Cleaning up the encoded flag. Allowing any image (cropped or gray scale) to be encode...

diff --git a/include/caffe/util/io.hpp b/include/caffe/util/io.hpp
index a01f917..9d7540d 100644 (file)
--- a/include/caffe/util/io.hpp
+++ b/include/caffe/util/io.hpp
@@ -92,7 +92,14 @@ inline bool ReadFileToDatum(const string& filename, Datum* datum) {
 }
 
 bool ReadImageToDatum(const string& filename, const int label,
-    const int height, const int width, const bool is_color, Datum* datum);
+    const int height, const int width, const bool is_color,
+    const std::string & encoding, Datum* datum);
+
+inline bool ReadImageToDatum(const string& filename, const int label,
+    const int height, const int width, const bool is_color, Datum* datum) {
+  return ReadImageToDatum(filename, label, height, width, is_color,
+                          "", datum);
+}
 
 inline bool ReadImageToDatum(const string& filename, const int label,
     const int height, const int width, Datum* datum) {
@@ -109,20 +116,12 @@ inline bool ReadImageToDatum(const string& filename, const int label,
   return ReadImageToDatum(filename, label, 0, 0, true, datum);
 }
 
-bool DecodeDatum(const int height, const int width, const bool is_color,
-  Datum* datum);
-
-inline bool DecodeDatum(const int height, const int width, Datum* datum) {
-  return DecodeDatum(height, width, true, datum);
-}
-
-inline bool DecodeDatum(const bool is_color, Datum* datum) {
-  return DecodeDatum(0, 0, is_color, datum);
+inline bool ReadImageToDatum(const string& filename, const int label,
+    const std::string & encoding, Datum* datum) {
+  return ReadImageToDatum(filename, label, 0, 0, true, encoding, datum);
 }
 
-inline bool DecodeDatum(Datum* datum) {
-  return DecodeDatum(0, 0, true, datum);
-}
+bool DecodeDatumNative(Datum* datum);
 
 cv::Mat ReadImageToCVMat(const string& filename,
     const int height, const int width, const bool is_color);
@@ -135,16 +134,7 @@ cv::Mat ReadImageToCVMat(const string& filename,
 
 cv::Mat ReadImageToCVMat(const string& filename);
 
-cv::Mat DecodeDatumToCVMat(const Datum& datum,
-    const int height, const int width, const bool is_color);
-
-cv::Mat DecodeDatumToCVMat(const Datum& datum,
-    const int height, const int width);
-
-cv::Mat DecodeDatumToCVMat(const Datum& datum,
-    const bool is_color);
-
-cv::Mat DecodeDatumToCVMat(const Datum& datum);
+cv::Mat DecodeDatumToCVMatNative(const Datum& datum);
 
 void CVMatToDatum(const cv::Mat& cv_img, Datum* datum);
 

diff --git a/src/caffe/layers/data_layer.cpp b/src/caffe/layers/data_layer.cpp
index 227db20..891d039 100644 (file)
--- a/src/caffe/layers/data_layer.cpp
+++ b/src/caffe/layers/data_layer.cpp
@@ -42,7 +42,7 @@ void DataLayer<Dtype>::DataLayerSetUp(const vector<Blob<Dtype>*>& bottom,
   Datum datum;
   datum.ParseFromString(cursor_->value());
 
-  if (DecodeDatum(&datum)) {
+  if (DecodeDatumNative(&datum)) {
     LOG(INFO) << "Decoding Datum";
   }
   // image
@@ -98,7 +98,7 @@ void DataLayer<Dtype>::InternalThreadEntry() {
 
     cv::Mat cv_img;
     if (datum.encoded()) {
-       cv_img = DecodeDatumToCVMat(datum);
+       cv_img = DecodeDatumToCVMatNative(datum);
     }
     read_time += timer.MicroSeconds();
     timer.Start();

