updates

diff --git a/src/caffeine/blob.cpp b/src/caffeine/blob.cpp
index 0c16be6..2c5f724 100644 (file)
--- a/src/caffeine/blob.cpp
+++ b/src/caffeine/blob.cpp
@@ -7,25 +7,25 @@
 namespace caffeine {
 
 template <typename Dtype>
-void Blob<Dtype>::Reshape(const int num, const int height,
-    const int width, const int channels) {
+void Blob<Dtype>::Reshape(const int num, const int channels, const int height,
+    const int width) {
   CHECK_GT(num, 0);
+  CHECK_GT(channels, 0);
   CHECK_GT(height, 0);
   CHECK_GT(width, 0);
-  CHECK_GT(channels, 0);
   num_ = num;
+  channels_ = channels;
   height_ = height;
   width_ = width;
-  channels_ = channels;
-  count_ = num_ * height_ * width_ * channels_;
+  count_ = num_ * channels_ * height_ * width_;
   data_.reset(new SyncedMemory(count_ * sizeof(Dtype)));
   diff_.reset(new SyncedMemory(count_ * sizeof(Dtype)));
 }
 
 template <typename Dtype>
-Blob<Dtype>::Blob(const int num, const int height,
-    const int width, const int channels) {
-  Reshape(num, height, width, channels);
+Blob<Dtype>::Blob(const int num, const int channels, const int height,
+    const int width) {
+  Reshape(num, channels, height, width);
 }
 
 template <typename Dtype>
@@ -33,7 +33,7 @@ Blob<Dtype>::Blob(const Blob<Dtype>& source) {
   if (source.count() == 0) {
     Blob();
   } else {
-    Reshape(source.num(), source.height(), source.width(), source.count());
+    Reshape(source.num(), source.channels(), source.height(), source.width());
     // create the synced memories.
     data_.reset(new SyncedMemory(count_ * sizeof(Dtype)));
     diff_.reset(new SyncedMemory(count_ * sizeof(Dtype)));
@@ -99,7 +99,7 @@ void Blob<Dtype>::Update() {
 
 template <typename Dtype>
 void Blob<Dtype>::FromProto(const BlobProto& proto) {
-  Reshape(proto.num(), proto.height(), proto.width(), proto.channels());
+  Reshape(proto.num(), proto.channels(), proto.height(), proto.width());
   // copy data
   Dtype* data_vec = mutable_cpu_data();
   for (int i = 0; i < count_; ++i) {
@@ -114,9 +114,9 @@ void Blob<Dtype>::FromProto(const BlobProto& proto) {
 template <typename Dtype>
 void Blob<Dtype>::ToProto(BlobProto* proto) {
   proto->set_num(num_);
+  proto->set_channels(channels_);
   proto->set_height(height_);
   proto->set_width(width_);
-  proto->set_channels(channels_);
   proto->clear_data();
   proto->clear_diff();
   const Dtype* data_vec = cpu_data();

diff --git a/src/caffeine/blob.hpp b/src/caffeine/blob.hpp
index 12e3825..42b3d96 100644 (file)
--- a/src/caffeine/blob.hpp
+++ b/src/caffeine/blob.hpp
@@ -13,16 +13,16 @@ class Blob {
   Blob()
        : num_(0), channels_(0), height_(0), width_(0), count_(0), data_(),
        diff_() {};
-  explicit Blob(const int num, const int height,
-    const int width, const int channels);
+  explicit Blob(const int num, const int channels, const int height,
+    const int width);
   Blob(const Blob<Dtype>& source);
   virtual ~Blob() {};
   void Reshape(const int num, const int height,
       const int width, const int channels);
   inline int num() const { return num_; }
+  inline int channels() const { return channels_; }
   inline int height() const { return height_; }
   inline int width() const { return width_; }
-  inline int channels() const { return channels_; }
   inline int count() const {return count_; }
   
