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/blob_weighted_sum.py (2219B)

## @package BlobWeightedSum
# Module caffe2.python.layers.blob_weighted_sum

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

class BlobWeightedSum(ModelLayer):
    """
    This layer implements the weighted sum:
    weighted element-wise sum of input blobs.
    """
    def __init__(
        self,
        model,
        input_record,
        init_weights=None,
        weight_optim=None,
        name='blob_weighted_sum',
        **kwargs
    ):
        super(BlobWeightedSum, self).__init__(model, name, input_record, **kwargs)

self.blobs = self.input_record.field_blobs()

self.num_weights = len(self.blobs)
        assert self.num_weights > 1, (
            "BlobWeightedSum expects more than one input blobs"
        )

assert len(input_record.field_types()[0].shape) > 0, (
            "BlobWeightedSum expects limited dimensions of the input tensor"
        )

assert all(
            input_record.field_types()[0].shape == input_record.field_types()[i].shape
            for i in range(1, self.num_weights)
        ), "Shape of input blobs should be the same shape {}".format(
            input_record.field_types()[0].shape
        )

if init_weights:
            assert self.num_weights == len(init_weights), (
                "the size of init_weights should be the same as input blobs, "
                "expects {}, got {}".format(self.num_weights, len(init_weights))
            )
        else:
            init_weights = [1.0] * self.num_weights

self.weights = [
            self.create_param(
                param_name="w_{}".format(idx),
                shape=[1],
                initializer=('ConstantFill', {'value': float(init_weights[idx])}),
                optimizer=weight_optim
            ) for idx in range(self.num_weights)
        ]

self.output_schema = schema.Scalar(
            input_record.field_types()[0],
            self.get_next_blob_reference('blob_weighted_sum_out')
        )

def add_ops(self, net):
        net.WeightedSum(
            [x for pair in zip(self.blobs, self.weights) for x in pair],
            self.output_schema(),
            grad_on_w=True,
        )

## @package BlobWeightedSum # Module caffe2.python.layers.blob_weighted_sum from caffe2.python import schema from caffe2.python.layers.layers import ModelLayer class BlobWeightedSum(ModelLayer): """ This layer implements the weighted sum: weighted element-wise sum of input blobs. """ def __init__( self, model, input_record, init_weights=None, weight_optim=None, name='blob_weighted_sum', **kwargs ): super(BlobWeightedSum, self).__init__(model, name, input_record, **kwargs) self.blobs = self.input_record.field_blobs() self.num_weights = len(self.blobs) assert self.num_weights > 1, ( "BlobWeightedSum expects more than one input blobs" ) assert len(input_record.field_types()[0].shape) > 0, ( "BlobWeightedSum expects limited dimensions of the input tensor" ) assert all( input_record.field_types()[0].shape == input_record.field_types()[i].shape for i in range(1, self.num_weights) ), "Shape of input blobs should be the same shape {}".format( input_record.field_types()[0].shape ) if init_weights: assert self.num_weights == len(init_weights), ( "the size of init_weights should be the same as input blobs, " "expects {}, got {}".format(self.num_weights, len(init_weights)) ) else: init_weights = [1.0] * self.num_weights self.weights = [ self.create_param( param_name="w_{}".format(idx), shape=[1], initializer=('ConstantFill', {'value': float(init_weights[idx])}), optimizer=weight_optim ) for idx in range(self.num_weights) ] self.output_schema = schema.Scalar( input_record.field_types()[0], self.get_next_blob_reference('blob_weighted_sum_out') ) def add_ops(self, net): net.WeightedSum( [x for pair in zip(self.blobs, self.weights) for x in pair], self.output_schema(), grad_on_w=True, )