fix compilation problem

src/operators/kernel/cl/depthwise_conv_kernel.cpp

@@ -47,7 +47,7 @@ void DepthwiseConvKernel<GPU_CL, float>::Compute(
   int nh = default_work_size[2];
   auto input = param.Input()->GetCLImage();
   auto filter = param.Filter()->GetCLImage();
-  auto output = param.Output();
+  auto output = param.Output()->GetCLImage();
   int stride = param.Strides()[0];
   int offset = param.Offset();
   int input_c = param.Input()->CBlock();

src/operators/kernel/cl/fetch_kernel.cpp

@@ -58,7 +58,7 @@ void FetchKernel<GPU_CL, float>::Compute(const FetchParam<GPU_CL> &param) {
   clEnqueueNDRangeKernel(this->cl_helper_.CLCommandQueue(), kernel, 3, NULL,
                          default_work_size.data(), NULL, 0, NULL, NULL);
 
-  memcpy(out->data(), out_cl_tensor.Data(), out->memory_size());
+  memcpy(out->data<float>(), out_cl_tensor.Data<float>(), out->memory_size());
 }
 
 template class FetchKernel<GPU_CL, float>;