hchandirasekar
65 lines
1.4 KiB
C++
65 lines
1.4 KiB
C++
#include<cassert>
|
|
#include "../kernels.h"
|
|
|
|
class ReorgRT : public IPlugin {
|
|
|
|
public:
|
|
ReorgRT(int stride) {
|
|
this->stride = stride;
|
|
}
|
|
|
|
~ReorgRT(){
|
|
|
|
}
|
|
|
|
int getNbOutputs() const override {
|
|
return 1;
|
|
}
|
|
|
|
Dims getOutputDimensions(int index, const Dims* inputs, int nbInputDims) override {
|
|
return DimsCHW{inputs[0].d[0]*stride*stride, inputs[0].d[1]/stride, inputs[0].d[2]/stride};
|
|
}
|
|
|
|
void configure(const Dims* inputDims, int nbInputs, const Dims* outputDims, int nbOutputs, int maxBatchSize) override {
|
|
c = inputDims[0].d[0];
|
|
h = inputDims[0].d[1];
|
|
w = inputDims[0].d[2];
|
|
}
|
|
|
|
int initialize() override {
|
|
|
|
return 0;
|
|
}
|
|
|
|
virtual void terminate() override {
|
|
}
|
|
|
|
virtual size_t getWorkspaceSize(int maxBatchSize) const override {
|
|
return 0;
|
|
}
|
|
|
|
virtual int enqueue(int batchSize, const void*const * inputs, void** outputs, void* workspace, cudaStream_t stream) override {
|
|
|
|
reorgForward((dnnType*)reinterpret_cast<const dnnType*>(inputs[0]),
|
|
reinterpret_cast<dnnType*>(outputs[0]),
|
|
batchSize, c, h, w, stride, stream);
|
|
return 0;
|
|
}
|
|
|
|
|
|
virtual size_t getSerializationSize() override {
|
|
return 4*sizeof(int);
|
|
}
|
|
|
|
virtual void serialize(void* buffer) override {
|
|
char *buf = reinterpret_cast<char*>(buffer),*a=buf;
|
|
tk::dnn::writeBUF(buf, stride);
|
|
tk::dnn::writeBUF(buf, c);
|
|
tk::dnn::writeBUF(buf, h);
|
|
tk::dnn::writeBUF(buf, w);
|
|
assert(buf == a + getSerializationSize());
|
|
}
|
|
|
|
int c, h, w, stride;
|
|
};
|