Added Simplified Crop Layer, with fix for 0 crop.

Author: BlGene

include/caffe/layers/crop_layer.hpp

@@ -0,0 +1,49 @@
+#ifndef CAFFE_CROP_LAYER_HPP_
+#define CAFFE_CROP_LAYER_HPP_
+
+#include <utility>
+#include <vector>
+
+#include "caffe/blob.hpp"
+#include "caffe/layer.hpp"
+#include "caffe/proto/caffe.pb.h"
+
+namespace caffe {
+
+/**
+ * @brief Takes a Blob and crop it along either the width or height dimension,
+ *        outputting a cropped Blob.
+ *
+ * TODO(dox): thorough documentation for Forward, Backward, and proto params.
+ */
+
+template <typename Dtype>
+class CropLayer : public Layer<Dtype> {
+ public:
+  explicit CropLayer(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 "Crop"; }
+  virtual inline int ExactNumBottomBlobs() const { return 2; }
+  virtual inline int ExactNumTopBlobs() const { return 1; }
+
+ protected:
+  virtual void Forward_cpu(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 Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+      const vector<Blob<Dtype>*>& top);
+  virtual void Backward_gpu(const vector<Blob<Dtype>*>& top,
+      const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom);
+
+  int crop_h_, crop_w_;
+};
+
+}  // namespace caffe
+
+#endif  // CAFFE_CROP_LAYER_HPP_

src/caffe/layers/crop_layer.cpp

@@ -0,0 +1,78 @@
+#include <algorithm>
+#include <map>
+#include <set>
+#include <vector>
+
+#include "caffe/layer.hpp"
+#include "caffe/layers/crop_layer.hpp"
+#include "caffe/net.hpp"
+
+
+namespace caffe {
+
+template <typename Dtype>
+void CropLayer<Dtype>::LayerSetUp(const vector<Blob<Dtype>*>& bottom,
+    const vector<Blob<Dtype>*>& top) {
+  const CropParameter& param = this->layer_param_.crop_param();
+  CHECK_EQ(bottom.size(), 2) << "Wrong number of bottom blobs.";
+  CHECK_EQ(bottom[0]->num_axes(), 4) << "Only works with 4D blobs.";
+  CHECK_EQ(bottom[1]->num_axes(), 4) << "Only works with 4D blobs.";
+  crop_h_ = param.offset_height();
+  crop_w_ = param.offset_width();
+}
+
+template <typename Dtype>
+void CropLayer<Dtype>::Reshape(const vector<Blob<Dtype>*>& bottom,
+    const vector<Blob<Dtype>*>& top) {
+  // Check that the image we are cropping minus the margin is bigger than the
+  // destination image.
+  CHECK_GE(bottom[0]->height()-crop_h_, bottom[1]->height())
+      << "invalid offset";
+  CHECK_GE(bottom[0]->width()-crop_w_, bottom[1]->width()) << "invalid offset";
+  top[0]->Reshape(bottom[0]->num(), bottom[0]->channels(), bottom[1]->height(),
+      bottom[1]->width());
+}
+
+template <typename Dtype>
+void CropLayer<Dtype>::Forward_cpu(const vector<Blob<Dtype>*>& bottom,
+    const vector<Blob<Dtype>*>& top) {
+  const Dtype* bottom_data = bottom[0]->cpu_data();
+  Dtype* top_data = top[0]->mutable_cpu_data();
+  for (int n = 0; n < top[0]->num(); ++n) {
+    for (int c = 0; c < top[0]->channels(); ++c) {
+      for (int h = 0; h < top[0]->height(); ++h) {
+        caffe_copy(top[0]->width(),
+            bottom_data + bottom[0]->offset(n, c, crop_h_ + h, crop_w_),
+            top_data + top[0]->offset(n, c, h));
+      }
+    }
+  }
+}
+
+template <typename Dtype>
+void CropLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
+    const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
+  const Dtype* top_diff = top[0]->cpu_diff();
+  Dtype* bottom_diff = bottom[0]->mutable_cpu_diff();
+  if (propagate_down[0]) {
+    caffe_set(bottom[0]->count(), static_cast<Dtype>(0), bottom_diff);
+    for (int n = 0; n < top[0]->num(); ++n) {
+      for (int c = 0; c < top[0]->channels(); ++c) {
+        for (int h = 0; h < top[0]->height(); ++h) {
+          caffe_copy(top[0]->width(),
+              top_diff + top[0]->offset(n, c, h),
+              bottom_diff + bottom[0]->offset(n, c, crop_h_ + h, crop_w_));
+        }
+      }
+    }
+  }
+}
+
+#ifdef CPU_ONLY
+STUB_GPU(CropLayer);
+#endif
+
+INSTANTIATE_CLASS(CropLayer);
+REGISTER_LAYER_CLASS(Crop);
+
+}  // namespace caffe

