neon.layers.container.MergeSum

class neon.layers.container.MergeSum(layers, name=None)[source]

Bases: neon.layers.container.Broadcast

__init__(layers, name=None)[source]

Methods

__init__(layers[, name])
accumulates(f) Higher order decorator function that enables accumulation functionality for that function.
allocate([shared_outputs]) Allocate output buffer to store activations from fprop.
allocate_deltas(global_deltas)
bprop(error[, alpha, beta]) Apply the backward pass transformation to the input data.
configure(in_obj) Sets shape based parameters of this layer given an input tuple or int
fprop(inputs[, inference]) Apply the forward pass transformation to the input data.
fusion_pass(layers) Groups patterns together in list.
gen_class(pdict)
get_description([get_weights, keep_states]) Get layer parameters.
get_is_mklop() is_mklop true means this op is on mkl backend
get_param_attrs()
get_terminal() Used for recursively getting final nodes from layer containers.
layers_bprop() Generator to iterator over the layers in the same
layers_fprop() Generator to iterator over the layers in the same
load_weights(pdict[, load_states]) Load weights.
nested_str([level]) Utility function for displaying layer info with a given indentation level.
propagate_parallelism(p)
recursive_gen(pdict, key) helper method to check whether the definition
revert_tensors()
serialize() Get state parameters for this layer.
set_acc_on(acc_on) Set the acc_on flag according to bool argument for each layer.
set_batch_size(N) Set minibatch size.
set_deltas(delta_buffers) Use pre-allocated (by layer containers) list of buffers for backpropagated error.
set_is_mklop()
set_next(layer) Set next_layer to provided layer.
set_not_mklop()
set_params(pdict)
set_seq_len(S) Set sequence length.
set_states(pdict)
accumulates(f)

Higher order decorator function that enables accumulation functionality for that function. Object that use this decorator are required to have an acc_param attribute. This attribute tuple declares the names for existing temp parameter and real parameter buffers. The temp parameter buffer copies the value of the parameter buffer before f is called, and after f is called the temp and normal buffers are summed. This decorator could be used to wrap any function that may want to accumulate parameters instead of overwriting.

allocate(shared_outputs=None)[source]

Allocate output buffer to store activations from fprop.

Parameters:shared_outputs (Tensor, optional) – pre-allocated tensor for activations to be computed into
allocate_deltas(global_deltas)
be = None
bprop(error, alpha=1.0, beta=0.0)[source]

Apply the backward pass transformation to the input data.

Parameters:
  • error (Tensor) – deltas back propagated from the adjacent higher layer
  • alpha (float, optional) – scale to apply to input for activation gradient bprop. Defaults to 1.0
  • beta (float, optional) – scale to apply to output activation gradient bprop. Defaults to 0.0
Returns:

deltas to propagate to the adjacent lower layer

Return type:

Tensor

classnm

Returns the class name.

configure(in_obj)

Sets shape based parameters of this layer given an input tuple or int or input layer

Parameters:in_obj (int, tuple, Layer or Tensor or dataset) – object that provides shape information for layer
Returns:shape of output data
Return type:(tuple)
fprop(inputs, inference=False)[source]

Apply the forward pass transformation to the input data.

Parameters:inputs (Tensor) – input data
Returns:output data
Return type:Tensor
fusion_pass(layers)

Groups patterns together in list. If pattern is [a, b], will transform [a, b, c, d, a, b, e] -> [[a, b], c, d, [a, b], e]. Support for multiple patterns.

gen_class(pdict)
get_description(get_weights=False, keep_states=False)

Get layer parameters. All parameters are needed for optimization, but only weights are serialized.

Parameters:
  • get_weights (bool, optional) – Control whether all parameters are returned or just weights for serialization.
  • keep_states (bool, optional) – Control whether all parameters are returned or just weights for serialization.
get_is_mklop()

is_mklop true means this op is on mkl backend and may require convert when from non-mkl op

get_param_attrs()
get_terminal()

Used for recursively getting final nodes from layer containers.

layers_bprop()

Generator to iterator over the layers in the same order as bprop

layers_fprop()

Generator to iterator over the layers in the same order as fprop

layers_to_optimize
load_weights(pdict, load_states=True)

Load weights.

Parameters:
  • pdict
  • load_states – (Default value = True)

Returns:

modulenm

Returns the full module path.

nest_deltas
nested_str(level=0)

Utility function for displaying layer info with a given indentation level.

Parameters:level (int, optional) – indentation level
Returns:layer info at the given indentation level
Return type:str
propagate_parallelism(p)
recursive_gen(pdict, key)

helper method to check whether the definition dictionary is defining a NervanaObject child, if so it will instantiate that object and replace the dictionary element with an instance of that object

revert_tensors()
serialize()

Get state parameters for this layer.

Returns:whatever data this model wants to receive in order to restore state
Return type:varies
set_acc_on(acc_on)

Set the acc_on flag according to bool argument for each layer. If a layer in the container does not support accumulate_updates it will be skipped.

Parameters:acc_on (bool) – Value to set the acc_on flag of supported layers to.
set_batch_size(N)

Set minibatch size.

Parameters:N (int) – minibatch size
set_deltas(delta_buffers)

Use pre-allocated (by layer containers) list of buffers for backpropagated error. Only set deltas for layers that own their own deltas Only allocate space if layer owns its own deltas (e.g., bias and activation work in-place, so do not own their deltas).

Parameters:delta_buffers (DeltasTree) – list of pre-allocated tensors (provided by layer container)
set_is_mklop()
set_next(layer)

Set next_layer to provided layer.

Parameters:layer (layer) – Next layer
set_not_mklop()
set_params(pdict)
set_seq_len(S)

Set sequence length.

Parameters:S (int) – sequence length
set_states(pdict)