added sigmoid layer

diff --git a/include/caffe/vision_layers.hpp b/include/caffe/vision_layers.hpp
index fd84866..82e52cd 100644 (file)
--- a/include/caffe/vision_layers.hpp
+++ b/include/caffe/vision_layers.hpp
@@ -46,6 +46,25 @@ class ReLULayer : public NeuronLayer<Dtype> {
 
 
 template <typename Dtype>
+class SigmoidLayer : public NeuronLayer<Dtype> {
+ public:
+  explicit SigmoidLayer(const LayerParameter& param)
+      : NeuronLayer<Dtype>(param) {}
+
+ protected:
+  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+
+  virtual Dtype Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const bool propagate_down, vector<Blob<Dtype>*>* bottom);
+  virtual Dtype Backward_gpu(const vector<Blob<Dtype>*>& top,
+      const bool propagate_down, vector<Blob<Dtype>*>* bottom);
+};
+
+
+template <typename Dtype>
 class BNLLLayer : public NeuronLayer<Dtype> {
  public:
   explicit BNLLLayer(const LayerParameter& param)

diff --git a/src/caffe/layer_factory.cpp b/src/caffe/layer_factory.cpp
index f4fb5e5..b62ba38 100644 (file)
--- a/src/caffe/layer_factory.cpp
+++ b/src/caffe/layer_factory.cpp
@@ -47,6 +47,8 @@ Layer<Dtype>* GetLayer(const LayerParameter& param) {
     return new PoolingLayer<Dtype>(param);
   } else if (type == "relu") {
     return new ReLULayer<Dtype>(param);
+  } else if (type == "sigmoid") {
+    return new SigmoidLayer<Dtype>(param);
   } else if (type == "softmax") {
     return new SoftmaxLayer<Dtype>(param);
   } else if (type == "softmax_loss") {

diff --git a/src/caffe/test/test_neuron_layer.cpp b/src/caffe/test/test_neuron_layer.cpp
index 1abee7c..8674519 100644 (file)
--- a/src/caffe/test/test_neuron_layer.cpp
+++ b/src/caffe/test/test_neuron_layer.cpp
@@ -89,6 +89,60 @@ TYPED_TEST(NeuronLayerTest, TestReLUGradientGPU) {
 }
 
 
+TYPED_TEST(NeuronLayerTest, TestSigmoidCPU) {
+  LayerParameter layer_param;
+  Caffe::set_mode(Caffe::CPU);
+  SigmoidLayer<TypeParam> layer(layer_param);
+  layer.SetUp(this->blob_bottom_vec_, &(this->blob_top_vec_));
+  layer.Forward(this->blob_bottom_vec_, &(this->blob_top_vec_));
+  // Now, check values
+  const TypeParam* bottom_data = this->blob_bottom_->cpu_data();
+  const TypeParam* top_data = this->blob_top_->cpu_data();
+  for (int i = 0; i < this->blob_bottom_->count(); ++i) {
+    EXPECT_FLOAT_EQ(top_data[i], 1. / (1 + exp(-bottom_data[i])));
+    //check that we squashed the value between 0 and 1
+    EXPECT_GE(top_data[i], 0.);
+    EXPECT_LE(top_data[i], 1.);
+  }
+}
+
+
+TYPED_TEST(NeuronLayerTest, TestSigmoidGradientCPU) {
+  LayerParameter layer_param;
+  Caffe::set_mode(Caffe::CPU);
+  SigmoidLayer<TypeParam> layer(layer_param);
+  GradientChecker<TypeParam> checker(1e-2, 1e-3, 1701, 0., 0.01);
+  checker.CheckGradientExhaustive(layer, this->blob_bottom_vec_, this->blob_top_vec_);
+}
+
+TYPED_TEST(NeuronLayerTest, TestSigmoidGPU) {
+  LayerParameter layer_param;
+  Caffe::set_mode(Caffe::GPU);
+  SigmoidLayer<TypeParam> layer(layer_param);
+  layer.SetUp(this->blob_bottom_vec_, &(this->blob_top_vec_));
+  layer.Forward(this->blob_bottom_vec_, &(this->blob_top_vec_));
+  // Now, check values
+  const TypeParam* bottom_data = this->blob_bottom_->cpu_data();
+  const TypeParam* top_data = this->blob_top_->cpu_data();
+  for (int i = 0; i < this->blob_bottom_->count(); ++i) {
+    EXPECT_FLOAT_EQ(top_data[i], 1. / (1 + exp(-bottom_data[i])));
+    //check that we squashed the value between 0 and 1
+    EXPECT_GE(top_data[i], 0.);
+    EXPECT_LE(top_data[i], 1.);
+  }
+}
+
+
+TYPED_TEST(NeuronLayerTest, TestSigmoidGradientGPU) {
+  LayerParameter layer_param;
+  Caffe::set_mode(Caffe::GPU);
+  SigmoidLayer<TypeParam> layer(layer_param);
+  GradientChecker<TypeParam> checker(1e-2, 1e-3, 1701, 0., 0.01);
+  checker.CheckGradientExhaustive(layer, this->blob_bottom_vec_, this->blob_top_vec_);
+}
+
+
+
 TYPED_TEST(NeuronLayerTest, TestDropoutCPU) {
   LayerParameter layer_param;
   Caffe::set_mode(Caffe::CPU);