parameters: - name (string) – name of the buffer. The buffer can be accessed from this module using the given name
- tensor (Tensor) – buffer to be registered.
Example:
>>> self.register_buffer('running_mean', torch.zeros(num_features))
-
register_forward_hook
(hook)¶ Registers a forward hook on the module.
The hook will be called every time after
forward()
has computed an output. It should have the following signature:hook(module, input, output) -> None
The hook should not modify the input or output.
Returns: torch.utils.hooks.RemovableHandle
– a handle that can be used to remove the added hook by callinghandle.remove()
-
register_forward_pre_hook
(hook)¶ Registers a forward pre-hook on the module.
The hook will be called every time before
forward()
is invoked. It should have the following signature:hook(module, input) -> None
The hook should not modify the input.
Returns: torch.utils.hooks.RemovableHandle
– a handle that can be used to remove the added hook by callinghandle.remove()
-
register_parameter
(name, param)¶ Adds a parameter to the module.
The parameter can be accessed as an attribute using given name.
Parameters: - name (string) – name of the parameter. The parameter can be accessed from this module using the given name
- parameter (Parameter) – parameter to be added to the module.
-
state_dict
(destination=None, prefix='', keep_vars=False)¶ 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.
Returns: dict – a dictionary containing a whole state of the module Example:
>>> module.state_dict().keys() ['bias', 'weight']
-
state_size
¶
-
to
(*args, **kwargs)¶ Moves and/or casts the parameters and buffers.
This can be called as
-
to
(device)
-
to
(dtype)
-
to
(device, dtype)
It has similar signature as
torch.Tensor.to()
, but does not take a Tensor and only takes in floating pointdtype
s. In particular, this method will only cast the floating point parameters and buffers todtype
. It will still move the integral parameters and buffers todevice
, if that is given. See below for examples.Note
This method modifies the module in-place.
Parameters: - device (
torch.device
) – the desired device of the parameters and buffers in this module - dtype (
torch.dtype
) – the desired floating point type of the floating point parameters and buffers in this module
Returns: Module – self
Example:
>>> 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) 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)
-
-
train
(mode=True)¶ 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.
Dropout
,BatchNorm
, etc.Returns: Module – self
-
type
(dst_type)¶ Casts all parameters and buffers to
dst_type
.Parameters: dst_type (type or string) – the desired type Returns: Module – self
-
zero_grad
()¶ Sets gradients of all model parameters to zero.
Module contents¶
-
class
mdgru.model_pytorch.crnn.
CRNNCell
(num_input, num_units, kw)[source]¶ Bases:
torch.nn.modules.module.Module
Base convolutional RNN method, implements common functions and serves as abstract class.
Property defaults contains default values for all properties of a CGRUCell that are the same for one MDGRU and is used to filter valid arguments.
Parameters: - kw (dict containing the following options.) –
- periodic_convolution_x [default: False]
- periodic_convolution_h [default: False]
- use_bernoulli [default: False]
- dropconnectx [default: None]
- dropconnecth [default: None]
- crnn_activation [default: built-in method tanh of type object at 0x7fc76941b980]
- num_input (number of input channels.) –
- num_units (Defines number of output channels.) –
- filter_size_x (Defines shape of filter kernel applied to input) –
- filter_size_h (Defines shape of filter kernel applied to state) –
- strides (Defines strides to be applied when filtering input (not yet implemented here)) –
-
_all_buffers
(memo=None)¶
-
_apply
(fn)¶
-
_defaults
= {'crnn_activation': <built-in method tanh of type object at 0x7fc76941b980>, 'dropconnecth': None, 'dropconnectx': None, 'periodic_convolution_h': False, 'periodic_convolution_x': False, 'use_bernoulli': False}¶
-
_get_dropconnect
(t, keep_rate_training, keep_rate_testing=1)[source]¶ Creates factors to be applied to filters to achieve either Bernoulli or Gaussian dropconnect.
-
_get_name
()¶
-
_load_from_state_dict
(state_dict, prefix, strict, missing_keys, unexpected_keys, error_msgs)¶ Copies parameters and buffers from
state_dict
into only this module, but not its descendants. This is called on every submodule inload_state_dict()
. Metadata saved for this module in inputstate_dict
is atstate_dict._metadata[prefix]
. Subclasses can achieve class-specific backward compatible loading using the version number atstate_dict._metadata[prefix]["version"]
.Note
state_dict
is not the same object as the inputstate_dict
toload_state_dict()
. So it can be modified.Parameters: - state_dict (dict) – a dict containing parameters and persistent buffers.
- prefix (str) – the prefix for parameters and buffers used in this module
- strict (bool) – whether to strictly enforce that the keys in
state_dict
withprefix
match the names of parameters and buffers in this module - missing_keys (list of str) – if
strict=False
, add missing keys to this list - unexpected_keys (list of str) – if
strict=False
, add unexpected keys to this list - error_msgs (list of str) – error messages should be added to this
list, and will be reported together in
load_state_dict()
-
_slow_forward
(*input, **kwargs)¶
-
_tracing_name
(tracing_state)¶
-
_version
= 1¶
-
add_module
(name, module)¶ Adds a child module to the current module.
The module can be accessed as an attribute using the given name.
Parameters: - name (string) – name of the child module. The child module can be accessed from this module using the given name
- parameter (Module) – child module to be added to the module.