diff --git a/src/caffe/layers/window_data_layer.cpp b/src/caffe/layers/window_data_layer.cpp
index 23ec83d..cceb4ff 100644 (file)
--- a/src/caffe/layers/window_data_layer.cpp
+++ b/src/caffe/layers/window_data_layer.cpp
@@ -281,7 +281,7 @@ void WindowDataLayer<Dtype>::InternalThreadEntry() {
       if (this->cache_images_) {
         pair<std::string, Datum> image_cached =
           image_database_cache_[window[WindowDataLayer<Dtype>::IMAGE_INDEX]];
-        cv_img = DecodeDatumToCVMat(image_cached.second);
+        cv_img = DecodeDatumToCVMatNative(image_cached.second);
       } else {
         cv_img = cv::imread(image.first, CV_LOAD_IMAGE_COLOR);
         if (!cv_img.data) {

diff --git a/src/caffe/test/test_io.cpp b/src/caffe/test/test_io.cpp
index 4d941fa..6b135ef 100644 (file)
--- a/src/caffe/test/test_io.cpp
+++ b/src/caffe/test/test_io.cpp
@@ -289,8 +289,8 @@ TEST_F(IOTest, TestDecodeDatum) {
   string filename = EXAMPLES_SOURCE_DIR "images/cat.jpg";
   Datum datum;
   EXPECT_TRUE(ReadFileToDatum(filename, &datum));
-  EXPECT_TRUE(DecodeDatum(&datum));
-  EXPECT_FALSE(DecodeDatum(&datum));
+  EXPECT_TRUE(DecodeDatumNative(&datum));
+  EXPECT_FALSE(DecodeDatumNative(&datum));
   Datum datum_ref;
   ReadImageToDatumReference(filename, 0, 0, 0, true, &datum_ref);
   EXPECT_EQ(datum.channels(), datum_ref.channels());
@@ -309,38 +309,17 @@ TEST_F(IOTest, TestDecodeDatumToCVMat) {
   string filename = EXAMPLES_SOURCE_DIR "images/cat.jpg";
   Datum datum;
   EXPECT_TRUE(ReadFileToDatum(filename, &datum));
-  cv::Mat cv_img = DecodeDatumToCVMat(datum);
+  cv::Mat cv_img = DecodeDatumToCVMatNative(datum);
   EXPECT_EQ(cv_img.channels(), 3);
   EXPECT_EQ(cv_img.rows, 360);
   EXPECT_EQ(cv_img.cols, 480);
 }
 
-TEST_F(IOTest, TestDecodeDatumToCVMatResized) {
-  string filename = EXAMPLES_SOURCE_DIR "images/cat.jpg";
-  Datum datum;
-  EXPECT_TRUE(ReadFileToDatum(filename, &datum));
-  cv::Mat cv_img = DecodeDatumToCVMat(datum, 100, 200);
-  EXPECT_EQ(cv_img.channels(), 3);
-  EXPECT_EQ(cv_img.rows, 100);
-  EXPECT_EQ(cv_img.cols, 200);
-}
-
-TEST_F(IOTest, TestDecodeDatumToCVMatResizedGray) {
-  string filename = EXAMPLES_SOURCE_DIR "images/cat.jpg";
-  Datum datum;
-  EXPECT_TRUE(ReadFileToDatum(filename, &datum));
-  const bool is_color = false;
-  cv::Mat cv_img = DecodeDatumToCVMat(datum, 200, 100, is_color);
-  EXPECT_EQ(cv_img.channels(), 1);
-  EXPECT_EQ(cv_img.rows, 200);
-  EXPECT_EQ(cv_img.cols, 100);
-}
-
 TEST_F(IOTest, TestDecodeDatumToCVMatContent) {
   string filename = EXAMPLES_SOURCE_DIR "images/cat.jpg";
   Datum datum;
-  EXPECT_TRUE(ReadFileToDatum(filename, &datum));
-  cv::Mat cv_img = DecodeDatumToCVMat(datum);
+  EXPECT_TRUE(ReadImageToDatum(filename, 0, std::string("jpg"), &datum));
+  cv::Mat cv_img = DecodeDatumToCVMatNative(datum);
   cv::Mat cv_img_ref = ReadImageToCVMat(filename);
   EXPECT_EQ(cv_img_ref.channels(), cv_img.channels());
   EXPECT_EQ(cv_img_ref.rows, cv_img.rows);