   const Dtype* cpu_data() const;
@@ -40,9 +40,9 @@ class Blob {
   shared_ptr<SyncedMemory> data_;
   shared_ptr<SyncedMemory> diff_;
   int num_;
+  int channels_;
   int height_;
   int width_;
-  int channels_;
   int count_;
 };  // class Blob
 

diff --git a/src/caffeine/layers/inner_product_layer.cu b/src/caffeine/layers/inner_product_layer.cu
index 88dd41c..8130dcc 100644 (file)
--- a/src/caffeine/layers/inner_product_layer.cu
+++ b/src/caffeine/layers/inner_product_layer.cu
@@ -15,21 +15,12 @@ void InnerProductLayer<Dtype>::SetUp(const vector<Blob<Dtype>*>& bottom,
   CHECK_EQ(bottom.size(), 1) << "IP Layer takes a single blob as input.";
   CHECK_EQ(top->size(), 1) << "IP Layer takes a single blob as output.";
   const int num_output = this->layer_param_.num_output();
-  const bool gemm_last_dim = this->layer_param_.gemm_last_dim();
   biasterm_ = this->layer_param_.biasterm();
   // Figure out the dimensions
-  if (gemm_last_dim) {
-    M_ = bottom[0]->count() / bottom[0]->channels();
-    K_ = bottom[0]->channels();
-    N_ = num_output;
-    (*top)[0]->Reshape(bottom[0]->num(), bottom[0]->height(),
-        bottom[0]->width(), num_output);
-  } else {
-    M_ = bottom[0]->num();
-    K_ = bottom[0]->count() / bottom[0]->num();
-    N_ = num_output;
-    (*top)[0]->Reshape(bottom[0]->num(), 1, 1, num_output);
-  }
+  M_ = bottom[0]->num();
+  K_ = bottom[0]->count() / bottom[0]->num();
+  N_ = num_output;
+  (*top)[0]->Reshape(bottom[0]->num(), num_output, 1, 1);
   if (biasterm_) {
     this->blobs_.resize(2);
   } else {
@@ -98,10 +89,8 @@ template <typename Dtype>
 Dtype InnerProductLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
     const bool propagate_down,
     vector<Blob<Dtype>*>* bottom) {
-  // TODO: gradient w.r.t the params
-  if (propagate_down) {
-    // TODO: gradient w.r.t. the bottom
-  }
+  const Dtype* top_diff = top[0]->cpu_diff();
+  CHECK(false);
   return Dtype(0);
 }
 

diff --git a/src/caffeine/proto/layer_param.proto b/src/caffeine/proto/layer_param.proto
index e921665..806c405 100644 (file)
--- a/src/caffeine/proto/layer_param.proto
+++ b/src/caffeine/proto/layer_param.proto
@@ -1,5 +1,25 @@
 package caffeine;
 
+message BlobProto {
+  optional int32 num = 1 [default = 0];
+  optional int32 height = 2 [default = 0];
+  optional int32 width = 3 [default = 0];
+  optional int32 channels = 4 [default = 0];
+  repeated float data = 5;
+  repeated float diff = 6;
+}
+
+message FillerParameter {
+  // The filler type. In default we will set it to Gaussian for easy
+  // debugging.
+  required string type = 1 [default = 'gaussian'];
+  optional float value = 2 [default = 0]; // the value in constant filler
+  optional float min = 3 [default = 0]; // the min value in uniform filler
+  optional float max = 4 [default = 1]; // the max value in uniform filler
+  optional float mean = 5 [default = 0]; // the mean value in gaussian filler
+  optional float std = 6 [default = 1]; // the std value in gaussian filler
+}
+
 message LayerParameter {
   required string name = 1; // the layer name
   required string type = 2; // the string to specify the layer type
@@ -20,27 +40,5 @@ message LayerParameter {
   optional float alpha = 13 [default = 1.]; // for local response norm
   optional float beta = 14 [default = 0.75]; // for local response norm
 
