在内部产品层,我需要乘以(top_diff * bottom_data) .* (2*weight)
。首先我们计算(result = top_diff * bottom_data
)作为caffe_cpu_gemm
中的矩阵乘法,然后在weight
和result
之间执行dot product
。如何在咖啡中的矩阵之间做点积?
更多的解释定义如下:
const Dtype* weight = this->blobs_[0]->cpu_data();
if (this->param_propagate_down_[0]) {
const Dtype* top_diff = top[0]->cpu_diff();
const Dtype* bottom_data = bottom[0]->cpu_data();
caffe_cpu_gemm<Dtype>(CblasTrans, CblasNoTrans, N_, K_, M_, (Dtype)1.,
top_diff, bottom_data, (Dtype)1., this->blobs_[0]->mutable_cpu_diff());
}
更多的了解,我查math_function.c
。它的实现如下:
template<>
void caffe_cpu_gemm<float>(const CBLAS_TRANSPOSE TransA,
const CBLAS_TRANSPOSE TransB, const int M, const int N, const int K,
const float alpha, const float* A, const float* B, const float beta,
float* C) {
int lda = (TransA == CblasNoTrans) ? K : M;
int ldb = (TransB == CblasNoTrans) ? N : K;
cblas_sgemm(CblasRowMajor, TransA, TransB, M, N, K, alpha, A, lda, B,
ldb, beta, C, N);
}
我觉得我应该在caffe_cpu_gemm()
执行乘法(result = top_diff * bottom_data
),之后做dot product
与weight
。我应该怎么做?!
非常感谢!任何意见,将不胜感激!