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/batch_normalization.py (3823B)

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

import numpy as np

class BatchNormalization(ModelLayer):
    def __init__(
        self,
        model,
        input_record,
        name='batch_normalization',
        scale_optim=None,
        bias_optim=None,
        momentum=0.9,
        order='NCHW',
        scale_init_value=1.0,
        **kwargs
    ):
        super(BatchNormalization, self).__init__(
            model, name, input_record, **kwargs)

assert isinstance(input_record, schema.Scalar), "Incorrect input type"

self.input_shape = input_record.field_type().shape

if len(self.input_shape) == 3:
            if order == "NCHW":
                input_dims = self.input_shape[0]
            elif order == "NHWC":
                input_dims = self.input_shape[2]
            else:
                raise ValueError("Please specify a correct order")
        else:
            assert len(self.input_shape) == 1, (
                "This layer supports only 4D or 2D tensors")
            input_dims = self.input_shape[0]

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

self.momentum = momentum
        self.order = order

self.scale = self.create_param(param_name='scale',
                                       shape=[input_dims],
                                       initializer=('ConstantFill', {'value': scale_init_value}),
                                       optimizer=scale_optim)
        self.bias = self.create_param(param_name='bias',
                                       shape=[input_dims],
                                       initializer=('ConstantFill', {'value': 0.0}),
                                       optimizer=bias_optim)
        self.rm = self.create_param(param_name='running_mean',
                                       shape=[input_dims],
                                       initializer=('ConstantFill', {'value': 0.0}),
                                       optimizer=model.NoOptim)
        self.riv = self.create_param(param_name='running_inv_var',
                                       shape=[input_dims],
                                       initializer=('ConstantFill', {'value': 1.0}),
                                       optimizer=model.NoOptim)

def _add_ops(self, net, is_test, out_blob=None):
        original_input_blob = self.input_record.field_blobs()
        input_blob = net.NextScopedBlob('expand_input')
        if len(self.input_shape) == 1:
            input_blob = net.ExpandDims(original_input_blob,
                                        dims=[2, 3])
        else:
            input_blob = original_input_blob[0]

if out_blob is None:
            bn_output = self.output_schema.field_blobs()
        else:
            bn_output = out_blob
        if is_test:
            output_blobs = bn_output
        else:
            output_blobs = bn_output + [self.rm, self.riv,
                                        net.NextScopedBlob('bn_saved_mean'),
                                        net.NextScopedBlob('bn_saved_iv')]

net.SpatialBN([input_blob, self.scale,
                       self.bias, self.rm, self.riv],
                      output_blobs,
                      momentum=self.momentum,
                      is_test=is_test,
                      order=self.order)

if len(self.input_shape) == 1:
            net.Squeeze(bn_output,
                        bn_output,
                        dims=[2, 3])

def add_train_ops(self, net):
        self._add_ops(net, is_test=False)

def add_eval_ops(self, net):
        self._add_ops(net, is_test=True)

def add_ops(self, net):
        self.add_eval_ops(net)

from caffe2.python import schema from caffe2.python.layers.layers import ModelLayer import numpy as np class BatchNormalization(ModelLayer): def __init__( self, model, input_record, name='batch_normalization', scale_optim=None, bias_optim=None, momentum=0.9, order='NCHW', scale_init_value=1.0, **kwargs ): super(BatchNormalization, self).__init__( model, name, input_record, **kwargs) assert isinstance(input_record, schema.Scalar), "Incorrect input type" self.input_shape = input_record.field_type().shape if len(self.input_shape) == 3: if order == "NCHW": input_dims = self.input_shape[0] elif order == "NHWC": input_dims = self.input_shape[2] else: raise ValueError("Please specify a correct order") else: assert len(self.input_shape) == 1, ( "This layer supports only 4D or 2D tensors") input_dims = self.input_shape[0] self.output_schema = schema.Scalar( (np.float32, self.input_shape), self.get_next_blob_reference('output') ) self.momentum = momentum self.order = order self.scale = self.create_param(param_name='scale', shape=[input_dims], initializer=('ConstantFill', {'value': scale_init_value}), optimizer=scale_optim) self.bias = self.create_param(param_name='bias', shape=[input_dims], initializer=('ConstantFill', {'value': 0.0}), optimizer=bias_optim) self.rm = self.create_param(param_name='running_mean', shape=[input_dims], initializer=('ConstantFill', {'value': 0.0}), optimizer=model.NoOptim) self.riv = self.create_param(param_name='running_inv_var', shape=[input_dims], initializer=('ConstantFill', {'value': 1.0}), optimizer=model.NoOptim) def _add_ops(self, net, is_test, out_blob=None): original_input_blob = self.input_record.field_blobs() input_blob = net.NextScopedBlob('expand_input') if len(self.input_shape) == 1: input_blob = net.ExpandDims(original_input_blob, dims=[2, 3]) else: input_blob = original_input_blob[0] if out_blob is None: bn_output = self.output_schema.field_blobs() else: bn_output = out_blob if is_test: output_blobs = bn_output else: output_blobs = bn_output + [self.rm, self.riv, net.NextScopedBlob('bn_saved_mean'), net.NextScopedBlob('bn_saved_iv')] net.SpatialBN([input_blob, self.scale, self.bias, self.rm, self.riv], output_blobs, momentum=self.momentum, is_test=is_test, order=self.order) if len(self.input_shape) == 1: net.Squeeze(bn_output, bn_output, dims=[2, 3]) def add_train_ops(self, net): self._add_ops(net, is_test=False) def add_eval_ops(self, net): self._add_ops(net, is_test=True) def add_ops(self, net): self.add_eval_ops(net)