spynnaker.pyNN.models.neuron.local_only package¶
Module contents¶
- class spynnaker.pyNN.models.neuron.local_only.AbstractLocalOnly¶
Bases:
AbstractSynapseDynamics
Processes synapses locally without the need for SDRAM.
- property absolute_max_atoms_per_core¶
The absolute maximum number of atoms per core supported by this synapse dynamics object.
- Return type:
- abstract get_parameters_usage_in_bytes(n_atoms, incoming_projections)[source]¶
Get the size of the parameters in bytes.
- Parameters:
n_atoms (int) – The number of atoms in the vertex
incoming_projections (list(Projection)) – The projections to get the size of
- Return type:
- property is_combined_core_capable¶
Whether the synapse dynamics can run on a core combined with the neuron, or if a separate core is needed.
- Return type:
- abstract write_parameters(spec, region, machine_vertex, weight_scales)[source]¶
Write the parameters to the spec.
- Parameters:
spec (DataSpecificationGenerator) – The specification to write to
region (int) – region ID to write to
machine_vertex (MachineVertex) – The machine vertex being targeted
weight_scales (list(float)) – Scale factors to apply to the weights
- class spynnaker.pyNN.models.neuron.local_only.LocalOnlyConvolution(delay=None)¶
Bases:
AbstractLocalOnly
,AbstractSupportsSignedWeights
A convolution synapse dynamics that can process spikes with only DTCM.
- Parameters:
delay (float) – The delay used in the connection; by default 1 time step
- get_maximum_positive_weight(incoming_projection)[source]¶
Get the maximum likely positive weight.
Note
This must be a value >= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_mean_negative_weight(incoming_projection)[source]¶
Get the mean of the negative weights.
Note
This must be a value <= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_mean_positive_weight(incoming_projection)[source]¶
Get the mean of the positive weights.
Note
This must be a value >= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_minimum_negative_weight(incoming_projection)[source]¶
Get the minimum likely negative weight.
Note
This must be a value <= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_negative_synapse_index(incoming_projection)[source]¶
Get the synapse type that negative weights will arrive at.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_parameters_usage_in_bytes(n_atoms, incoming_projections)[source]¶
Get the size of the parameters in bytes.
- Parameters:
n_atoms (int) – The number of atoms in the vertex
incoming_projections (list(Projection)) – The projections to get the size of
- Return type:
- get_positive_synapse_index(incoming_projection)[source]¶
Get the synapse type that positive weights will arrive at.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_variance_negative_weight(incoming_projection)[source]¶
Get the variance of the negative weights.
Note
This must be a value <= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_variance_positive_weight(incoming_projection)[source]¶
Get the variance of the positive weights.
Note
This must be a value >= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_vertex_executable_suffix()[source]¶
Get the executable suffix for a vertex for this dynamics.
- Return type:
- merge(synapse_dynamics)[source]¶
Merge with the given synapse_dynamics and return the result, or error if merge is not possible.
- Parameters:
synapse_dynamics (AbstractSynapseDynamics) –
- Return type:
- write_parameters(spec, region, machine_vertex, weight_scales)[source]¶
Write the parameters to the spec.
- Parameters:
spec (DataSpecificationGenerator) – The specification to write to
region (int) – region ID to write to
machine_vertex (MachineVertex) – The machine vertex being targeted
weight_scales (list(float)) – Scale factors to apply to the weights
- class spynnaker.pyNN.models.neuron.local_only.LocalOnlyPoolDense(delay=None)¶
Bases:
AbstractLocalOnly
,AbstractSupportsSignedWeights
A convolution synapse dynamics that can process spikes with only DTCM.
- Parameters:
delay (float) – The delay used in the connection; by default 1 time step
- get_maximum_positive_weight(incoming_projection)[source]¶
Get the maximum likely positive weight.
Note
This must be a value >= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_mean_negative_weight(incoming_projection)[source]¶
Get the mean of the negative weights.
Note
This must be a value <= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_mean_positive_weight(incoming_projection)[source]¶
Get the mean of the positive weights.
Note
This must be a value >= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_minimum_negative_weight(incoming_projection)[source]¶
Get the minimum likely negative weight.
Note
This must be a value <= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_negative_synapse_index(incoming_projection)[source]¶
Get the synapse type that negative weights will arrive at.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_parameters_usage_in_bytes(n_atoms, incoming_projections)[source]¶
Get the size of the parameters in bytes.
- Parameters:
n_atoms (int) – The number of atoms in the vertex
incoming_projections (list(Projection)) – The projections to get the size of
- Return type:
- get_positive_synapse_index(incoming_projection)[source]¶
Get the synapse type that positive weights will arrive at.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_variance_negative_weight(incoming_projection)[source]¶
Get the variance of the negative weights.
Note
This must be a value <= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_variance_positive_weight(incoming_projection)[source]¶
Get the variance of the positive weights.
Note
This must be a value >= 0.
- Parameters:
incoming_projection (Projection) – The projection targeted
- Return type:
- get_vertex_executable_suffix()[source]¶
Get the executable suffix for a vertex for this dynamics.
- Return type:
- merge(synapse_dynamics)[source]¶
Merge with the given synapse_dynamics and return the result, or error if merge is not possible.
- Parameters:
synapse_dynamics (AbstractSynapseDynamics) –
- Return type:
- write_parameters(spec, region, machine_vertex, weight_scales)[source]¶
Write the parameters to the spec.
- Parameters:
spec (DataSpecificationGenerator) – The specification to write to
region (int) – region ID to write to
machine_vertex (MachineVertex) – The machine vertex being targeted
weight_scales (list(float)) – Scale factors to apply to the weights