diff --git a/src/caffe/util/io.cpp b/src/caffe/util/io.cpp
index f738e05..6553168 100644 (file)
--- a/src/caffe/util/io.cpp
+++ b/src/caffe/util/io.cpp
@@ -98,11 +98,36 @@ cv::Mat ReadImageToCVMat(const string& filename,
 cv::Mat ReadImageToCVMat(const string& filename) {
   return ReadImageToCVMat(filename, 0, 0, true);
 }
-
+// Do the file extension and encoding match?
+static bool matchExt(const std::string & fn,
+                     std::string en) {
+  size_t p = fn.rfind('.');
+  std::string ext = p != fn.npos ? fn.substr(p) : fn;
+  std::transform(ext.begin(), ext.end(), ext.begin(), ::tolower);
+  std::transform(en.begin(), en.end(), en.begin(), ::tolower);
+  if ( ext == en )
+    return true;
+  if ( en == "jpg" && ext == "jpeg" )
+    return true;
+  return false;
+}
 bool ReadImageToDatum(const string& filename, const int label,
-    const int height, const int width, const bool is_color, Datum* datum) {
+    const int height, const int width, const bool is_color,
+    const std::string & encoding, Datum* datum) {
   cv::Mat cv_img = ReadImageToCVMat(filename, height, width, is_color);
   if (cv_img.data) {
+    if (encoding.size()) {
+      if ( (cv_img.channels() == 3) == is_color && !height && !width &&
+          matchExt(filename, encoding) )
+        return ReadFileToDatum(filename, label, datum);
+      std::vector<uchar> buf;
+      cv::imencode("."+encoding, cv_img, buf);
+      datum->set_data(std::string(reinterpret_cast<char*>(&buf[0]),
+                      buf.size()));
+      datum->set_label(label);
+      datum->set_encoded(true);
+      return true;
+    }
     CVMatToDatum(cv_img, datum);
     datum->set_label(label);
     return true;
@@ -131,47 +156,24 @@ bool ReadFileToDatum(const string& filename, const int label,
   }
 }
 
-cv::Mat DecodeDatumToCVMat(const Datum& datum,
-    const int height, const int width, const bool is_color) {
+cv::Mat DecodeDatumToCVMatNative(const Datum& datum) {
   cv::Mat cv_img;
   CHECK(datum.encoded()) << "Datum not encoded";
-  int cv_read_flag = (is_color ? CV_LOAD_IMAGE_COLOR :
-    CV_LOAD_IMAGE_GRAYSCALE);
   const string& data = datum.data();
   std::vector<char> vec_data(data.c_str(), data.c_str() + data.size());
-  if (height > 0 && width > 0) {
-    cv::Mat cv_img_origin = cv::imdecode(cv::Mat(vec_data), cv_read_flag);
-    cv::resize(cv_img_origin, cv_img, cv::Size(width, height));
-  } else {
-    cv_img = cv::imdecode(vec_data, cv_read_flag);
-  }
+  cv_img = cv::imdecode(vec_data, -1);
   if (!cv_img.data) {
     LOG(ERROR) << "Could not decode datum ";
   }
   return cv_img;
 }
 
-cv::Mat DecodeDatumToCVMat(const Datum& datum,
-    const int height, const int width) {
-  return DecodeDatumToCVMat(datum, height, width, true);
-}
-
-cv::Mat DecodeDatumToCVMat(const Datum& datum,
-    const bool is_color) {
-  return DecodeDatumToCVMat(datum, 0, 0, is_color);
-}
-
-cv::Mat DecodeDatumToCVMat(const Datum& datum) {
-  return DecodeDatumToCVMat(datum, 0, 0, true);
-}
-
 // If Datum is encoded will decoded using DecodeDatumToCVMat and CVMatToDatum
 // if height and width are set it will resize it
 // If Datum is not encoded will do nothing
-bool DecodeDatum(const int height, const int width, const bool is_color,
-                Datum* datum) {
+bool DecodeDatumNative(Datum* datum) {
   if (datum->encoded()) {
-    cv::Mat cv_img = DecodeDatumToCVMat((*datum), height, width, is_color);
+    cv::Mat cv_img = DecodeDatumToCVMatNative((*datum));
     CVMatToDatum(cv_img, datum);
     return true;
   } else {

diff --git a/tools/compute_image_mean.cpp b/tools/compute_image_mean.cpp
index dff63a0..b1fc7ca 100644 (file)
--- a/tools/compute_image_mean.cpp
+++ b/tools/compute_image_mean.cpp
@@ -50,7 +50,7 @@ int main(int argc, char** argv) {
   Datum datum;
   datum.ParseFromString(cursor->value());
 
