ModelZoo/Vision/DenseNet.pm untested

filter: Statementstmt 0.0% 0 / 95 Branchbran 0.0% 0 / 6 Conditioncond n/a MC/DCmcdc n/a Subroutinesub 0.0% 0 / 5 Podpod n/a totaltotal 0.0% 0 / 106 CC 1 SCAR 6.9
CC
1
Cov
0%
BEGIN
2.0
BEGIN
2.0
BEGIN
2.0
CRAP 2.0
1 # Licensed to the Apache Software Foundation (ASF) under one
2 # or more contributor license agreements. See the NOTICE file
3 # distributed with this work for additional information
4 # regarding copyright ownership. The ASF licenses this file
5 # to you under the Apache License, Version 2.0 (the
6 # "License"); you may not use this file except in compliance
7 # with the License. You may obtain a copy of the License at
8 #
9 # http://www.apache.org/licenses/LICENSE-2.0
10 #
11 # Unless required by applicable law or agreed to in writing,
12 # software distributed under the License is distributed on an
13 # "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
14 # KIND, either express or implied. See the License for the
15 # specific language governing permissions and limitations
16 # under the License.
17  
18 package AI::MXNet::Gluon::ModelZoo::Vision::DenseNet;
19 use strict;
20 use warnings;
21 use AI::MXNet::Base;
22 use AI::MXNet::Function::Parameters;
23 use AI::MXNet::Gluon::Mouse;
24 extends 'AI::MXNet::Gluon::HybridBlock';
25  
26 func _make_dense_block($num_layers, $bn_size, $growth_rate, $dropout, $stage_index)
27 {
28 my $out = nn->HybridSequential(prefix=>"stage${stage_index}_");
29 $out->name_scope(sub {
30 for(1..$num_layers)
31 {
32 $out->add(_make_dense_layer($growth_rate, $bn_size, $dropout));
33 }
34 });
35 return $out;
36 }
37  
38 func _make_dense_layer($growth_rate, $bn_size, $dropout)
39 {
40 my $new_features = nn->HybridSequential(prefix=>'');
41 $new_features->add(nn->BatchNorm());
42 $new_features->add(nn->Activation('relu'));
43 $new_features->add(nn->Conv2D($bn_size * $growth_rate, kernel_size=>1, use_bias=>0));
44 $new_features->add(nn->BatchNorm());
45 $new_features->add(nn->Activation('relu'));
46 $new_features->add(nn->Conv2D($growth_rate, kernel_size=>3, padding=>1, use_bias=>0));
47 if($dropout)
48 {
49 $new_features->add(nn->Dropout($dropout));
50 }
51  
52 my $out = nn->HybridConcurrent(axis=>1, prefix=>'');
53 $out->add(nn->Identity());
54 $out->add($new_features);
55  
56 return $out;
57 }
58  
59 func _make_transition($num_output_features)
60 {
61 my $out = nn->HybridSequential(prefix=>'');
62 $out->add(nn->BatchNorm());
63 $out->add(nn->Activation('relu'));
64 $out->add(nn->Conv2D($num_output_features, kernel_size=>1, use_bias=>0));
65 $out->add(nn->AvgPool2D(pool_size=>2, strides=>2));
66 return $out;
67 }
68  
69 =head1 NAME
70  
71 AI::MXNet::Gluon::ModelZoo::Vision::DenseNet - Densenet-BC model from the "Densely Connected Convolutional Networks"
72 =cut
73  
74 =head1 DESCRIPTION
75  
76 Densenet-BC model from the "Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf> paper.
77  
78 Parameters
79 ----------
80 num_init_features : Int
81 Number of filters to learn in the first convolution layer.
82 growth_rate : Int
83 Number of filters to add each layer (`k` in the paper).
84 block_config : array ref of Int
85 List of integers for numbers of layers in each pooling block.
86 bn_size : Int, default 4
87 Multiplicative factor for number of bottle neck layers.
88 (i.e. bn_size * k features in the bottleneck layer)
