Merge pull request #3591 from jeffdonahue/scale-bias-layer

Scale and Bias Layers

2 files changed, 137 insertions, 0 deletions

diff --git a/include/caffe/layers/bias_layer.hpp b/include/caffe/layers/bias_layer.hpp
new file mode 100644
index 00000000..eedc3aaa
--- /dev/null
+++ b/include/caffe/layers/bias_layer.hpp
@@ -0,0 +1,54 @@
+#ifndef CAFFE_BIAS_LAYER_HPP_
+#define CAFFE_BIAS_LAYER_HPP_
+
+#include <vector>
+
+#include "caffe/blob.hpp"
+#include "caffe/layer.hpp"
+#include "caffe/proto/caffe.pb.h"
+
+namespace caffe {
+
+/**
+ * @brief Computes a sum of two input Blobs, with the shape of the
+ *        latter Blob "broadcast" to match the shape of the former.
+ *        Equivalent to tiling the latter Blob, then computing the elementwise
+ *        sum.
+ *
+ * The second input may be omitted, in which case it's learned as a parameter
+ * of the layer.
+ */
+template <typename Dtype>
+class BiasLayer : public Layer<Dtype> {
+ public:
+  explicit BiasLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+
+  virtual inline const char* type() const { return "Bias"; }
+  virtual inline int MinBottomBlobs() const { return 1; }
+  virtual inline int MaxBottomBlobs() const { return 2; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
+  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
+
+ private:
+  Blob<Dtype> bias_multiplier_;
+  int outer_dim_, bias_dim_, inner_dim_, dim_;
+};
+
+
+
+}  // namespace caffe
+
+#endif  // CAFFE_BIAS_LAYER_HPP_
diff --git a/include/caffe/layers/scale_layer.hpp b/include/caffe/layers/scale_layer.hpp
new file mode 100644
index 00000000..924df2e5
--- /dev/null
+++ b/include/caffe/layers/scale_layer.hpp
@@ -0,0 +1,83 @@
+#ifndef CAFFE_SCALE_LAYER_HPP_
+#define CAFFE_SCALE_LAYER_HPP_
+
+#include <vector>
+
+#include "caffe/blob.hpp"
+#include "caffe/layer.hpp"
+#include "caffe/proto/caffe.pb.h"
+
+#include "caffe/layers/bias_layer.hpp"
+
+namespace caffe {
+
+/**
+ * @brief Computes a product of two input Blobs, with the shape of the
+ *        latter Blob "broadcast" to match the shape of the former.
+ *        Equivalent to tiling the latter Blob, then computing the elementwise
+ *        product.
+ *
+ * The second input may be omitted, in which case it's learned as a parameter
+ * of the layer.
+ */
+template <typename Dtype>
+class ScaleLayer: public Layer<Dtype> {
+ public:
+  explicit ScaleLayer(const LayerParameter& param)
+      : Layer<Dtype>(param) {}
+  virtual void LayerSetUp(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Reshape(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+
+  virtual inline const char* type() const { return "Scale"; }
+  // Scale
+  virtual inline int MinBottomBlobs() const { return 1; }
+  virtual inline int MaxBottomBlobs() const { return 2; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+ protected:
+  /**
+   * In the below shape specifications, @f$ i @f$ denotes the value of the
+   * `axis` field given by `this->layer_param_.scale_param().axis()`, after
+   * canonicalization (i.e., conversion from negative to positive index,
+   * if applicable).
+   *
+   * @param bottom input Blob vector (length 2)
+   *   -# @f$ (d_0 \times ... \times
+   *           d_i \times ... \times d_j \times ... \times d_n) @f$
+   *      the first factor @f$ x @f$
+   *   -# @f$ (d_i \times ... \times d_j) @f$
+   *      the second factor @f$ y @f$
+   * @param top output Blob vector (length 1)
+   *   -# @f$ (d_0 \times ... \times
+   *           d_i \times ... \times d_j \times ... \times d_n) @f$
+   *      the product @f$ z = x y @f$ computed after "broadcasting" y.
+   *      Equivalent to tiling @f$ y @f$ to have the same shape as @f$ x @f$,
+   *      then computing the elementwise product.
+   */
+  virtual void Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Backward_cpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
+  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
+
+  shared_ptr<Layer<Dtype> > bias_layer_;
+  vector<Blob<Dtype>*> bias_bottom_vec_;
+  vector<bool> bias_propagate_down_;
+  int bias_param_id_;
+
+  Blob<Dtype> sum_multiplier_;
+  Blob<Dtype> sum_result_;
+  Blob<Dtype> temp_;
+  int axis_;
+  int outer_dim_, scale_dim_, inner_dim_;
+};
+
+
+}  // namespace caffe
+
+#endif  // CAFFE_SCALE_LAYER_HPP_