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/sparse_dropout_with_replacement.py (3943B)

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

# Model layer for implementing probabilistic replacement of elements in
# IdLists.  Takes probabilities for train, eval and predict nets as input, as
# well as the replacement value when dropout happens.  For features we may have
# available to us in train net but not in predict net, we'd set dropout
# probability for predict net to be 1.0 and set the feature to the replacement
# value given here.  This way, the value is tied to the particular model and not
# to any specific logic in feature processing in serving.

# Consider the following example where X is the values in the IdList and Lengths
# is the number of values corresponding to each example.
# X: [1, 2, 3, 4, 5]
# Lengths: [2, 3]
# This IdList contains 2 items of lengths 2, 3.  Let's assume we used a ratio of
# 0.5 and ended up dropping out 2nd example, and used a replacement value of -1.
# We will end up with the following IdList.
#
# Y: [1, 2, -1]
# OutputLengths: [2, 1]
# where the 2nd item values [3,4,5] were replaced with [-1] and the length got
# set to 1.

class SparseDropoutWithReplacement(ModelLayer):
    def __init__(
            self,
            model,
            input_record,
            dropout_prob_train,
            dropout_prob_eval,
            dropout_prob_predict,
            replacement_value,
            name='sparse_dropout',
            **kwargs):

super(SparseDropoutWithReplacement, self).__init__(model, name, input_record, **kwargs)
        assert schema.equal_schemas(input_record, IdList), "Incorrect input type"

self.dropout_prob_train = float(dropout_prob_train)
        self.dropout_prob_eval = float(dropout_prob_eval)
        self.dropout_prob_predict = float(dropout_prob_predict)
        self.replacement_value = int(replacement_value)
        assert (self.dropout_prob_train >= 0 and
                self.dropout_prob_train <= 1.0), \
            "Expected 0 <= dropout_prob_train <= 1, but got %s" \
            % self.dropout_prob_train
        assert (self.dropout_prob_eval >= 0 and
                self.dropout_prob_eval <= 1.0), \
            "Expected 0 <= dropout_prob_eval <= 1, but got %s" \
            % dropout_prob_eval
        assert (self.dropout_prob_predict >= 0 and
                self.dropout_prob_predict <= 1.0), \
            "Expected 0 <= dropout_prob_predict <= 1, but got %s" \
            % dropout_prob_predict
        assert(self.dropout_prob_train > 0 or
               self.dropout_prob_eval > 0 or
               self.dropout_prob_predict > 0), \
            "Ratios all set to 0.0 for train, eval and predict"

self.output_schema = schema.NewRecord(model.net, IdList)
        if input_record.lengths.metadata:
            self.output_schema.lengths.set_metadata(
                input_record.lengths.metadata)
        if input_record.items.metadata:
            self.output_schema.items.set_metadata(
                input_record.items.metadata)

def _add_ops(self, net, ratio):
        input_values_blob = self.input_record.items()
        input_lengths_blob = self.input_record.lengths()

output_lengths_blob = self.output_schema.lengths()
        output_values_blob = self.output_schema.items()

net.SparseDropoutWithReplacement([input_values_blob,
                                          input_lengths_blob],
                                         [output_values_blob,
                                          output_lengths_blob],
                                         ratio=ratio,
                                         replacement_value=self.replacement_value)

def add_train_ops(self, net):
        self._add_ops(net, self.dropout_prob_train)

def add_eval_ops(self, net):
        self._add_ops(net, self.dropout_prob_eval)

def add_ops(self, net):
        self._add_ops(net, self.dropout_prob_predict)

from caffe2.python import schema from caffe2.python.layers.layers import ( IdList, ModelLayer, ) # Model layer for implementing probabilistic replacement of elements in # IdLists. Takes probabilities for train, eval and predict nets as input, as # well as the replacement value when dropout happens. For features we may have # available to us in train net but not in predict net, we'd set dropout # probability for predict net to be 1.0 and set the feature to the replacement # value given here. This way, the value is tied to the particular model and not # to any specific logic in feature processing in serving. # Consider the following example where X is the values in the IdList and Lengths # is the number of values corresponding to each example. # X: [1, 2, 3, 4, 5] # Lengths: [2, 3] # This IdList contains 2 items of lengths 2, 3. Let's assume we used a ratio of # 0.5 and ended up dropping out 2nd example, and used a replacement value of -1. # We will end up with the following IdList. # # Y: [1, 2, -1] # OutputLengths: [2, 1] # where the 2nd item values [3,4,5] were replaced with [-1] and the length got # set to 1. class SparseDropoutWithReplacement(ModelLayer): def __init__( self, model, input_record, dropout_prob_train, dropout_prob_eval, dropout_prob_predict, replacement_value, name='sparse_dropout', **kwargs): super(SparseDropoutWithReplacement, self).__init__(model, name, input_record, **kwargs) assert schema.equal_schemas(input_record, IdList), "Incorrect input type" self.dropout_prob_train = float(dropout_prob_train) self.dropout_prob_eval = float(dropout_prob_eval) self.dropout_prob_predict = float(dropout_prob_predict) self.replacement_value = int(replacement_value) assert (self.dropout_prob_train >= 0 and self.dropout_prob_train <= 1.0), \ "Expected 0 <= dropout_prob_train <= 1, but got %s" \ % self.dropout_prob_train assert (self.dropout_prob_eval >= 0 and self.dropout_prob_eval <= 1.0), \ "Expected 0 <= dropout_prob_eval <= 1, but got %s" \ % dropout_prob_eval assert (self.dropout_prob_predict >= 0 and self.dropout_prob_predict <= 1.0), \ "Expected 0 <= dropout_prob_predict <= 1, but got %s" \ % dropout_prob_predict assert(self.dropout_prob_train > 0 or self.dropout_prob_eval > 0 or self.dropout_prob_predict > 0), \ "Ratios all set to 0.0 for train, eval and predict" self.output_schema = schema.NewRecord(model.net, IdList) if input_record.lengths.metadata: self.output_schema.lengths.set_metadata( input_record.lengths.metadata) if input_record.items.metadata: self.output_schema.items.set_metadata( input_record.items.metadata) def _add_ops(self, net, ratio): input_values_blob = self.input_record.items() input_lengths_blob = self.input_record.lengths() output_lengths_blob = self.output_schema.lengths() output_values_blob = self.output_schema.items() net.SparseDropoutWithReplacement([input_values_blob, input_lengths_blob], [output_values_blob, output_lengths_blob], ratio=ratio, replacement_value=self.replacement_value) def add_train_ops(self, net): self._add_ops(net, self.dropout_prob_train) def add_eval_ops(self, net): self._add_ops(net, self.dropout_prob_eval) def add_ops(self, net): self._add_ops(net, self.dropout_prob_predict)