-
apply
(fn)¶ 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 torch-nn-init).Parameters: fn ( Module
-> None) – function to be applied to each submoduleReturns: Module – self Example:
>>> def init_weights(m): print(m) if type(m) == nn.Linear: m.weight.data.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) )
-
children
()¶ Returns an iterator over immediate children modules.
Yields: Module – a child module
-
cpu
()¶ Moves all model parameters and buffers to the CPU.
Returns: Module – self
-
cuda
(device=None)¶ 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.
Parameters: device (int, optional) – if specified, all parameters will be copied to that device Returns: Module – self
-
double
()¶ Casts all floating point parameters and buffers to
double
datatype.Returns: Module – self
-
dump_patches
= False¶
-
eval
()¶ 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.
Dropout
,BatchNorm
, etc.
-
extra_repr
()¶ Set the extra representation of the module
To print customized extra information, you should reimplement this method in your own modules. Both single-line and multi-line strings are acceptable.
-
float
()¶ Casts all floating point parameters and buffers to float datatype.
Returns: Module – self
-
forward
(*input)¶ Defines the computation performed at every call.
Should be overridden by all subclasses.
Note
Although the recipe for forward pass needs to be defined within this function, one should call the
Module
instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.
-
half
()¶ Casts all floating point parameters and buffers to
half
datatype.Returns: Module – self
-
load_state_dict
(state_dict, strict=True)¶ Copies parameters and buffers from
state_dict
into this module and its descendants. Ifstrict
isTrue
, then the keys ofstate_dict
must exactly match the keys returned by this module’sstate_dict()
function.Parameters:
-
modules
()¶ 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 (2 -> 2) (1): Linear (2 -> 2) ) 1 -> Linear (2 -> 2)
-
named_children
()¶ 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)
-
named_modules
(memo=None, prefix='')¶ Returns an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
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 (2 -> 2) (1): Linear (2 -> 2) )) 1 -> ('0', Linear (2 -> 2))
-
named_parameters
(memo=None, prefix='')¶ Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself
Yields: (string, Parameter) – Tuple containing the name and parameter Example:
>>> for name, param in self.named_parameters(): >>> if name in ['bias']: >>> print(param.size())
-
output_size
¶
-
parameters
()¶ Returns an iterator over module parameters.
This is typically passed to an optimizer.
Yields: Parameter – module parameter Example:
>>> for param in model.parameters(): >>> print(type(param.data), param.size()) <class 'torch.FloatTensor'> (20L,) <class 'torch.FloatTensor'> (20L, 1L, 5L, 5L)
-
register_backward_hook
(hook)¶ 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) -> Tensor or None
The
grad_input
andgrad_output
may be tuples if the module has multiple inputs or outputs. The hook should not modify its arguments, but it can optionally return a new gradient with respect to input that will be used in place ofgrad_input
in subsequent computations.Returns: torch.utils.hooks.RemovableHandle
– a handle that can be used to remove the added hook by callinghandle.remove()
-
register_buffer
(name, tensor)¶ Adds a persistent 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 persistent state.Buffers can be accessed as attributes using given names.
Parameters: - name (string) – name of the buffer. The buffer can be accessed from this module using the given name
- tensor (Tensor) – buffer to be registered.
Example:
>>> self.register_buffer('running_mean', torch.zeros(num_features))
-
register_forward_hook
(hook)¶ Registers a forward hook on the module.
The hook will be called every time after
forward()
has computed an output. It should have the following signature:hook(module, input, output) -> None
The hook should not modify the input or output.
Returns: torch.utils.hooks.RemovableHandle
– a handle that can be used to remove the added hook by callinghandle.remove()
-
register_forward_pre_hook
(hook)¶ Registers a forward pre-hook on the module.
The hook will be called every time before
forward()
is invoked. It should have the following signature:hook(module, input) -> None
The hook should not modify the input.
Returns: torch.utils.hooks.RemovableHandle
– a handle that can be used to remove the added hook by callinghandle.remove()
-
register_parameter
(name, param)¶ Adds a parameter to the module.
The parameter can be accessed as an attribute using given name.
Parameters: - name (string) – name of the parameter. The parameter can be accessed from this module using the given name
- parameter (Parameter) – parameter to be added to the module.
-
state_dict
(destination=None, prefix='', keep_vars=False)¶ 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.
Returns: dict – a dictionary containing a whole state of the module Example:
>>> module.state_dict().keys() ['bias', 'weight']
-
state_size
¶
-
to
(*args, **kwargs)¶ Moves and/or casts the parameters and buffers.
This can be called as
-
to
(device)
-
to
(dtype)
-
to
(device, dtype)
It has similar signature as
torch.Tensor.to()
, but does not take a Tensor and only takes in floating pointdtype
s. In particular, this method will only cast the floating point parameters and buffers todtype
. It will still move the integral parameters and buffers todevice
, if that is given. See below for examples.Note
This method modifies the module in-place.
Parameters: - device (
torch.device
) – the desired device of the parameters and buffers in this module - dtype (
torch.dtype
) – the desired floating point type of the floating point parameters and buffers in this module
Returns: Module – self
Example:
>>> 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) 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)
-
-
train
(mode=True)¶ 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.
Dropout
,BatchNorm
, etc.Returns: Module – self
-
type
(dst_type)¶ Casts all parameters and buffers to
dst_type
.Parameters: dst_type (type or string) – the desired type Returns: Module – self
-
zero_grad
()¶ Sets gradients of all model parameters to zero.
- kw (dict containing the following options.) –