89 dropout : float, default 0
90 Rate of dropout after each dense layer.
91 classes : int, default 1000
92 Number of classification classes.
93 =cut
94 has [qw/num_init_features
95 growth_rate/] => (is => 'ro', isa => 'Int', required => 1);
96 has 'block_config' => (is => 'ro', isa => 'ArrayRef[Int]', required => 1);
97 has 'bn_size' => (is => 'ro', isa => 'Int', default => 4);
98 has 'dropout' => (is => 'ro', isa => 'Num', default => 0);
99 has 'classes' => (is => 'ro', isa => 'Int', default => 1000);
100 method python_constructor_arguments(){ [qw/num_init_features growth_rate block_config bn_size dropout classes/] }
101  
102 sub BUILD
103 {
104 my $self = shift;
105 $self->name_scope(sub {
106 $self->features(nn->HybridSequential(prefix=>''));
107 $self->features->add(
108 nn->Conv2D(
109 $self->num_init_features, kernel_size=>7,
110 strides=>2, padding=>3, use_bias=>0
111 )
112 );
113 $self->features->add(nn->BatchNorm());
114 $self->features->add(nn->Activation('relu'));
115 $self->features->add(nn->MaxPool2D(pool_size=>3, strides=>2, padding=>1));
116 # Add dense blocks
117 my $num_features = $self->num_init_features;
118 for(enumerate($self->block_config))
119 {
120 my ($i, $num_layers) = @$_;
121 $self->features->add(_make_dense_block($num_layers, $self->bn_size, $self->growth_rate, $self->dropout, $i+1));
122 $num_features += $num_layers * $self->growth_rate;
123 if($i != @{ $self->block_config } - 1)
124 {
125 $self->features->add(_make_transition(int($num_features/2)));
126 $num_features = int($num_features/2);
127 }
128 }
129 $self->features->add(nn->BatchNorm());
130 $self->features->add(nn->Activation('relu'));
131 $self->features->add(nn->AvgPool2D(pool_size=>7));
132 $self->features->add(nn->Flatten());
133  
134 $self->output(nn->Dense($self->classes));
135 });
136 }
137  
138 method hybrid_forward(GluonClass $F, GluonInput $x)
139 {
140 $x = $self->features->($x);
141 $x = $self->output->($x);
142 return $x;
143 }
144  
145 package AI::MXNet::Gluon::ModelZoo::Vision;
146  
147 my %densenet_spec = (
148 121 => [64, 32, [6, 12, 24, 16]],
149 161 => [96, 48, [6, 12, 36, 24]],
150 169 => [64, 32, [6, 12, 32, 32]],
151 201 => [64, 32, [6, 12, 48, 32]]
152 );
153  
154 =head2 get_densenet
155  
156 Densenet-BC model from the
157 "Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf> paper.
158  
159 Parameters
160 ----------
161 $num_layers : Int
162 Number of layers for the variant of densenet. Options are 121, 161, 169, 201.
163 :$pretrained : Bool, default 0
164 Whether to load the pretrained weights for model.
165 :$ctx : AI::MXNet::Context, default CPU
166 The context in which to load the pretrained weights.
167 :$root : Str, default '~/.mxnet/models'
168 Location for keeping the model parameters.
169 =cut
170  
171 method get_densenet(
172 Int $num_layers, Bool :$pretrained=0, :$ctx=AI::MXNet::Context->cpu(),
173 :$root='~/.mxnet/models',
174 Int :$bn_size=4,
175 Num :$dropout=0,
176 Int :$classes=1000
177 )
178 {
179 my ($num_init_features, $growth_rate, $block_config) = @{ $densenet_spec{$num_layers} };
180 my $net = AI::MXNet::Gluon::ModelZoo::Vision::DenseNet->new(
181 $num_init_features, $growth_rate, $block_config,
182 $bn_size, $dropout, $classes
183 );
184 if($pretrained)
185 {
186 $net->load_parameters(
187 AI::MXNet::Gluon::ModelZoo::ModelStore->get_model_file(
188 "densenet$num_layers",
189 root=>$root
190 ),
191 ctx=>$ctx
192 );
193 }
194 return $net;
195 }
196  
197 =head2 densenet121
198  
199 Densenet-BC 121-layer model from the
200 "Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf> paper.
201  
202 Parameters
203 ----------
204 :$pretrained : Bool, default 0
205 Whether to load the pretrained weights for model.
206 :$ctx : AI::MXNet::Context, default CPU
207 The context in which to load the pretrained weights.
208 :$root : Str, default '~/.mxnet/models'
209 Location for keeping the model parameters.
210 =cut
211  
212 method densenet121(%kwargs)
213 {
214 return __PACKAGE__->get_densenet(121, %kwargs)
215 }
216  
217 =head2 densenet161
218  
219 Densenet-BC 161-layer model from the
220 "Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf> paper.
221  
222 Parameters
223 ----------
224 :$pretrained : Bool, default 0
225 Whether to load the pretrained weights for model.
226 :$ctx : AI::MXNet::Context, default CPU
227 The context in which to load the pretrained weights.
228 :$root : Str, default '~/.mxnet/models'
229 Location for keeping the model parameters.
230 =cut
231  
232 method densenet161(%kwargs)
233 {
234 return __PACKAGE__->get_densenet(161, %kwargs)
235 }
236  
237 =head2 densenet169
238  
239 Densenet-BC 169-layer model from the
240 "Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf> paper.
241  
242 Parameters
243 ----------
244 :$pretrained : Bool, default 0
245 Whether to load the pretrained weights for model.
246 :$ctx : AI::MXNet::Context, default CPU
247 The context in which to load the pretrained weights.
248 :$root : Str, default '~/.mxnet/models'
249 Location for keeping the model parameters.
250 =cut
251  
252 method densenet169(%kwargs)
253 {
254 return __PACKAGE__->get_densenet(169, %kwargs)
255 }
256  
257 =head2 densenet201
258  
259 Densenet-BC 201-layer model from the
260 "Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf> paper.
261  
262 Parameters
263 ----------
264 :$pretrained : Bool, default 0
265 Whether to load the pretrained weights for model.
266 :$ctx : AI::MXNet::Context, default CPU
267 The context in which to load the pretrained weights.
268 :$root : Str, default '~/.mxnet/models'
269 Location for keeping the model parameters.
270 =cut
271  
272 method densenet201(%kwargs)
273 {
274 return __PACKAGE__->get_densenet(201, %kwargs)
275 }
276  
277 1;