 |
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, sigma, w_init=None, b_init=None, name='random_fourier_features', 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 | |
| output_dims | |
| output_schema | |
| w | |
| 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 random fourier feature map for feature processing.
Applies sqrt(2 / output_dims) * cos(wx+b), where:
output_dims is the output feature dimensions, and
wx + b applies FC using randomized, fixed weight and bias parameters
For more information, see the original paper:
https://people.eecs.berkeley.edu/~brecht/papers/07.rah.rec.nips.pdf
Inputs:
output_dims -- output feature dimensions
sigma -- bandwidth for the Gaussian kernel estimator
w_init -- initalization options for weight parameter
b_init -- initalization options for bias parameter
Definition at line 12 of file random_fourier_features.py.
1.8.11