Separate layers relatively independent of images out of vision_layers

diff --git a/include/caffe/common_layers.hpp b/include/caffe/common_layers.hpp
new file mode 100644 (file)
index 0000000..761c19f
--- /dev/null
+++ b/include/caffe/common_layers.hpp
@@ -0,0 +1,182 @@
+// Copyright 2014 BVLC and contributors.
+
+#ifndef CAFFE_COMMON_LAYERS_HPP_
+#define CAFFE_COMMON_LAYERS_HPP_
+
+#include <string>
+#include <utility>
+#include <vector>
+
+#include "caffe/blob.hpp"
+#include "caffe/common.hpp"
+#include "caffe/layer.hpp"
+#include "caffe/neuron_layers.hpp"
+#include "caffe/loss_layers.hpp"
+#include "caffe/data_layers.hpp"
+#include "caffe/proto/caffe.pb.h"
+
+namespace caffe {
+
+/* ArgmaxLayer
+  Compute the index of the max value across all (channels x height x width).
+  [In the future, can take specific dimension.]
+  Intended for use after a classification layer to produce prediction.
+  If parameter out_max_val is set to true, then output is a vector of pairs
+  (max_ind, max_val) for each image.
+
+  NOTE: does not implement Backwards operation.
+*/
+template <typename Dtype>
+class ArgMaxLayer : public Layer<Dtype> {
+ public:
+  explicit ArgMaxLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+
+  virtual inline LayerParameter_LayerType type() const {
+    return LayerParameter_LayerType_ARGMAX;
+  }
+  virtual inline int ExactNumBottomBlobs() const { return 1; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+ protected:
+  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom) {
+    NOT_IMPLEMENTED;
+  }
+  bool out_max_val_;
+};
+
+/* ConcatLayer
+  Takes at least two blobs and concatenates them along either num or
+  channel dim, outputting the result.
+*/
+template <typename Dtype>
+class ConcatLayer : public Layer<Dtype> {
+ public:
+  explicit ConcatLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+
+  virtual inline LayerParameter_LayerType type() const {
+    return LayerParameter_LayerType_CONCAT;
+  }
+  virtual inline int MinBottomBlobs() const { return 2; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+ protected:
+  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+
+  Blob<Dtype> col_bob_;
+  int count_;
+  int num_;
+  int channels_;
+  int height_;
+  int width_;
+  int concat_dim_;
+};
+
+/* FlattenLayer
+*/
+template <typename Dtype>
+class FlattenLayer : public Layer<Dtype> {
+ public:
+  explicit FlattenLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+
+  virtual inline LayerParameter_LayerType type() const {
+    return LayerParameter_LayerType_FLATTEN;
+  }
+  virtual inline int ExactNumBottomBlobs() const { return 1; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+ protected:
+  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+
+  int count_;
+};
+
+/* SoftmaxLayer
+*/
+template <typename Dtype>
+class SoftmaxLayer : public Layer<Dtype> {
+ public:
+  explicit SoftmaxLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+
+  virtual inline LayerParameter_LayerType type() const {
+    return LayerParameter_LayerType_SOFTMAX;
+  }
+  virtual inline int ExactNumBottomBlobs() const { return 1; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+ protected:
+  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
+     const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+
+  // sum_multiplier is just used to carry out sum using blas
+  Blob<Dtype> sum_multiplier_;
+  // scale is an intermediate blob to hold temporary results.
+  Blob<Dtype> scale_;
+};
+
+/* SplitLayer
+*/
+template <typename Dtype>
+class SplitLayer : public Layer<Dtype> {
+ public:
+  explicit SplitLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+
+  virtual inline LayerParameter_LayerType type() const {
+    return LayerParameter_LayerType_SPLIT;
+  }
+  virtual inline int ExactNumBottomBlobs() const { return 1; }
+  virtual inline int MinTopBlobs() const { return 1; }
+
+ protected:
+  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      vector<Blob<Dtype>*>* top);
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
+
+  int count_;
+};
+
+}  // namespace caffe
+
+#endif  // CAFFE_COMMON_LAYERS_HPP_

diff --git a/include/caffe/vision_layers.hpp b/include/caffe/vision_layers.hpp
index b68dcbf..ef04772 100644 (file)
--- a/include/caffe/vision_layers.hpp
+++ b/include/caffe/vision_layers.hpp
@@ -9,84 +9,15 @@
 
