summaryrefslogtreecommitdiff
path: root/src/caffe/test/test_image_data_layer.cpp
blob: 481fcef7b2701a9dd8e4ef25ebc9a70bb08b0aa9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
#ifdef USE_OPENCV
#include <map>
#include <string>
#include <vector>

#include "gtest/gtest.h"

#include "caffe/blob.hpp"
#include "caffe/common.hpp"
#include "caffe/filler.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/util/io.hpp"
#include "caffe/vision_layers.hpp"

#include "caffe/test/test_caffe_main.hpp"

namespace caffe {

template <typename TypeParam>
class ImageDataLayerTest : public MultiDeviceTest<TypeParam> {
  typedef typename TypeParam::Dtype Dtype;

 protected:
  ImageDataLayerTest()
      : seed_(1701),
        blob_top_data_(new Blob<Dtype>()),
        blob_top_label_(new Blob<Dtype>()) {}
  virtual void SetUp() {
    blob_top_vec_.push_back(blob_top_data_);
    blob_top_vec_.push_back(blob_top_label_);
    Caffe::set_random_seed(seed_);
    // Create test input file.
    MakeTempFilename(&filename_);
    std::ofstream outfile(filename_.c_str(), std::ofstream::out);
    LOG(INFO) << "Using temporary file " << filename_;
    for (int i = 0; i < 5; ++i) {
      outfile << EXAMPLES_SOURCE_DIR "images/cat.jpg " << i;
    }
    outfile.close();
    // Create test input file for images of distinct sizes.
    MakeTempFilename(&filename_reshape_);
    std::ofstream reshapefile(filename_reshape_.c_str(), std::ofstream::out);
    LOG(INFO) << "Using temporary file " << filename_reshape_;
    reshapefile << EXAMPLES_SOURCE_DIR "images/cat.jpg " << 0;
    reshapefile << EXAMPLES_SOURCE_DIR "images/fish-bike.jpg " << 1;
    reshapefile.close();
  }

  virtual ~ImageDataLayerTest() {
    delete blob_top_data_;
    delete blob_top_label_;
  }

  int seed_;
  string filename_;
  string filename_reshape_;
  Blob<Dtype>* const blob_top_data_;
  Blob<Dtype>* const blob_top_label_;
  vector<Blob<Dtype>*> blob_bottom_vec_;
  vector<Blob<Dtype>*> blob_top_vec_;
};

TYPED_TEST_CASE(ImageDataLayerTest, TestDtypesAndDevices);

TYPED_TEST(ImageDataLayerTest, TestRead) {
  typedef typename TypeParam::Dtype Dtype;
  LayerParameter param;
  ImageDataParameter* image_data_param = param.mutable_image_data_param();
  image_data_param->set_batch_size(5);
  image_data_param->set_source(this->filename_.c_str());
  image_data_param->set_shuffle(false);
  ImageDataLayer<Dtype> layer(param);
  layer.SetUp(this->blob_bottom_vec_, this->blob_top_vec_);
  EXPECT_EQ(this->blob_top_data_->num(), 5);
  EXPECT_EQ(this->blob_top_data_->channels(), 3);
  EXPECT_EQ(this->blob_top_data_->height(), 360);
  EXPECT_EQ(this->blob_top_data_->width(), 480);
  EXPECT_EQ(this->blob_top_label_->num(), 5);
  EXPECT_EQ(this->blob_top_label_->channels(), 1);
  EXPECT_EQ(this->blob_top_label_->height(), 1);
  EXPECT_EQ(this->blob_top_label_->width(), 1);
  // Go through the data twice
  for (int iter = 0; iter < 2; ++iter) {
    layer.Forward(this->blob_bottom_vec_, this->blob_top_vec_);
    for (int i = 0; i < 5; ++i) {
      EXPECT_EQ(i, this->blob_top_label_->cpu_data()[i]);
    }
  }
}

