saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix 3828 (#3837)

Browse source
This commit is contained in:
Hariharan Seshadri 2020-05-06 00:05:15 -07:00 committed by GitHub
parent f0c9fbc051
commit b45ce92542
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 28 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

56
onnxruntime/core/providers/cuda/nn/conv.cc
View file

@ -166,40 +166,40 @@ Status Conv<T>::ComputeInternal(OpKernelContext* context) const {
s_.algo = perf.algo;
s_.workspace_bytes = perf.memory;
}
}
if (!y_data) {
Tensor* Y = context->Output(0, TensorShape(s_.y_dims));
// special case when there is a dim value of 0 in the shape.
if (Y->Shape().Size() == 0)
return Status::OK();
if (!y_data) {
Tensor* Y = context->Output(0, TensorShape(s_.y_dims));
// special case when there is a dim value of 0 in the shape.
if (Y->Shape().Size() == 0)
return Status::OK();
y_data = reinterpret_cast<CudaT*>(Y->template MutableData<T>());
}
y_data = reinterpret_cast<CudaT*>(Y->template MutableData<T>());
}
const auto alpha = Consts<CudaT>::One;
const auto beta = Consts<CudaT>::Zero;
const auto alpha = Consts<CudaT>::One;
const auto beta = Consts<CudaT>::Zero;
IAllocatorUniquePtr<void> workspace = GetScratchBuffer<void>(s_.workspace_bytes);
IAllocatorUniquePtr<void> workspace = GetScratchBuffer<void>(s_.workspace_bytes);
CUDNN_RETURN_IF_ERROR(cudnnConvolutionForward(CudnnHandle(),
&alpha,
s_.x_tensor,
x_data,
s_.filter_desc,
w_data,
s_.conv_desc,
s_.algo,
workspace.get(),
s_.workspace_bytes,
&beta,
s_.y_tensor,
y_data));
CUDNN_RETURN_IF_ERROR(cudnnConvolutionForward(CudnnHandle(),
&alpha,
s_.x_tensor,
x_data,
s_.filter_desc,
w_data,
s_.conv_desc,
s_.algo,
workspace.get(),
s_.workspace_bytes,
&beta,
s_.y_tensor,
y_data));
if (has_bias) {
const Tensor* B = context->Input<Tensor>(2);
auto b_data = reinterpret_cast<const CudaT*>(B->template Data<T>());
CUDNN_RETURN_IF_ERROR(cudnnAddTensor(CudnnHandle(), &alpha, s_.b_tensor, b_data, &alpha, s_.y_tensor, y_data));
if (has_bias) {
const Tensor* B = context->Input<Tensor>(2);
auto b_data = reinterpret_cast<const CudaT*>(B->template Data<T>());
CUDNN_RETURN_IF_ERROR(cudnnAddTensor(CudnnHandle(), &alpha, s_.b_tensor, b_data, &alpha, s_.y_tensor, y_data));
}
}
return Status::OK();