From 6f8b5f40817506f11d3d54dbeac64b67eaec49c5 Mon Sep 17 00:00:00 2001
From: LordMathis <matus@namesny.com>
Date: Mon, 20 May 2024 13:05:48 +0200
Subject: [PATCH] Rename batchnorm

---
 examples/inception_v3/inception_v3.cpp |  2 +-
 include/layers/batch_norm.cuh          | 10 +++++-----
 src/layers/batch_norm.cu               | 24 ++++++++++++------------
 test/layers/test_batch_norm.cu         |  4 ++--
 4 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/examples/inception_v3/inception_v3.cpp b/examples/inception_v3/inception_v3.cpp
index ba6cc4d..5c1715b 100644
--- a/examples/inception_v3/inception_v3.cpp
+++ b/examples/inception_v3/inception_v3.cpp
@@ -30,7 +30,7 @@ class BasicConv2d : public CUDANet::Module {
 
         int batchNormSize = conv->getOutputSize();
 
-        CUDANet::Layers::BatchNorm *batchNorm = new CUDANet::Layers::BatchNorm(
+        CUDANet::Layers::BatchNorm2D *batchNorm = new CUDANet::Layers::BatchNorm2D(
             batchNormSize, outputChannels, 1e-3f,
             CUDANet::Layers::ActivationType::RELU
         );
diff --git a/include/layers/batch_norm.cuh b/include/layers/batch_norm.cuh
index c24a946..91abb2e 100644
--- a/include/layers/batch_norm.cuh
+++ b/include/layers/batch_norm.cuh
@@ -8,11 +8,11 @@
 
 namespace CUDANet::Layers {
 
-class BatchNorm : public WeightedLayer {
+class BatchNorm2D : public WeightedLayer {
   public:
-    BatchNorm(int inputSize, int inputChannels, float epsilon, ActivationType activationType);
+    BatchNorm2D(int inputSize, int inputChannels, float epsilon, ActivationType activationType);
 
-    ~BatchNorm();
+    ~BatchNorm2D();
 
     /**
      * @brief Compute the forward pass of the batchnorm layer
@@ -105,13 +105,13 @@ class BatchNorm : public WeightedLayer {
 
     /**
      * @brief Initialize mean of the batchnorm layer with zeros
-     * 
+     *
      */
     void initializeMean();
 
     /**
      * @brief Initialize sqrt of variance of the batchnorm layer with ones
-     * 
+     *
      */
     void initializeSqrtVar();
 
diff --git a/src/layers/batch_norm.cu b/src/layers/batch_norm.cu
index 486a728..c96e6cf 100644
--- a/src/layers/batch_norm.cu
+++ b/src/layers/batch_norm.cu
@@ -9,7 +9,7 @@
 
 using namespace CUDANet::Layers;
 
-BatchNorm::BatchNorm(
+BatchNorm2D::BatchNorm2D(
     int            inputSize,
     int            inputChannels,
     float          epsilon,
@@ -63,7 +63,7 @@ BatchNorm::BatchNorm(
         (inputSize * inputSize + BLOCK_SIZE - 1) / BLOCK_SIZE;
 }
 
-BatchNorm::~BatchNorm() {
+BatchNorm2D::~BatchNorm2D() {
     cudaFree(d_output);
     cudaFree(d_mean);
     cudaFree(d_mean_sub);
@@ -74,33 +74,33 @@ BatchNorm::~BatchNorm() {
     cudaFree(d_epsilon);
 }
 
-void BatchNorm::initializeWeights() {
+void BatchNorm2D::initializeWeights() {
     std::fill(weights.begin(), weights.end(), 1.0f);
 }
 
-void BatchNorm::initializeBiases() {
+void BatchNorm2D::initializeBiases() {
     std::fill(biases.begin(), biases.end(), 0.0f);
 }
 
-void BatchNorm::setWeights(const float *weights_input) {
+void BatchNorm2D::setWeights(const float *weights_input) {
     std::copy(weights_input, weights_input + weights.size(), weights.begin());
     toCuda();
 }
 
-std::vector<float> BatchNorm::getWeights() {
+std::vector<float> BatchNorm2D::getWeights() {
     return weights;
 }
 
-void BatchNorm::setBiases(const float *biases_input) {
+void BatchNorm2D::setBiases(const float *biases_input) {
     std::copy(biases_input, biases_input + biases.size(), biases.begin());
     toCuda();
 }
 
-std::vector<float> BatchNorm::getBiases() {
+std::vector<float> BatchNorm2D::getBiases() {
     return biases;
 }
 
-void BatchNorm::toCuda() {
+void BatchNorm2D::toCuda() {
     CUDA_CHECK(cudaMemcpy(
         d_weights, weights.data(), sizeof(float) * inputChannels,
         cudaMemcpyHostToDevice
@@ -111,15 +111,15 @@ void BatchNorm::toCuda() {
     ));
 }
 
-int BatchNorm::getInputSize() {
+int BatchNorm2D::getInputSize() {
     return inputSize * inputSize * inputChannels;
 }
 
-int BatchNorm::getOutputSize() {
+int BatchNorm2D::getOutputSize() {
     return inputSize * inputSize * inputChannels;
 }
 
-float *BatchNorm::forward(const float *d_input) {
+float *BatchNorm2D::forward(const float *d_input) {
     
     // Compute per-channel batch normalization
     for (int i = 0; i < inputChannels; i++) {
diff --git a/test/layers/test_batch_norm.cu b/test/layers/test_batch_norm.cu
index 46da0fa..c3fbb4c 100644
--- a/test/layers/test_batch_norm.cu
+++ b/test/layers/test_batch_norm.cu
@@ -12,7 +12,7 @@ TEST(BatchNormLayerTest, BatchNormSmallForwardTest) {
 
     cudaError_t cudaStatus;
 
-    CUDANet::Layers::BatchNorm batchNorm(
+    CUDANet::Layers::BatchNorm2D batchNorm(
         inputSize, nChannels, 1e-5f, CUDANet::Layers::ActivationType::NONE
     );
 
@@ -69,7 +69,7 @@ TEST(BatchNormLayerTest, BatchNormSmallForwardTest) {
         0.9126f, 0.71485f, -0.08184f, -0.19131f
     };
 
-    // std::cout << "BatchNorm: " << std::endl;
+    // std::cout << "BatchNorm2D: " << std::endl;
     for (int i = 0; i < output.size(); i++) {
         EXPECT_NEAR(output[i], expected[i], 1e-5);
         // std::cout << output[i] << " ";