-  // for innerproduct: if true, carry out inner product computation on the
-  // last dim only
-  optional bool gemm_last_dim = 15 [ default = false];
-}
-
-message FillerParameter {
-  // The filler type. In default we will set it to Gaussian for easy
-  // debugging.
-  required string type = 1 [default = 'gaussian'];
-  optional float value = 2 [default = 0]; // the value in constant filler
-  optional float min = 3 [default = 0]; // the min value in uniform filler
-  optional float max = 4 [default = 1]; // the max value in uniform filler
-  optional float mean = 5 [default = 0]; // the mean value in gaussian filler
-  optional float std = 6 [default = 1]; // the std value in gaussian filler
-}
-
-message BlobProto {
-  optional int32 num = 1 [default = 0];
-  optional int32 height = 2 [default = 0];
-  optional int32 width = 3 [default = 0];
-  optional int32 channels = 4 [default = 0];
-  repeated float data = 5;
-  repeated float diff = 6;
+  repeated BlobProto blobs = 50; // for possible data.
 }

diff --git a/src/caffeine/test/test_blob.cpp b/src/caffeine/test/test_blob.cpp
index edb8bbe..308d6bd 100644 (file)
--- a/src/caffeine/test/test_blob.cpp
+++ b/src/caffeine/test/test_blob.cpp
@@ -26,9 +26,9 @@ TYPED_TEST(BlobSimpleTest, TestInitialization) {
   EXPECT_TRUE(this->blob_);
   EXPECT_TRUE(this->blob_preshaped_);
   EXPECT_EQ(this->blob_preshaped_->num(), 2);
-  EXPECT_EQ(this->blob_preshaped_->height(), 3);
-  EXPECT_EQ(this->blob_preshaped_->width(), 4);
-  EXPECT_EQ(this->blob_preshaped_->channels(), 5);
+  EXPECT_EQ(this->blob_preshaped_->channels(), 3);
+  EXPECT_EQ(this->blob_preshaped_->height(), 4);
+  EXPECT_EQ(this->blob_preshaped_->width(), 5);
   EXPECT_EQ(this->blob_preshaped_->count(), 120);
   EXPECT_EQ(this->blob_->num(), 0);
   EXPECT_EQ(this->blob_->channels(), 0);
@@ -47,9 +47,9 @@ TYPED_TEST(BlobSimpleTest, TestPointers) {
 TYPED_TEST(BlobSimpleTest, TestReshape) {
   this->blob_->Reshape(2, 3, 4, 5);
   EXPECT_EQ(this->blob_->num(), 2);
-  EXPECT_EQ(this->blob_->height(), 3);
-  EXPECT_EQ(this->blob_->width(), 4);
-  EXPECT_EQ(this->blob_->channels(), 5);
+  EXPECT_EQ(this->blob_->channels(), 3);
+  EXPECT_EQ(this->blob_->height(), 4);
+  EXPECT_EQ(this->blob_->width(), 5);
   EXPECT_EQ(this->blob_->count(), 120);
 }
 
@@ -61,6 +61,11 @@ TYPED_TEST(BlobSimpleTest, TestCopyConstructor) {
   Blob<TypeParam> target(source);
   const TypeParam* source_data = source.cpu_data();
   const TypeParam* target_data = target.cpu_data();
+  EXPECT_EQ(target.num(), source.num());
+  EXPECT_EQ(target.channels(), source.channels());
+  EXPECT_EQ(target.height(), source.height());
+  EXPECT_EQ(target.width(), source.width());
+  EXPECT_EQ(target.count(), source.count());
   for (int i = 0; i < source.count(); ++i) {
     EXPECT_EQ(source_data[i], target_data[i]);
   }

diff --git a/src/caffeine/test/test_caffeine_main.cpp b/src/caffeine/test/test_caffeine_main.cpp
index c430105..2c8042c 100644 (file)
--- a/src/caffeine/test/test_caffeine_main.cpp
+++ b/src/caffeine/test/test_caffeine_main.cpp
@@ -1,14 +1,20 @@
-#include <iostream>
 #include <cstdlib>
+#include <cstdio>
+#include <iostream>
 