src/caffe/layers/crop_layer.cu

@@ -0,0 +1,60 @@
+#include <vector>
+
+#include "caffe/layers/crop_layer.hpp"
+
+namespace caffe {
+
+// Copy (one line per thread) from one array to another, with arbitrary
+// strides in the last two dimensions.
+template <typename Dtype>
+__global__ void copy_kernel(const int n, const int height, const int width,
+    const int src_outer_stride, const int src_inner_stride,
+    const int dest_outer_stride, const int dest_inner_stride,
+    const Dtype* src, Dtype* dest) {
+  CUDA_KERNEL_LOOP(index, n) {
+    int src_start = index / height * src_outer_stride
+                  + index % height * src_inner_stride;
+    int dest_start = index / height * dest_outer_stride
+                   + index % height * dest_inner_stride;
+    for (int i = 0; i < width; ++i) {
+      dest[dest_start + i] = src[src_start + i];
+    }
+  }
+}
+
+template <typename Dtype>
+void CropLayer<Dtype>::Forward_gpu(const vector<Blob<Dtype>*>& bottom,
+    const vector<Blob<Dtype>*>& top) {
+  const Dtype* bottom_data = bottom[0]->gpu_data();
+  Dtype* top_data = top[0]->mutable_gpu_data();
+  const int lines = top[0]->count() / top[0]->width();
+
+  // NOLINT_NEXT_LINE(whitespace/operators)
+  copy_kernel<<<CAFFE_GET_BLOCKS(lines), CAFFE_CUDA_NUM_THREADS>>>(
+      lines, top[0]->height(), top[0]->width(),
+      bottom[0]->height() * bottom[0]->width(), bottom[0]->width(),
+      top[0]->height() * top[0]->width(), top[0]->width(),
+      bottom_data + bottom[0]->offset(0, 0, crop_h_, crop_w_), top_data);
+}
+
+template <typename Dtype>
+void CropLayer<Dtype>::Backward_gpu(const vector<Blob<Dtype>*>& top,
+    const vector<bool>& propagate_down, const vector<Blob<Dtype>*>& bottom) {
+  const Dtype* top_diff = top[0]->gpu_diff();
+  Dtype* bottom_diff = bottom[0]->mutable_gpu_diff();
+  const int lines = top[0]->count() / top[0]->width();
+
+  if (propagate_down[0]) {
+    caffe_gpu_set(bottom[0]->count(), static_cast<Dtype>(0), bottom_diff);
+    // NOLINT_NEXT_LINE(whitespace/operators)
+    copy_kernel<<<CAFFE_GET_BLOCKS(lines), CAFFE_CUDA_NUM_THREADS>>>(
+        lines, top[0]->height(), top[0]->width(),
+        top[0]->height() * top[0]->width(), top[0]->width(),
+        bottom[0]->height() * bottom[0]->width(), bottom[0]->width(),
+        top_diff, bottom_diff + bottom[0]->offset(0, 0, crop_h_, crop_w_));
+  }
+}
+
+INSTANTIATE_LAYER_GPU_FUNCS(CropLayer);
+
+}  // namespace caffe

src/caffe/proto/caffe.proto

@@ -309,7 +309,7 @@ message ParamSpec {
 // NOTE
 // Update the next available ID when you add a new LayerParameter field.
 //
-// LayerParameter next available layer-specific ID: 147 (last added: parse_evaluate_param)
+// LayerParameter next available layer-specific ID: 148 (last added: crop_param)
 message LayerParameter {
   optional string name = 1; // the layer name
   optional string type = 2; // the layer type
@@ -363,6 +363,7 @@ message LayerParameter {
   optional ConcatParameter concat_param = 104;
   optional ContrastiveLossParameter contrastive_loss_param = 105;
   optional ConvolutionParameter convolution_param = 106;
+  optional CropParameter crop_param = 147;
   optional DataParameter data_param = 107;
   optional DropoutParameter dropout_param = 108;
   optional DummyDataParameter dummy_data_param = 109;
@@ -539,6 +540,38 @@ message BiasParameter {
   optional FillerParameter filler = 3;
 }
 
+// Message that stores parameters used by PoolingLayer
+message BinPoolingParameter {
+  enum PoolMethod {
+    MAX = 0;
+    AVE = 1;
+    STOCHASTIC = 2;
+  }
+  optional PoolMethod pool = 1 [default = MAX]; // The pooling method
+  // Pad, kernel size, and stride are all given as a single value for equal
+  // dimensions in height and width or as Y, X pairs.
+  optional uint32 pad = 4 [default = 0]; // The padding size (equal in Y, X)
+  optional uint32 pad_h = 9 [default = 0]; // The padding height
+  optional uint32 pad_w = 10 [default = 0]; // The padding width
+  optional uint32 kernel_size = 2; // The kernel size (square)
+  optional uint32 kernel_h = 5; // The kernel height
+  optional uint32 kernel_w = 6; // The kernel width
+  optional uint32 stride = 3 [default = 1]; // The stride (equal in Y, X)
+  optional uint32 stride_h = 7; // The stride height
+  optional uint32 stride_w = 8; // The stride width
+  optional uint32 bin_size = 13; // The spatial bin #
+  optional uint32 bin_h = 14; // The spatial bin # in height direction
+  optional uint32 bin_w = 15; // The spatial bin # in width direction
+  enum Engine {
+    DEFAULT = 0;
+    CAFFE = 1;
+    CUDNN = 2;
+  }
+  optional Engine engine = 11 [default = DEFAULT];
+  // If global_pooling then it will pool over the size of the bottom by doing
+  // kernel_h = bottom->height and kernel_w = bottom->width
+  optional bool global_pooling = 12 [default = false];
+}
 message ContrastiveLossParameter {
   // margin for dissimilar pair
   optional float margin = 1 [default = 1.0];
@@ -604,6 +637,13 @@ message ConvolutionParameter {
   optional bool force_nd_im2col = 17 [default = false];
 }
 
+message CropParameter {
+    // Assumes standard dimensions: ( N,C,H,W )
+    // This could possibly be extended to  use "optional BlobShape offsets"
+    optional uint32 offset_height = 1[default = 0];
+    optional uint32 offset_width = 2[default = 0];
+}
+
 message DataParameter {
   enum DB {
     LEVELDB = 0;