if (biasterm_) {
bias_diff = this->blobs_[1]->mutable_gpu_diff();
- CUDA_CHECK(cudaMemset(bias_diff, 0.,
+ CUDA_CHECK(cudaMemset(bias_diff, 0,
sizeof(Dtype) * this->blobs_[1]->count()));
for (int n = 0; n < NUM_; ++n) {
caffe_gpu_gemv<Dtype>(CblasNoTrans, NUM_OUTPUT_, N_,
int weight_offset = M_ * K_;
int col_offset = K_ * N_;
int top_offset = M_ * N_;
- CUDA_CHECK(cudaMemset(weight_diff, 0.,
+ CUDA_CHECK(cudaMemset(weight_diff, 0,
sizeof(Dtype) * this->blobs_[0]->count()));
for (int n = 0; n < NUM_; ++n) {
// since we saved memory in the forward pass by not storing all col data,