 #include <cuda_runtime.h>
 #include <glog/logging.h>
 #include <gtest/gtest.h>
 
-using namespace std;
+namespace caffeine {
 
 cudaDeviceProp CAFFEINE_TEST_CUDA_PROP;
 
+}  // namespace caffeine
+
+using namespace caffeine;
+using namespace std;
+
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);
   ::google::InitGoogleLogging(argv[0]);
@@ -47,3 +53,4 @@ int main(int argc, char** argv) {
   
   return RUN_ALL_TESTS();
 }
+

diff --git a/src/caffeine/test/test_innerproduct_layer.cpp b/src/caffeine/test/test_innerproduct_layer.cpp
index 820d56c..1a43750 100644 (file)
--- a/src/caffeine/test/test_innerproduct_layer.cpp
+++ b/src/caffeine/test/test_innerproduct_layer.cpp
@@ -7,9 +7,9 @@
 #include "caffeine/filler.hpp"
 #include "caffeine/vision_layers.hpp"
 
-extern cudaDeviceProp CAFFEINE_TEST_CUDA_PROP;
-
 namespace caffeine {
+
+extern cudaDeviceProp CAFFEINE_TEST_CUDA_PROP;
   
 template <typename Dtype>
 class InnerProductLayerTest : public ::testing::Test {
@@ -44,13 +44,6 @@ TYPED_TEST(InnerProductLayerTest, TestSetUp) {
   EXPECT_EQ(this->blob_top_->height(), 1);
   EXPECT_EQ(this->blob_top_->width(), 1);
   EXPECT_EQ(this->blob_top_->channels(), 10);
-  layer_param.set_gemm_last_dim(true);
-  layer.reset(new InnerProductLayer<TypeParam>(layer_param));
-  layer->SetUp(this->blob_bottom_vec_, &(this->blob_top_vec_));
-  EXPECT_EQ(this->blob_top_->num(), 2);
-  EXPECT_EQ(this->blob_top_->height(), 3);
-  EXPECT_EQ(this->blob_top_->width(), 4);
-  EXPECT_EQ(this->blob_top_->channels(), 10);
 }
 
 TYPED_TEST(InnerProductLayerTest, TestCPU) {

diff --git a/src/caffeine/test/test_neuron_layer.cpp b/src/caffeine/test/test_neuron_layer.cpp
index 45c52c3..a634a3a 100644 (file)
--- a/src/caffeine/test/test_neuron_layer.cpp
+++ b/src/caffeine/test/test_neuron_layer.cpp
@@ -8,7 +8,10 @@
 #include "caffeine/vision_layers.hpp"
 #include "caffeine/test/test_gradient_check_util.hpp"
 
+
 namespace caffeine {
+
+extern cudaDeviceProp CAFFEINE_TEST_CUDA_PROP;
   
 template <typename Dtype>
 class NeuronLayerTest : public ::testing::Test {
@@ -150,11 +153,15 @@ TYPED_TEST(NeuronLayerTest, TestDropoutGPU) {
 
 
 TYPED_TEST(NeuronLayerTest, TestDropoutGradientGPU) {
-  LayerParameter layer_param;
-  Caffeine::set_mode(Caffeine::GPU);
-  DropoutLayer<TypeParam> layer(layer_param);
-  GradientChecker<TypeParam> checker(1e-2, 1e-3);
-  checker.CheckGradient(layer, this->blob_bottom_vec_, this->blob_top_vec_);
+  if (CAFFEINE_TEST_CUDA_PROP.major >= 2) {
+    LayerParameter layer_param;
+    Caffeine::set_mode(Caffeine::GPU);
+    DropoutLayer<TypeParam> layer(layer_param);
+    GradientChecker<TypeParam> checker(1e-2, 1e-3);
+    checker.CheckGradient(layer, this->blob_bottom_vec_, this->blob_top_vec_);
+  } else {
+    LOG(ERROR) << "Skipping test to spare my laptop.";
+  }
 }