-  if (DecodeDatum(&datum)) {
+  if (DecodeDatumNative(&datum)) {
     LOG(INFO) << "Decoding Datum";
   }
 
@@ -68,7 +68,7 @@ int main(int argc, char** argv) {
   while (cursor->valid()) {
     Datum datum;
     datum.ParseFromString(cursor->value());
-    DecodeDatum(&datum);
+    DecodeDatumNative(&datum);
 
     const std::string& data = datum.data();
     size_in_datum = std::max<int>(datum.data().size(),

diff --git a/tools/convert_imageset.cpp b/tools/convert_imageset.cpp
index 7fbf5b0..816a91f 100644 (file)
--- a/tools/convert_imageset.cpp
+++ b/tools/convert_imageset.cpp
@@ -39,6 +39,8 @@ DEFINE_bool(check_size, false,
     "When this option is on, check that all the datum have the same size");
 DEFINE_bool(encoded, false,
     "When this option is on, the encoded image will be save in datum");
+DEFINE_string(encode_type, "",
+    "Optional: What type should we encode the image as ('png','jpg',...).");
 
 int main(int argc, char** argv) {
   ::google::InitGoogleLogging(argv[0]);
@@ -63,6 +65,7 @@ int main(int argc, char** argv) {
   const bool is_color = !FLAGS_gray;
   const bool check_size = FLAGS_check_size;
   const bool encoded = FLAGS_encoded;
+  const string encode_type = FLAGS_encode_type;
 
   std::ifstream infile(argv[2]);
   std::vector<std::pair<std::string, int> > lines;
@@ -78,11 +81,8 @@ int main(int argc, char** argv) {
   }
   LOG(INFO) << "A total of " << lines.size() << " images.";
 
-  if (encoded) {
-    CHECK_EQ(FLAGS_resize_height, 0) << "With encoded don't resize images";
-    CHECK_EQ(FLAGS_resize_width, 0) << "With encoded don't resize images";
-    CHECK(!check_size) << "With encoded cannot check_size";
-  }
+  if (encode_type.size() && !encoded)
+    LOG(INFO) << "encode_type specified, assuming encoded=true.";
 
   int resize_height = std::max<int>(0, FLAGS_resize_height);
   int resize_width = std::max<int>(0, FLAGS_resize_width);
@@ -98,18 +98,24 @@ int main(int argc, char** argv) {
   int count = 0;
   const int kMaxKeyLength = 256;
   char key_cstr[kMaxKeyLength];
-  int data_size;
+  int data_size = 0;
   bool data_size_initialized = false;
 
   for (int line_id = 0; line_id < lines.size(); ++line_id) {
     bool status;
-    if (encoded) {
-      status = ReadFileToDatum(root_folder + lines[line_id].first,
-        lines[line_id].second, &datum);
-    } else {
-      status = ReadImageToDatum(root_folder + lines[line_id].first,
-          lines[line_id].second, resize_height, resize_width, is_color, &datum);
+    std::string enc = encode_type;
+    if (encoded && !enc.size()) {
+      // Guess the encoding type from the file name
+      string fn = lines[line_id].first;
+      size_t p = fn.rfind('.');
+      if ( p == fn.npos )
+        LOG(WARNING) << "Failed to guess the encoding of '" << fn << "'";
+      enc = fn.substr(p);
+      std::transform(enc.begin(), enc.end(), enc.begin(), ::tolower);
     }
+    status = ReadImageToDatum(root_folder + lines[line_id].first,
+        lines[line_id].second, resize_height, resize_width, is_color,
+        enc, &datum);
     if (status == false) continue;
     if (check_size) {
       if (!data_size_initialized) {