FM / layers

/usr/local/lib64/python3.6/site-packages/caffe2/python/layers/

/usr/local/lib64/python3.6/site-packages/caffe2/python/layers

Name	Size	Mode	Actions
__pycache__/	-	0755	rm
adaptive_weight.py	5687	0644	edit dl rm
add_bias.py	1396	0644	edit dl rm
arc_cosine_feature_map.py	7345	0644	edit dl rm
batch_huber_loss.py	3523	0644	edit dl rm
batch_lr_loss.py	11577	0644	edit dl rm
batch_mse_loss.py	2333	0644	edit dl rm
batch_normalization.py	3823	0644	edit dl rm
batch_sigmoid_cross_entropy_loss.py	1483	0644	edit dl rm
batch_softmax_loss.py	4580	0644	edit dl rm
blob_weighted_sum.py	2219	0644	edit dl rm
bpr_loss.py	1499	0644	edit dl rm
bucket_weighted.py	2355	0644	edit dl rm
build_index.py	1937	0644	edit dl rm
concat.py	4849	0644	edit dl rm
constant_weight.py	1208	0644	edit dl rm
conv.py	5050	0644	edit dl rm
dropout.py	1410	0644	edit dl rm
fc.py	9296	0644	edit dl rm
fc_without_bias.py	1954	0644	edit dl rm
fc_with_bootstrap.py	12788	0644	edit dl rm
feature_sparse_to_dense.py	14361	0644	edit dl rm
functional.py	4875	0644	edit dl rm
gather_record.py	3260	0644	edit dl rm
homotopy_weight.py	4306	0644	edit dl rm
label_smooth.py	3507	0644	edit dl rm
last_n_window_collector.py	2392	0644	edit dl rm
layers.py	17412	0644	edit dl rm
layer_normalization.py	4291	0644	edit dl rm
margin_rank_loss.py	1951	0644	edit dl rm
merge_id_lists.py	1500	0644	edit dl rm
pairwise_similarity.py	3549	0644	edit dl rm
position_weighted.py	2066	0644	edit dl rm
random_fourier_features.py	3187	0644	edit dl rm
reservoir_sampling.py	3013	0644	edit dl rm
sampling_train.py	2210	0644	edit dl rm
sampling_trainable_mixin.py	1366	0644	edit dl rm
select_record_by_context.py	2381	0644	edit dl rm
semi_random_features.py	5809	0644	edit dl rm
sparse_dropout_with_replacement.py	3943	0644	edit dl rm
sparse_feature_hash.py	4618	0644	edit dl rm
sparse_itemwise_dropout_with_replacement.py	3944	0644	edit dl rm
sparse_lookup.py	22170	0644	edit dl rm
split.py	2257	0644	edit dl rm
tags.py	4114	0644	edit dl rm
uniform_sampling.py	2779	0644	edit dl rm
__init__.py	943	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/caffe2/python/layers/random_fourier_features.py (3187B)

from caffe2.python import schema
from caffe2.python.layers.layers import ModelLayer

import numpy as np

class RandomFourierFeatures(ModelLayer):
    """
    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 -- initialization options for weight parameter
        b_init -- initialization options for bias parameter

"""
    def __init__(
            self,
            model,
            input_record,
            output_dims,
            sigma,  # bandwidth
            w_init=None,
            b_init=None,
            name='random_fourier_features',
            **kwargs):

super(RandomFourierFeatures, self).__init__(model, name, input_record,
                                                    **kwargs)
        assert isinstance(input_record, schema.Scalar), "Incorrect input type"

input_dims = input_record.field_type().shape[0]
        assert input_dims >= 1, "Expected input dimensions >= 1, got %s" \
                                % input_dims
        self.output_dims = output_dims
        assert self.output_dims >= 1, "Expected output dimensions >= 1, got %s" \
                                      % self.output_dims

self.output_schema = schema.Scalar(
            (np.float32, (self.output_dims, )),
            self.get_next_blob_reference('output')
        )

assert sigma > 0.0, "Expected bandwidth > 0, got %s" % sigma

# Initialize train_init_net parameters
        w_init = w_init if w_init else (
            'GaussianFill', {'mean': 0.0, 'std': 1.0 / sigma}
        )

b_init = b_init if b_init else (
            'UniformFill', {'min': 0.0, 'max': 2 * np.pi}
        )

self.w = self.create_param(param_name='w',
                                   shape=[self.output_dims, input_dims],
                                   initializer=w_init,
                                   optimizer=model.NoOptim)

self.b = self.create_param(param_name='b',
                                   shape=[self.output_dims],
                                   initializer=b_init,
                                   optimizer=model.NoOptim)

def add_ops(self, net):
        # Random features: wx + b
        cosine_arg = net.FC(self.input_record.field_blobs() + [self.w, self.b],
                            net.NextScopedBlob("cosine_arg"))

# Apply cosine to new vectors
        new_feature_vec = net.Cos([cosine_arg],
                                  net.NextScopedBlob('new_feature_vec'))

# Multiply each element in vector by sqrt(2/D)
        scale = np.sqrt(2.0 / self.output_dims)
        net.Scale([new_feature_vec],
                  self.output_schema.field_blobs(),
                  scale=scale)

from caffe2.python import schema from caffe2.python.layers.layers import ModelLayer import numpy as np class RandomFourierFeatures(ModelLayer): """ 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 -- initialization options for weight parameter b_init -- initialization options for bias parameter """ def __init__( self, model, input_record, output_dims, sigma, # bandwidth w_init=None, b_init=None, name='random_fourier_features', **kwargs): super(RandomFourierFeatures, self).__init__(model, name, input_record, **kwargs) assert isinstance(input_record, schema.Scalar), "Incorrect input type" input_dims = input_record.field_type().shape[0] assert input_dims >= 1, "Expected input dimensions >= 1, got %s" \ % input_dims self.output_dims = output_dims assert self.output_dims >= 1, "Expected output dimensions >= 1, got %s" \ % self.output_dims self.output_schema = schema.Scalar( (np.float32, (self.output_dims, )), self.get_next_blob_reference('output') ) assert sigma > 0.0, "Expected bandwidth > 0, got %s" % sigma # Initialize train_init_net parameters w_init = w_init if w_init else ( 'GaussianFill', {'mean': 0.0, 'std': 1.0 / sigma} ) b_init = b_init if b_init else ( 'UniformFill', {'min': 0.0, 'max': 2 * np.pi} ) self.w = self.create_param(param_name='w', shape=[self.output_dims, input_dims], initializer=w_init, optimizer=model.NoOptim) self.b = self.create_param(param_name='b', shape=[self.output_dims], initializer=b_init, optimizer=model.NoOptim) def add_ops(self, net): # Random features: wx + b cosine_arg = net.FC(self.input_record.field_blobs() + [self.w, self.b], net.NextScopedBlob("cosine_arg")) # Apply cosine to new vectors new_feature_vec = net.Cos([cosine_arg], net.NextScopedBlob('new_feature_vec')) # Multiply each element in vector by sqrt(2/D) scale = np.sqrt(2.0 / self.output_dims) net.Scale([new_feature_vec], self.output_schema.field_blobs(), scale=scale)