#include <string>
#include "caffe/blob.hpp"
-#include "caffe/common.hpp"
#include "caffe/proto/caffe.pb.h"
#include "caffe/syncedmem.hpp"
#include "caffe/util/math_functions.hpp"
// These have num == channels == 1; width is number of inputs; height is
// number of outputs. The 'sparse' variable specifies the mean number
// of non-zero input weights for a given output.
- CHECK_EQ(blob->num(), 1);
- CHECK_EQ(blob->channels(), 1);
- int num_outputs = blob->height();
+ CHECK_GE(blob->num_axes(), 1);
+ const int num_outputs = blob->shape(0);
Dtype non_zero_probability = Dtype(sparse) / Dtype(num_outputs);
rand_vec_.reset(new SyncedMemory(blob->count() * sizeof(int)));
int* mask = reinterpret_cast<int*>(rand_vec_->mutable_cpu_data());
}
};
+/*!
+@brief Fills a Blob with coefficients for bilinear interpolation.
+
+A common use case is with the DeconvolutionLayer acting as upsampling.
+You can upsample a feature map with shape of (B, C, H, W) by any integer factor
+using the following proto.
+\code
+layer {
+ name: "upsample", type: "Deconvolution"
+ bottom: "{{bottom_name}}" top: "{{top_name}}"
+ convolution_param {
+ kernel_size: {{2 * factor - factor % 2}} stride: {{factor}}
+ num_output: {{C}} group: {{C}}
+ pad: {{ceil((factor - 1) / 2.)}}
+ weight_filler: { type: "bilinear" } bias_term: false
+ }
+ param { lr_mult: 0 decay_mult: 0 }
+}
+\endcode
+Please use this by replacing `{{}}` with your values. By specifying
+`num_output: {{C}} group: {{C}}`, it behaves as
+channel-wise convolution. The filter shape of this deconvolution layer will be
+(C, 1, K, K) where K is `kernel_size`, and this filler will set a (K, K)
+interpolation kernel for every channel of the filter identically. The resulting
+shape of the top feature map will be (B, C, factor * H, factor * W).
+Note that the learning rate and the
+weight decay are set to 0 in order to keep coefficient values of bilinear
+interpolation unchanged during training. If you apply this to an image, this
+operation is equivalent to the following call in Python with Scikit.Image.
+\code{.py}
+out = skimage.transform.rescale(img, factor, mode='constant', cval=0)
+\endcode
+ */
+template <typename Dtype>
+class BilinearFiller : public Filler<Dtype> {
+ public:
+ explicit BilinearFiller(const FillerParameter& param)
+ : Filler<Dtype>(param) {}
+ virtual void Fill(Blob<Dtype>* blob) {
+ CHECK_EQ(blob->num_axes(), 4) << "Blob must be 4 dim.";
+ CHECK_EQ(blob->width(), blob->height()) << "Filter must be square";
+ Dtype* data = blob->mutable_cpu_data();
+ int f = ceil(blob->width() / 2.);
+ float c = (2 * f - 1 - f % 2) / (2. * f);
+ for (int i = 0; i < blob->count(); ++i) {
+ float x = i % blob->width();
+ float y = (i / blob->width()) % blob->height();
+ data[i] = (1 - fabs(x / f - c)) * (1 - fabs(y / f - c));
+ }
+ CHECK_EQ(this->filler_param_.sparse(), -1)
+ << "Sparsity not supported by this Filler.";
+ }
+};
+
/**
* @brief Get a specific filler from the specification given in FillerParameter.
*
return new XavierFiller<Dtype>(param);
} else if (type == "msra") {
return new MSRAFiller<Dtype>(param);
+ } else if (type == "bilinear") {
+ return new BilinearFiller<Dtype>(param);
} else {
CHECK(false) << "Unknown filler name: " << param.type();
}