 #include "caffe/blob.hpp"
 #include "caffe/common.hpp"
+#include "caffe/common_layers.hpp"
+#include "caffe/data_layers.hpp"
 #include "caffe/layer.hpp"
-#include "caffe/neuron_layers.hpp"
 #include "caffe/loss_layers.hpp"
-#include "caffe/data_layers.hpp"
+#include "caffe/neuron_layers.hpp"
 #include "caffe/proto/caffe.pb.h"
 
 namespace caffe {
 
-/* ArgmaxLayer
-  Compute the index of the max value across all (channels x height x width).
-  [In the future, can take specific dimension.]
-  Intended for use after a classification layer to produce prediction.
-  If parameter out_max_val is set to true, then output is a vector of pairs
-  (max_ind, max_val) for each image.
-
-  NOTE: does not implement Backwards operation.
-*/
-template <typename Dtype>
-class ArgMaxLayer : public Layer<Dtype> {
- public:
-  explicit ArgMaxLayer(const LayerParameter& param)
-      : Layer<Dtype>(param) {}
-  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-
-  virtual inline LayerParameter_LayerType type() const {
-    return LayerParameter_LayerType_ARGMAX;
-  }
-  virtual inline int ExactNumBottomBlobs() const { return 1; }
-  virtual inline int ExactNumTopBlobs() const { return 1; }
-
- protected:
-  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom) {
-    NOT_IMPLEMENTED;
-  }
-  bool out_max_val_;
-};
-
-/* ConcatLayer
-  Takes at least two blobs and concatenates them along either num or
-  channel dim, outputting the result.
-*/
-template <typename Dtype>
-class ConcatLayer : public Layer<Dtype> {
- public:
-  explicit ConcatLayer(const LayerParameter& param)
-      : Layer<Dtype>(param) {}
-  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-
-  virtual inline LayerParameter_LayerType type() const {
-    return LayerParameter_LayerType_CONCAT;
-  }
-  virtual inline int MinBottomBlobs() const { return 2; }
-  virtual inline int ExactNumTopBlobs() const { return 1; }
-
- protected:
-  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-
-  Blob<Dtype> col_bob_;
-  int count_;
-  int num_;
-  int channels_;
-  int height_;
-  int width_;
-  int concat_dim_;
-};
-
 /* ConvolutionLayer
 */
 template <typename Dtype>
@@ -161,35 +92,6 @@ class EltwiseLayer : public Layer<Dtype> {
   vector<Dtype> coeffs_;
 };
 
-/* FlattenLayer
-*/
-template <typename Dtype>
-class FlattenLayer : public Layer<Dtype> {
- public:
-  explicit FlattenLayer(const LayerParameter& param)
-      : Layer<Dtype>(param) {}
-  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-
-  virtual inline LayerParameter_LayerType type() const {
-    return LayerParameter_LayerType_FLATTEN;
-  }
-  virtual inline int ExactNumBottomBlobs() const { return 1; }
-  virtual inline int ExactNumTopBlobs() const { return 1; }
-
- protected:
-  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-
-  int count_;
-};
-
 /* Im2colLayer
 */
 template <typename Dtype>
@@ -373,67 +275,6 @@ class PoolingLayer : public Layer<Dtype> {
   shared_ptr<Blob<int> > max_idx_;
 };
 
-/* SoftmaxLayer
-*/
-template <typename Dtype>
-class SoftmaxLayer : public Layer<Dtype> {
- public:
-  explicit SoftmaxLayer(const LayerParameter& param)
-      : Layer<Dtype>(param) {}
-  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-
-  virtual inline LayerParameter_LayerType type() const {
-    return LayerParameter_LayerType_SOFTMAX;
-  }
-  virtual inline int ExactNumBottomBlobs() const { return 1; }
-  virtual inline int ExactNumTopBlobs() const { return 1; }
-
- protected:
-  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
-     const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-
-  // sum_multiplier is just used to carry out sum using blas
-  Blob<Dtype> sum_multiplier_;
-  // scale is an intermediate blob to hold temporary results.
-  Blob<Dtype> scale_;
-};
-
-/* SplitLayer
-*/
-template <typename Dtype>
-class SplitLayer : public Layer<Dtype> {
- public:
-  explicit SplitLayer(const LayerParameter& param)
-      : Layer<Dtype>(param) {}
-  virtual void SetUp(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-
-  virtual inline LayerParameter_LayerType type() const {
-    return LayerParameter_LayerType_SPLIT;
-  }
-  virtual inline int ExactNumBottomBlobs() const { return 1; }
-  virtual inline int MinTopBlobs() const { return 1; }
-
- protected:
-  virtual Dtype Forward_cpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual Dtype Forward_gpu(const vector<Blob<Dtype>*>& bottom,
-      vector<Blob<Dtype>*>* top);
-  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
-      const vector<bool>& propagate_down, vector<Blob<Dtype>*>* bottom);
-
-  int count_;
-};
-
 }  // namespace caffe
 
 #endif  // CAFFE_VISION_LAYERS_HPP_