summaryrefslogtreecommitdiff
path: root/src/caffe/util/io.cpp
blob: f2650e9a22ae6ec1698a8e25de605453f6d3f92e (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
182
183
184
// Copyright 2014 BVLC and contributors.

#include <stdint.h>
#include <fcntl.h>
#include <google/protobuf/text_format.h>
#include <google/protobuf/io/zero_copy_stream_impl.h>
#include <google/protobuf/io/coded_stream.h>
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/highgui/highgui_c.h>
#include <opencv2/imgproc/imgproc.hpp>

#include <algorithm>
#include <string>
#include <vector>
#include <fstream>  // NOLINT(readability/streams)

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

using std::fstream;
using std::ios;
using std::max;
using std::string;
using google::protobuf::io::FileInputStream;
using google::protobuf::io::FileOutputStream;
using google::protobuf::io::ZeroCopyInputStream;
using google::protobuf::io::CodedInputStream;
using google::protobuf::io::ZeroCopyOutputStream;
using google::protobuf::io::CodedOutputStream;
using google::protobuf::Message;

namespace caffe {

bool ReadProtoFromTextFile(const char* filename, Message* proto) {
  int fd = open(filename, O_RDONLY);
  CHECK_NE(fd, -1) << "File not found: " << filename;
  FileInputStream* input = new FileInputStream(fd);
  bool success = google::protobuf::TextFormat::Parse(input, proto);
  delete input;
  close(fd);
  return success;
}

void WriteProtoToTextFile(const Message& proto, const char* filename) {
  int fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC, 0644);
  FileOutputStream* output = new FileOutputStream(fd);
  CHECK(google::protobuf::TextFormat::Print(proto, output));
  delete output;
  close(fd);
}

bool ReadProtoFromBinaryFile(const char* filename, Message* proto) {
  int fd = open(filename, O_RDONLY);
  CHECK_NE(fd, -1) << "File not found: " << filename;
  ZeroCopyInputStream* raw_input = new FileInputStream(fd);
  CodedInputStream* coded_input = new CodedInputStream(raw_input);
  coded_input->SetTotalBytesLimit(1073741824, 536870912);

  bool success = proto->ParseFromCodedStream(coded_input);

  delete coded_input;
  delete raw_input;
  close(fd);
  return success;
}

void WriteProtoToBinaryFile(const Message& proto, const char* filename) {
  fstream output(filename, ios::out | ios::trunc | ios::binary);
  CHECK(proto.SerializeToOstream(&output));
}

bool ReadImageToDatum(const string& filename, const int label,
    const int height, const int width, const bool iscolor, Datum* datum) {
  cv::Mat cv_img;
  int cv_read_flag = (iscolor ? CV_LOAD_IMAGE_COLOR : CV_LOAD_IMAGE_GRAYSCALE);
  if (height > 0 && width > 0) {
    cv::Mat cv_img_origin = cv::imread(filename, cv_read_flag);
    cv::resize(cv_img_origin, cv_img, cv::Size(height, width));
  } else {
    cv_img = cv::imread(filename, cv_read_flag);
  }
  if (!cv_img.data) {
    LOG(ERROR) << "Could not open or find file " << filename;
    return false;
  }
  int num_channels = (iscolor ? 3 : 1);
  datum->set_channels(num_channels);
  datum->set_height(cv_img.rows);
  datum->set_width(cv_img.cols);
  datum->set_label(label);
  datum->clear_data();
  datum->clear_float_data();
  string* datum_string = datum->mutable_data();
  if (iscolor) {
    for (int c = 0; c < num_channels; ++c) {
      for (int h = 0; h < cv_img.rows; ++h) {
        for (int w = 0; w < cv_img.cols; ++w) {
          datum_string->push_back(
            static_cast<char>(cv_img.at<cv::Vec3b>(h, w)[c]));
        }
      }
    }
  } else {  // Faster than repeatedly testing iscolor for each pixel w/i loop
    for (int h = 0; h < cv_img.rows; ++h) {
      for (int w = 0; w < cv_img.cols; ++w) {
        datum_string->push_back(
          static_cast<char>(cv_img.at<uchar>(h, w)));
        }
      }
  }
  return true;
}

// Verifies format of data stored in HDF5 file and reshapes blob accordingly.
template <typename Dtype>
void hdf5_load_nd_dataset_helper(
    hid_t file_id, const char* dataset_name_, int min_dim, int max_dim,
    Blob<Dtype>* blob) {
  // Verify that the number of dimensions is in the accepted range.
  herr_t status;
  int ndims;
  status = H5LTget_dataset_ndims(file_id, dataset_name_, &ndims);
  CHECK_GE(ndims, min_dim);
  CHECK_LE(ndims, max_dim);

  // Verify that the data format is what we expect: float or double.
  std::vector<hsize_t> dims(ndims);
  H5T_class_t class_;
  status = H5LTget_dataset_info(
      file_id, dataset_name_, dims.data(), &class_, NULL);
  CHECK_EQ(class_, H5T_FLOAT) << "Expected float or double data";

  blob->Reshape(
    dims[0],
    (dims.size() > 1) ? dims[1] : 1,
    (dims.size() > 2) ? dims[2] : 1,
    (dims.size() > 3) ? dims[3] : 1);
}

template <>
void hdf5_load_nd_dataset<float>(hid_t file_id, const char* dataset_name_,
        int min_dim, int max_dim, Blob<float>* blob) {
  hdf5_load_nd_dataset_helper(file_id, dataset_name_, min_dim, max_dim, blob);
  herr_t status = H5LTread_dataset_float(
    file_id, dataset_name_, blob->mutable_cpu_data());
}

template <>
void hdf5_load_nd_dataset<double>(hid_t file_id, const char* dataset_name_,
        int min_dim, int max_dim, Blob<double>* blob) {
  hdf5_load_nd_dataset_helper(file_id, dataset_name_, min_dim, max_dim, blob);
  herr_t status = H5LTread_dataset_double(
    file_id, dataset_name_, blob->mutable_cpu_data());
}

template <>
void hdf5_save_nd_dataset<float>(
    const hid_t file_id, const string dataset_name, const Blob<float>& blob) {
  hsize_t dims[HDF5_NUM_DIMS];
  dims[0] = blob.num();
  dims[1] = blob.channels();
  dims[2] = blob.height();
  dims[3] = blob.width();
  herr_t status = H5LTmake_dataset_float(
      file_id, dataset_name.c_str(), HDF5_NUM_DIMS, dims, blob.cpu_data());
  CHECK_GE(status, 0) << "Failed to make float dataset " << dataset_name;
}

template <>
void hdf5_save_nd_dataset<double>(
    const hid_t file_id, const string dataset_name, const Blob<double>& blob) {
  hsize_t dims[HDF5_NUM_DIMS];
  dims[0] = blob.num();
  dims[1] = blob.channels();
  dims[2] = blob.height();
  dims[3] = blob.width();
  herr_t status = H5LTmake_dataset_double(
      file_id, dataset_name.c_str(), HDF5_NUM_DIMS, dims, blob.cpu_data());
  CHECK_GE(status, 0) << "Failed to make double dataset " << dataset_name;
}

}  // namespace caffe