Add avgPool2d implementation

src/backends/cuda/kernels/pool.cu

@@ -1,6 +1,6 @@
 #include "cuda_helper.cuh"
 #include "layer.hpp"
-#include "pooling.cuh"
+#include "pool.cuh"
 
 using namespace CUDANet;
 

src/backends/cuda/layer_ops.cu

@@ -135,5 +135,31 @@ CUDANet::Tensor& CUDA::maxPool2d(
     CUDA_CHECK(cudaGetLastError());
     CUDA_CHECK(cudaDeviceSynchronize());
 
+    return output;
+}
+
+CUDANet::Tensor& CUDA::avgPool2d(
+    const CUDANet::Tensor& input,
+    CUDANet::Tensor& output,
+    CUDANet::Shape input_shape,
+    CUDANet::Shape pool_shape,
+    CUDANet::Shape stride_shape,
+    CUDANet::Shape padding_shape,
+    CUDANet::Shape output_shape
+) {
+    dim3 block(8, 8, 8);
+    dim3 grid(
+        (output_shape[0] + block.x - 1) / block.x,
+        (output_shape[1] + block.y - 1) / block.y,
+        (output_shape[2] + block.z - 1) / block.z
+    );
+
+    Kernels::avg_pool<<<grid, block>>>(
+        input.data<float>(), output.data<float>(), input_shape, output_shape, pool_shape,
+        stride_shape, padding_shape
+    );
+    CUDA_CHECK(cudaGetLastError());
+    CUDA_CHECK(cudaDeviceSynchronize());
+
     return output;
 }

src/backends/cuda/layers/avg_pooling.cu

@@ -1,45 +0,0 @@
-#include "avg_pooling.hpp"
-#include "cuda_helper.cuh"
-#include "pooling.cuh"
-
-using namespace CUDANet::Layers;
-
-void AvgPooling2d::initCUDA() {
-    d_output = nullptr;
-    CUDA_CHECK(cudaMalloc(
-        (void**)&d_output,
-        sizeof(float) * outputSize.first * outputSize.second * nChannels
-    ));
-}
-
-void AvgPooling2d::delCUDA() {
-    cudaFree(d_output);
-}
-
-float* AvgPooling2d::forwardCUDA(const float* d_input) {
-    dim3 block(8, 8, 8);
-    dim3 grid(
-        (outputSize.first + block.x - 1) / block.x,
-        (outputSize.second + block.y - 1) / block.y,
-        (nChannels + block.z - 1) / block.z
-    );
-
-    Kernels::avg_pooling<<<grid, block>>>(
-        d_input, d_output, inputSize, outputSize, nChannels, poolingSize,
-        stride, padding
-    );
-    CUDA_CHECK(cudaGetLastError());
-
-    activation->activate(d_output);
-    CUDA_CHECK(cudaDeviceSynchronize());
-
-    return d_output;
-}
-
-void AdaptiveAvgPooling2d::initCUDA() {
-    cudaFree(d_output);
-    cudaMalloc(
-        (void**)&d_output,
-        sizeof(float) * outputSize.first * outputSize.second * nChannels
-    );
-}