 |
Caffe2 - Python API
A deep learning, cross platform ML framework
|
|
Caffe2 - Python API
A deep learning, cross platform ML framework
|
Public Member Functions | |
| def | __init__ (self, model, input_record, output_dims, s=1, scale_random=1.0, scale_learned=1.0, weight_init_random=None, bias_init_random=None, weight_init_learned=None, bias_init_learned=None, weight_optim=None, bias_optim=None, set_weight_as_global_constant=False, name='semi_random_features', kwargs) |
| def | add_ops (self, net) |
 Public Member Functions inherited from caffe2.python.layers.arc_cosine_feature_map.ArcCosineFeatureMap | |
| def | __init__ (self, model, input_record, output_dims, s=1, scale=1.0, weight_init=None, bias_init=None, weight_optim=None, bias_optim=None, set_weight_as_global_constant=False, initialize_output_schema=True, name='arc_cosine_feature_map', kwargs) |
| def | add_ops (self, net) |
| Public Member Functions inherited from caffe2.python.layers.layers.ModelLayer | |
| def | __init__ (self, model, prefix, input_record, predict_input_record_fields=None, tags=None, kwargs) |
| def | get_type (self) |
| def | predict_input_record (self) |
| def | input_record (self) |
| def | predict_output_schema (self) |
| def | predict_output_schema (self, output_schema) |
| def | output_schema (self) |
| def | output_schema (self, output_schema) |
| def | get_parameters (self) |
| def | get_fp16_compatible_parameters (self) |
| def | get_memory_usage (self) |
| def | add_init_params (self, init_net) |
| def | create_param (self, param_name, shape, initializer, optimizer, ps_param=None, regularizer=None) |
| def | get_next_blob_reference (self, name) |
| def | add_operators (self, net, init_net=None, context=InstantiationContext.TRAINING) |
| def | add_ops (self, net) |
| def | add_eval_ops (self, net) |
| def | add_train_ops (self, net) |
| def | add_ops_to_accumulate_pred (self, net) |
| def | add_param_copy_operators (self, net) |
| def | export_output_for_metrics (self) |
| def | export_params_for_metrics (self) |
Public Attributes | |
| input_record_full | |
| input_record_random | |
| output_schema | |
| stddev | |
| Public Attributes inherited from caffe2.python.layers.arc_cosine_feature_map.ArcCosineFeatureMap | |
| params | |
| model | |
| set_weight_as_global_constant | |
| input_dims | |
| output_schema | |
| output_dims | |
| s | |
| stddev | |
| random_w | |
| random_b | |
| Public Attributes inherited from caffe2.python.layers.layers.ModelLayer | |
| name | |
| model | |
| kwargs | |
| request_only | |
| precomputation_request_only | |
| precomputation_object_only | |
| eval_output_schema | |
| tags | |
| params | |
Implementation of the semi-random kernel feature map.
Applies H(x_rand) * x_rand^s * x_learned, where
H is the Heaviside step function,
x_rand is the input after applying FC with randomized parameters,
and x_learned is the input after applying FC with learnable parameters.
If using multilayer model with semi-random layers, then input and output records
should have a 'full' and 'random' Scalar. The random Scalar will be passed as
input to process the random features.
For more information, see the original paper:
https://arxiv.org/pdf/1702.08882.pdf
Inputs :
output_dims -- dimensions of the output vector
s -- if s == 0, will obtain linear semi-random features;
else if s == 1, will obtain squared semi-random features;
else s >= 2, will obtain higher order semi-random features
scale_random -- amount to scale the standard deviation
(for random parameter initialization when weight_init or
bias_init hasn't been specified)
scale_learned -- amount to scale the standard deviation
(for learned parameter initialization when weight_init or
bias_init hasn't been specified)
weight_init_random -- initialization distribution for random weight parameter
(if None, will use Gaussian distribution)
bias_init_random -- initialization distribution for random bias pararmeter
(if None, will use Uniform distribution)
weight_init_learned -- initialization distribution for learned weight parameter
(if None, will use Gaussian distribution)
bias_init_learned -- initialization distribution for learned bias pararmeter
(if None, will use Uniform distribution)
weight_optim -- optimizer for weight params for learned features
bias_optim -- optimizer for bias param for learned features
set_weight_as_global_constant -- if True, initialized random parameters
will be constant across all distributed
instances of the layer
Definition at line 11 of file semi_random_features.py.
1.8.11