mirror of
https://github.com/saymrwulf/pytorch.git
synced 2026-05-15 21:00:47 +00:00
aed3aabc7f
Summary: we may not need dense feature inputs in some models (e.g., double helix). Reviewed By: dzhulgakov Differential Revision: D4568755 fbshipit-source-id: 6850508f86fafb53f81783b2a2a38776be5455d7
66 lines
2.6 KiB
Python
66 lines
2.6 KiB
Python
from __future__ import absolute_import
|
|
from __future__ import division
|
|
from __future__ import print_function
|
|
from __future__ import unicode_literals
|
|
|
|
from caffe2.python import core, schema
|
|
from caffe2.python.layers.layers import (
|
|
ModelLayer,
|
|
LayerParameter
|
|
)
|
|
import math
|
|
import numpy as np
|
|
|
|
|
|
class FC(ModelLayer):
|
|
|
|
def __init__(self, model, input_record, output_dims, weight_init=None,
|
|
bias_init=None, weight_optim=None, bias_optim=None, name='fc',
|
|
**kwargs):
|
|
super(FC, self).__init__(model, name, input_record, **kwargs)
|
|
assert isinstance(input_record, schema.Scalar), "Incorrect input type"
|
|
assert len(input_record.field_types()[0].shape) > 0, (
|
|
"FC expects limited dimensions of the input tensor")
|
|
|
|
input_dims = input_record.field_types()[0].shape[0]
|
|
assert input_dims > 0, (
|
|
"FC expects input dimensions > 0, got {}".format(input_dims))
|
|
|
|
self.output_schema = schema.Scalar(
|
|
(np.float32, (output_dims, )),
|
|
model.net.NextScopedBlob(name + '_output')
|
|
)
|
|
|
|
scale = math.sqrt(1.0 / input_dims)
|
|
weight_init = weight_init if weight_init else (
|
|
'UniformFill', {'min': -scale, 'max': scale})
|
|
bias_init = bias_init if bias_init else (
|
|
'UniformFill', {'min': -scale, 'max': scale})
|
|
|
|
self.w = model.net.NextScopedBlob(name + "_w")
|
|
self.b = model.net.NextScopedBlob(name + "_b")
|
|
|
|
self.params.append(
|
|
LayerParameter(
|
|
parameter=self.w,
|
|
initializer=core.CreateOperator(weight_init[0],
|
|
[],
|
|
self.w,
|
|
shape=[output_dims, input_dims],
|
|
**weight_init[1]
|
|
),
|
|
optimizer=weight_optim))
|
|
self.params.append(
|
|
LayerParameter(
|
|
parameter=self.b,
|
|
initializer=core.CreateOperator(bias_init[0],
|
|
[],
|
|
self.b,
|
|
shape=[output_dims, ],
|
|
**bias_init[1]
|
|
),
|
|
optimizer=bias_optim))
|
|
|
|
def add_ops(self, net):
|
|
net.FC(self.input_record.field_blobs() + [self.w, self.b],
|
|
self.output_schema.field_blobs(), **self.kwargs)
|