diff --git a/include/aidge/backend/cpu/operator/ConvImpl.hpp b/include/aidge/backend/cpu/operator/ConvImpl.hpp
index c06d0912f419909013f930867ce3c3238c1a5555..41784ac96f4345aa2653e40d1fd575efa284e3b7 100644
--- a/include/aidge/backend/cpu/operator/ConvImpl.hpp
+++ b/include/aidge/backend/cpu/operator/ConvImpl.hpp
@@ -26,16 +26,16 @@
namespace Aidge {
// Operator implementation entry point for the backend
using Conv1D_Op = Conv_Op<1>;
-using ConvImpl1D_cpu = OperatorImpl_cpu<Conv_Op<1>,
- void(const std::array<DimSize_t, 1>&,
- const std::array<DimSize_t, 1>&,
- const std::array<DimSize_t, 1>&,
- const std::array<DimSize_t, 3> &,
- DimSize_t,
- const void *,
- const void *,
- const void *,
- void *)>;
+using ConvImpl1D_cpu = OperatorImpl_cpu<Conv1D_Op,
+ void(const DimSize_t &,
+ const DimSize_t &,
+ const DimSize_t &,
+ const std::array<DimSize_t, 3> &,
+ DimSize_t,
+ const void *,
+ const void *,
+ const void *,
+ void *),
using Conv2D_Op = Conv_Op<2>;
using ConvImpl2D_cpu = OperatorImpl_cpu<Conv_Op<2>,
diff --git a/include/aidge/backend/cpu/operator/ConvImpl_kernels.hpp b/include/aidge/backend/cpu/operator/ConvImpl_kernels.hpp
index 1229d5714e6b0cbae4e42ece9130c2c2305f133e..93230f54713ad7063ffbcd76f0a4545035fd5267 100644
--- a/include/aidge/backend/cpu/operator/ConvImpl_kernels.hpp
+++ b/include/aidge/backend/cpu/operator/ConvImpl_kernels.hpp
@@ -39,16 +39,15 @@ namespace Aidge {
* @param output_ Output Tensor.
*/
template <class I, class W, class B, class O>
-void ConvImpl1D_cpu_forward_kernel(const std::array<DimSize_t, 1>& strideDims,
- const std::array<DimSize_t, 1>& dilationDims,
- const std::array<DimSize_t, 1>& kernelDims,
- const std::array<DimSize_t, 3>& inputDims,
- DimSize_t outChannels,
- const void *input_,
- const void *weights_,
- const void *biases_,
- void *output_)
-{
+void ConvImpl1D_cpu_forward_kernel(const DimSize_t &strideDim,
+ const DimSize_t &dilationDim,
+ const DimSize_t &kernelDim,
+ const std::array<DimSize_t, 3> &inputDims,
+ DimSize_t outChannels,
+ const void *input_,
+ const void *weights_,
+ const void *biases_,
+ void *output_) {
// FIXME: missing convolution attributes as arguments
const I *input = static_cast<const I *>(input_);
const W *weights = static_cast<const W *>(weights_);
@@ -56,34 +55,51 @@ void ConvImpl1D_cpu_forward_kernel(const std::array<DimSize_t, 1>& strideDims,
O *output = static_cast<O *>(output_);
// output H size
- const std::size_t oxSize =
- static_cast<std::size_t>(std::floor(static_cast<float>(inputDims[2] - dilationDims[0]*(kernelDims[0] - 1) - 1 + strideDims[0]) /
- static_cast<float>(strideDims[0])));
- const DimSize_t dilated_kernel_x = dilationDims[0]*(kernelDims[0] - 1) + 1;
+ const std::size_t oxSize = static_cast<std::size_t>(std::floor(
+ static_cast<float>(inputDims[2] - dilationDim * (kernelDim - 1) - 1 +
+ strideDim) /
+ static_cast<float>(strideDim)));
+ const DimSize_t dilated_kernel_x = dilationDim * (kernelDim - 1) + 1;
- // TODO: kernel computation
- // output (batch, outCh, Xout, Yout)
- // input (batch, inCh, Xin, Yin)
- // weight (outCh, inCh, kernelX, kernelY)
- // does not take Dilation attribute into account
using signedsize = std::make_signed<std::size_t>::type;
for (std::size_t batch = 0; batch < inputDims[0]; ++batch) {
for (std::size_t outCh = 0; outCh < outChannels; ++outCh) {
