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/uniform_sampling.py (2779B)

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

import numpy as np

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

class UniformSampling(ModelLayer):
    """
    Uniform sampling `num_samples - len(input_record)` unique elements from the
    range [0, num_elements). `samples` is the concatenation of input_record and
    the samples. input_record is expected to be unique.
    """

def __init__(
        self,
        model,
        input_record,
        num_samples,
        num_elements,
        name='uniform_sampling',
        **kwargs
    ):
        super(UniformSampling, self).__init__(
            model, name, input_record, **kwargs
        )

assert num_elements > num_samples > 0
        assert isinstance(input_record, schema.Scalar)

self.num_elements = num_elements

num_examples_init = ('GivenTensorInt64Fill',
                             {'values': [num_samples]})
        self.num_samples = self.create_param(param_name='num_examples',
                                              shape=(1,),
                                              initializer=num_examples_init,
                                              optimizer=model.NoOptim)

sampling_blob_init = ('ConstantFill',
                              {'value': float(num_samples) / num_elements,
                               'dtype': core.DataType.FLOAT})
        self.sampling_prob = self.create_param(param_name='prob',
                                               shape=(num_samples,),
                                               initializer=sampling_blob_init,
                                               optimizer=model.NoOptim)

self.output_schema = schema.Struct(
            (
                'samples', schema.Scalar(
                    np.int32, self.get_next_blob_reference("samples")
                )
            ),
            ('sampling_prob', schema.Scalar(np.float32, self.sampling_prob)),
        )

def add_ops(self, net):
        net.StopGradient(self.sampling_prob, self.sampling_prob)

shape = net.Shape([self.input_record()], net.NextScopedBlob("shape"))
        shape = net.Sub([self.num_samples, shape], shape)
        samples = net.UniqueUniformFill(
            [shape, self.input_record()],
            net.NextScopedBlob("samples_before_concat"),
            min=0,
            max=self.num_elements - 1,
            input_as_shape=True
        )

net.Concat(
            [self.input_record(), samples],
            [self.output_schema.samples(), net.NextScopedBlob("split_info")],
            axis=0
        )
        net.StopGradient(
            self.output_schema.samples(), self.output_schema.samples()
        )

## @package uniform_sampling # Module caffe2.python.layers.uniform_sampling import numpy as np from caffe2.python import core, schema from caffe2.python.layers.layers import ModelLayer class UniformSampling(ModelLayer): """ Uniform sampling `num_samples - len(input_record)` unique elements from the range [0, num_elements). `samples` is the concatenation of input_record and the samples. input_record is expected to be unique. """ def __init__( self, model, input_record, num_samples, num_elements, name='uniform_sampling', **kwargs ): super(UniformSampling, self).__init__( model, name, input_record, **kwargs ) assert num_elements > num_samples > 0 assert isinstance(input_record, schema.Scalar) self.num_elements = num_elements num_examples_init = ('GivenTensorInt64Fill', {'values': [num_samples]}) self.num_samples = self.create_param(param_name='num_examples', shape=(1,), initializer=num_examples_init, optimizer=model.NoOptim) sampling_blob_init = ('ConstantFill', {'value': float(num_samples) / num_elements, 'dtype': core.DataType.FLOAT}) self.sampling_prob = self.create_param(param_name='prob', shape=(num_samples,), initializer=sampling_blob_init, optimizer=model.NoOptim) self.output_schema = schema.Struct( ( 'samples', schema.Scalar( np.int32, self.get_next_blob_reference("samples") ) ), ('sampling_prob', schema.Scalar(np.float32, self.sampling_prob)), ) def add_ops(self, net): net.StopGradient(self.sampling_prob, self.sampling_prob) shape = net.Shape([self.input_record()], net.NextScopedBlob("shape")) shape = net.Sub([self.num_samples, shape], shape) samples = net.UniqueUniformFill( [shape, self.input_record()], net.NextScopedBlob("samples_before_concat"), min=0, max=self.num_elements - 1, input_as_shape=True ) net.Concat( [self.input_record(), samples], [self.output_schema.samples(), net.NextScopedBlob("split_info")], axis=0 ) net.StopGradient( self.output_schema.samples(), self.output_schema.samples() )