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/pairwise_similarity.py (3549B)

## @package dot_product
# Module caffe2.python.layers.dot_product

from caffe2.python import schema
from caffe2.python.layers.layers import (
    ModelLayer,
)

class PairwiseSimilarity(ModelLayer):

def __init__(self, model, input_record, output_dim, pairwise_similarity_func='dot',
                 name='pairwise_similarity', **kwargs):
        super(PairwiseSimilarity, self).__init__(model, name, input_record, **kwargs)
        assert isinstance(input_record, schema.Struct), (
            "Incorrect input type. Expected Struct, but received: {0}".
            format(input_record))
        assert (
            ('all_embeddings' in input_record) ^
            ('x_embeddings' in input_record and 'y_embeddings' in input_record)
        ), (
            "either (all_embeddings) xor (x_embeddings and y_embeddings) " +
            "should be given."
        )
        self.pairwise_similarity_func = pairwise_similarity_func
        if 'all_embeddings' in input_record:
            x_embeddings = input_record['all_embeddings']
            y_embeddings = input_record['all_embeddings']
        else:
            x_embeddings = input_record['x_embeddings']
            y_embeddings = input_record['y_embeddings']

assert isinstance(x_embeddings, schema.Scalar), (
            "Incorrect input type for x. Expected Scalar, " +
            "but received: {0}".format(x_embeddings))
        assert isinstance(y_embeddings, schema.Scalar), (
            "Incorrect input type for y. Expected Scalar, " +
            "but received: {0}".format(y_embeddings)
        )

if 'indices_to_gather' in input_record:
            indices_to_gather = input_record['indices_to_gather']
            assert isinstance(indices_to_gather, schema.Scalar), (
                "Incorrect type of indices_to_gather. "
                "Expected Scalar, but received: {0}".format(indices_to_gather)
            )
            self.indices_to_gather = indices_to_gather
        else:
            self.indices_to_gather = None

self.x_embeddings = x_embeddings
        self.y_embeddings = y_embeddings

dtype = x_embeddings.field_types()[0].base

self.output_schema = schema.Scalar(
            (dtype, (output_dim,)),
            self.get_next_blob_reference('output')
        )

def add_ops(self, net):
        if self.pairwise_similarity_func == "cosine_similarity":
            x_embeddings_norm = net.Normalize(self.x_embeddings(), axis=1)
            y_embeddings_norm = net.Normalize(self.y_embeddings(), axis=1)
            Y = net.BatchMatMul(
                [x_embeddings_norm, y_embeddings_norm],
                [self.get_next_blob_reference(x_embeddings_norm + '_matmul')],
                trans_b=1,
            )
        elif self.pairwise_similarity_func == "dot":
            Y = net.BatchMatMul(
                [self.x_embeddings(), self.y_embeddings()],
                [self.get_next_blob_reference(self.x_embeddings() + '_matmul')],
                trans_b=1,
            )
        else:
            raise NotImplementedError(
                "pairwise_similarity_func={} is not valid".format(
                    self.pairwise_similarity_func
                )
            )

if self.indices_to_gather:
            flattened = net.Flatten(
                Y, Y + '_flatten',
            )
            net.BatchGather(
                [flattened, self.indices_to_gather()],
                self.output_schema(),
            )
        else:
            net.Flatten(Y, self.output_schema())

## @package dot_product # Module caffe2.python.layers.dot_product from caffe2.python import schema from caffe2.python.layers.layers import ( ModelLayer, ) class PairwiseSimilarity(ModelLayer): def __init__(self, model, input_record, output_dim, pairwise_similarity_func='dot', name='pairwise_similarity', **kwargs): super(PairwiseSimilarity, self).__init__(model, name, input_record, **kwargs) assert isinstance(input_record, schema.Struct), ( "Incorrect input type. Expected Struct, but received: {0}". format(input_record)) assert ( ('all_embeddings' in input_record) ^ ('x_embeddings' in input_record and 'y_embeddings' in input_record) ), ( "either (all_embeddings) xor (x_embeddings and y_embeddings) " + "should be given." ) self.pairwise_similarity_func = pairwise_similarity_func if 'all_embeddings' in input_record: x_embeddings = input_record['all_embeddings'] y_embeddings = input_record['all_embeddings'] else: x_embeddings = input_record['x_embeddings'] y_embeddings = input_record['y_embeddings'] assert isinstance(x_embeddings, schema.Scalar), ( "Incorrect input type for x. Expected Scalar, " + "but received: {0}".format(x_embeddings)) assert isinstance(y_embeddings, schema.Scalar), ( "Incorrect input type for y. Expected Scalar, " + "but received: {0}".format(y_embeddings) ) if 'indices_to_gather' in input_record: indices_to_gather = input_record['indices_to_gather'] assert isinstance(indices_to_gather, schema.Scalar), ( "Incorrect type of indices_to_gather. " "Expected Scalar, but received: {0}".format(indices_to_gather) ) self.indices_to_gather = indices_to_gather else: self.indices_to_gather = None self.x_embeddings = x_embeddings self.y_embeddings = y_embeddings dtype = x_embeddings.field_types()[0].base self.output_schema = schema.Scalar( (dtype, (output_dim,)), self.get_next_blob_reference('output') ) def add_ops(self, net): if self.pairwise_similarity_func == "cosine_similarity": x_embeddings_norm = net.Normalize(self.x_embeddings(), axis=1) y_embeddings_norm = net.Normalize(self.y_embeddings(), axis=1) Y = net.BatchMatMul( [x_embeddings_norm, y_embeddings_norm], [self.get_next_blob_reference(x_embeddings_norm + '_matmul')], trans_b=1, ) elif self.pairwise_similarity_func == "dot": Y = net.BatchMatMul( [self.x_embeddings(), self.y_embeddings()], [self.get_next_blob_reference(self.x_embeddings() + '_matmul')], trans_b=1, ) else: raise NotImplementedError( "pairwise_similarity_func={} is not valid".format( self.pairwise_similarity_func ) ) if self.indices_to_gather: flattened = net.Flatten( Y, Y + '_flatten', ) net.BatchGather( [flattened, self.indices_to_gather()], self.output_schema(), ) else: net.Flatten(Y, self.output_schema())