remove zero initialize gradients (weight_diff, bias_diff) BVLC/caffe#…

…3254
antran89 · Apr 15, 2017 · 7b9b298 · 7b9b298
1 parent f790848
commit 7b9b298
Show file tree

Hide file tree

Showing 2 changed files with 0 additions and 6 deletions.
diff --git a/src/caffe/layers/convolution3d_layer.cpp b/src/caffe/layers/convolution3d_layer.cpp
@@ -184,7 +184,6 @@ void Convolution3DLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
 
     if (bias_term_) {
         bias_diff = this->blobs_[1]->mutable_cpu_diff();
-        memset(bias_diff, 0, sizeof(Dtype) * this->blobs_[1]->count());
         for (int n = 0; n < num_; ++n) {
             caffe_cpu_gemv<Dtype>(CblasNoTrans, num_output_, N_,
                                   1., top_diff + top[0]->offset(n),
@@ -196,7 +195,6 @@ void Convolution3DLayer<Dtype>::Backward_cpu(const vector<Blob<Dtype>*>& top,
     int weight_offset = M_ * K_;
     int top_offset = M_ * N_;
 
-    memset(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,
         // we will need to recompute them.

diff --git a/src/caffe/layers/convolution3d_layer.cu b/src/caffe/layers/convolution3d_layer.cu
@@ -81,8 +81,6 @@ void Convolution3DLayer<Dtype>::Backward_gpu (const vector<Blob<Dtype>*>& top,
 
     if (bias_term_) {
         bias_diff = this->blobs_[1]->mutable_gpu_diff();
-        CUDA_CHECK(cudaMemset(bias_diff, 0,
-                              sizeof(Dtype) * this->blobs_[1]->count()));
         // indices for calling offset function of a blob [n,c,l,h,w]
         vector<int> indices(5, 0);
         for (int n = 0; n < num_; ++n) {
@@ -97,8 +95,6 @@ void Convolution3DLayer<Dtype>::Backward_gpu (const vector<Blob<Dtype>*>& top,
     int weight_offset = M_ * K_;
     int top_offset = M_ * N_;
 
-    CUDA_CHECK(cudaMemset(weight_diff, 0,
-                          sizeof(Dtype) * this->blobs_[0]->count()));
     // indices for calling offset function of a blob [n,c,l,h,w]
     vector<int> indices(5, 0);
     for (int n = 0; n < num_; ++n) {