TYPED_TEST(ImageDataLayerTest, TestResize) {
  typedef typename TypeParam::Dtype Dtype;
  LayerParameter param;
  ImageDataParameter* image_data_param = param.mutable_image_data_param();
  image_data_param->set_batch_size(5);
  image_data_param->set_source(this->filename_.c_str());
  image_data_param->set_new_height(256);
  image_data_param->set_new_width(256);
  image_data_param->set_shuffle(false);
  ImageDataLayer<Dtype> layer(param);
  layer.SetUp(this->blob_bottom_vec_, this->blob_top_vec_);
  EXPECT_EQ(this->blob_top_data_->num(), 5);
  EXPECT_EQ(this->blob_top_data_->channels(), 3);
  EXPECT_EQ(this->blob_top_data_->height(), 256);
  EXPECT_EQ(this->blob_top_data_->width(), 256);
  EXPECT_EQ(this->blob_top_label_->num(), 5);
  EXPECT_EQ(this->blob_top_label_->channels(), 1);
  EXPECT_EQ(this->blob_top_label_->height(), 1);
  EXPECT_EQ(this->blob_top_label_->width(), 1);
  // Go through the data twice
  for (int iter = 0; iter < 2; ++iter) {
    layer.Forward(this->blob_bottom_vec_, this->blob_top_vec_);
    for (int i = 0; i < 5; ++i) {
      EXPECT_EQ(i, this->blob_top_label_->cpu_data()[i]);
    }
  }
}

TYPED_TEST(ImageDataLayerTest, TestReshape) {
  typedef typename TypeParam::Dtype Dtype;
  LayerParameter param;
  ImageDataParameter* image_data_param = param.mutable_image_data_param();
  image_data_param->set_batch_size(1);
  image_data_param->set_source(this->filename_reshape_.c_str());
  image_data_param->set_shuffle(false);
  ImageDataLayer<Dtype> layer(param);
  layer.SetUp(this->blob_bottom_vec_, this->blob_top_vec_);
  EXPECT_EQ(this->blob_top_label_->num(), 1);
  EXPECT_EQ(this->blob_top_label_->channels(), 1);
  EXPECT_EQ(this->blob_top_label_->height(), 1);
  EXPECT_EQ(this->blob_top_label_->width(), 1);
  // cat.jpg
  layer.Forward(this->blob_bottom_vec_, this->blob_top_vec_);
  EXPECT_EQ(this->blob_top_data_->num(), 1);
  EXPECT_EQ(this->blob_top_data_->channels(), 3);
  EXPECT_EQ(this->blob_top_data_->height(), 360);
  EXPECT_EQ(this->blob_top_data_->width(), 480);
  // fish-bike.jpg
  layer.Forward(this->blob_bottom_vec_, this->blob_top_vec_);
  EXPECT_EQ(this->blob_top_data_->num(), 1);
  EXPECT_EQ(this->blob_top_data_->channels(), 3);
  EXPECT_EQ(this->blob_top_data_->height(), 323);
  EXPECT_EQ(this->blob_top_data_->width(), 481);
}

TYPED_TEST(ImageDataLayerTest, TestShuffle) {
  typedef typename TypeParam::Dtype Dtype;
  LayerParameter param;
  ImageDataParameter* image_data_param = param.mutable_image_data_param();
  image_data_param->set_batch_size(5);
  image_data_param->set_source(this->filename_.c_str());
  image_data_param->set_shuffle(true);
  ImageDataLayer<Dtype> layer(param);
  layer.SetUp(this->blob_bottom_vec_, this->blob_top_vec_);
  EXPECT_EQ(this->blob_top_data_->num(), 5);
  EXPECT_EQ(this->blob_top_data_->channels(), 3);
  EXPECT_EQ(this->blob_top_data_->height(), 360);
  EXPECT_EQ(this->blob_top_data_->width(), 480);
  EXPECT_EQ(this->blob_top_label_->num(), 5);
  EXPECT_EQ(this->blob_top_label_->channels(), 1);
  EXPECT_EQ(this->blob_top_label_->height(), 1);
  EXPECT_EQ(this->blob_top_label_->width(), 1);
  // Go through the data twice
  for (int iter = 0; iter < 2; ++iter) {
    layer.Forward(this->blob_bottom_vec_, this->blob_top_vec_);
    map<Dtype, int> values_to_indices;
    int num_in_order = 0;
    for (int i = 0; i < 5; ++i) {
      Dtype value = this->blob_top_label_->cpu_data()[i];
      // Check that the value has not been seen already (no duplicates).
      EXPECT_EQ(values_to_indices.find(value), values_to_indices.end());
      values_to_indices[value] = i;
      num_in_order += (value == Dtype(i));
    }
    EXPECT_EQ(5, values_to_indices.size());
    EXPECT_GT(5, num_in_order);
  }
}

}  // namespace caffe
#endif  // USE_OPENCV