- const std::size_t oIndex = (outCh + batch*outChannels) * oxSize;
+ const std::size_t oIndex = (outCh + batch * outChannels) * oxSize;
// If bias = nullptr, set B(0)
B biasVal = (biases != nullptr) ? biases[outCh] : B(0);
- std::fill(output + oIndex, output+(oIndex+oxSize), biasVal);
+ std::fill(output + oIndex, output + (oIndex + oxSize), biasVal);
for (std::size_t inCh = 0; inCh < inputDims[1]; ++inCh) {
- const std::size_t iIndex = (inCh + batch*inputDims[1]) * inputDims[2];
- const std::size_t wIndex = (inCh + outCh*inputDims[1]) * kernelDims[0];
+ const std::size_t iIndex =
+ (inCh + batch * inputDims[1]) * inputDims[2];
+ const std::size_t wIndex =
+ (inCh + outCh * inputDims[1]) * kernelDim;
for (std::size_t ox = 0; ox < oxSize; ++ox) {
- // const signedsize difx = static_cast<signedsize>(- ox * strideDims[0]);
- // const std::size_t sxMin = static_cast<std::size_t>(std::max(difx, signedsize(0)));
- // const std::size_t sxMax = (static_cast<signedsize>(inputDims[2]) + difx) < 0 ? 0 : ((inputDims[2] + difx) > kernelDims[0] ? kernelDims[0] : inputDims[2] + difx);
+ // const signedsize difx = static_cast<signedsize>(- ox *
+ // strideDims); const std::size_t sxMin =
+ // static_cast<std::size_t>(std::max(difx, signedsize(0)));
+ // const std::size_t sxMax =
+ // (static_cast<signedsize>(inputDims[2]) + difx) < 0 ? 0 :
+ // ((inputDims[2] + difx) > kernelDims[0] ? kernelDims :
+ // inputDims[2] + difx);
const std::size_t sxMin = 0;
const std::size_t sxMax = dilated_kernel_x;
const std::size_t oIndexFull = oIndex + ox;
- const signedsize ix = static_cast<signedsize>(ox * strideDims[0]);
+ const signedsize ix =
+ static_cast<signedsize>(ox * strideDim);
+
+ for (std::size_t sx = sxMin; sx * dilationDim < sxMax;
+ ++sx) {
+ output[oIndexFull] +=
+ weights[wIndex + sx] *
+ input[iIndex + static_cast<std::size_t>(
+ ix + static_cast<signedsize>(
+ sx * dilationDim))];
+ }
+ }
+ }
+ }
+ }
+}
for (std::size_t sx = sxMin; sx*dilationDims[0] < sxMax; ++sx) {
output[oIndexFull] += weights[wIndex + sx] *
diff --git a/src/operator/ConvImpl.cpp b/src/operator/ConvImpl.cpp
index fdfe19fbf4bf3e71c86aa28b966cfb21a1b5ba40..20f03708c00741992eb24064face411149af4662 100644
--- a/src/operator/ConvImpl.cpp
+++ b/src/operator/ConvImpl.cpp
@@ -43,16 +43,17 @@ void Aidge::ConvImpl1D_cpu::forward() {
const auto& input2 = (op_.getInput(2)) ? op_.getInput(2)->refCastFrom(input2Fallback, *op_.getOutput(0)) : Tensor();
// Call kernel
- impl.forward(op_.strideDims(),
- op_.dilationDims(),
- op_.kernelDims(),
- op_.getInput(0)->template dims<3>(), // input dimensions
- dynamic_cast<const Conv_Op<1>&>(mOp).outChannels(), // outChannels
- input0.getImpl()->rawPtr(), // input
- input1.getImpl()->rawPtr(), // weight
- op_.getInput(2) ? input2.getImpl()->rawPtr() : nullptr, // bias
- getCPUPtr(mOp.getRawOutput(0)) // output
- );
+ impl.forward(
+ op_.strideDims()[0],
+ op_.dilationDims()[0],
+ op_.kernelDims()[0],
+ op_.getInput(0)->template dims<3>(), // input dimensions
+ dynamic_cast<const Conv_Op<1> &>(mOp).outChannels(), // outChannels
+ input0.getImpl()->rawPtr(), // input
+ input1.getImpl()->rawPtr(), // weight
+ op_.getInput(2) ? input2.getImpl()->rawPtr() : nullptr, // bias
+ getCPUPtr(mOp.getRawOutput(0)) // output
+ );
}
template <>