Updated example and README

fszewczyk · Nov 9, 2023 · d4debfb · d4debfb
1 parent a40b76d
commit d4debfb
Show file tree

Hide file tree

Showing 4 changed files with 33 additions and 25 deletions.
diff --git a/README.md b/README.md
@@ -34,14 +34,17 @@ int main() {
     using namespace shkyera;
     using T = Type::float32;
 
-    std::vector<Vec32> xs;
-    std::vector<Vec32> ys;
-
-    // ---------- INPUT ----------- | -------- OUTPUT --------- //
-    xs.push_back(Vec32::of(0, 0)); ys.push_back(Vec32::of(0));
-    xs.push_back(Vec32::of(1, 0)); ys.push_back(Vec32::of(1));
-    xs.push_back(Vec32::of(0, 1)); ys.push_back(Vec32::of(1));
-    xs.push_back(Vec32::of(1, 1)); ys.push_back(Vec32::of(0));
+    // This is our XOR dataset. It maps from Vec32 to Vec32
+    Dataset<Vec32, Vec32> data;
+    data.addSample(Vec32::of(0, 0), Vec32::of(0));
+    data.addSample(Vec32::of(0, 1), Vec32::of(1));
+    data.addSample(Vec32::of(1, 0), Vec32::of(1));
+    data.addSample(Vec32::of(1, 1), Vec32::of(0));
+
+    // The is the data loader, it will take care of batching
+    size_t batchSize = 2;
+    bool shuffle = true;
+    DataLoader loader(data, batchSize, shuffle);
 
     auto network = SequentialBuilder<Type::float32>::begin()
                     .add(Linear32::create(2, 15))
@@ -52,29 +55,26 @@ int main() {
                     .add(Sigmoid32::create())
                     .build();
 
-
-    auto optimizer = Adam32(network->parameters(), 0.05);
+    auto optimizer = Adam32(network->parameters(), 0.1);
     auto lossFunction = Loss::MSE<T>;
 
     for (size_t epoch = 0; epoch < 100; epoch++) { // We train for 100 epochs
         auto epochLoss = Val32::create(0);
 
-        optimizer.reset();                                      // Reset the gradients
-        for (size_t sample = 0; sample < xs.size(); ++sample) { // We go through each sample
-            Vec32 pred = network->forward(xs[sample]);          // We get some prediction
-            auto loss = lossFunction(pred, ys[sample]);         // And calculate its error
-
-            epochLoss = epochLoss + loss; // Store the loss for feedback
+        optimizer.reset();                                                // Reset the gradients
+        for (const auto &[x, y] : loader) {                               // For each batch
+            auto pred = network->forward(x);                              // We get some prediction
+            epochLoss = epochLoss + Loss::compute(lossFunction, pred, y); // And calculate its error
         }
         optimizer.step(); // Update the parameters
 
-        auto averageLoss = epochLoss / Val32::create(xs.size());
+        auto averageLoss = epochLoss / Val32::create(loader.getTotalBatches());
         std::cout << "Epoch: " << epoch + 1 << " Loss: " << averageLoss->getValue() << std::endl;
     }
 
-    for (size_t sample = 0; sample < xs.size(); ++sample) { // Go through each example
-        Vec32 pred = network->forward(xs[sample]);          // Predict result
-        std::cout << xs[sample] << " -> " << pred[0] << "\t| True: " << ys[sample][0] << std::endl;
+    for (auto &[x, y] : data) {          // Go through each example
+        auto pred = network->forward(x); // We get some prediction
+        std::cout << x << " -> " << pred[0] << "\t| True: " << y[0] << std::endl;
     }
 }
 ```
diff --git a/examples/xor_regression.cpp b/examples/xor_regression.cpp
@@ -5,13 +5,18 @@ int main() {
     using T = Type::float32;
 
     // clang-format off
+    // This is our XOR dataset. It maps from Vec32 to Vec32
     Dataset<Vec32, Vec32> data;
-
     data.addSample(Vec32::of(0, 0), Vec32::of(0));
     data.addSample(Vec32::of(0, 1), Vec32::of(1));
     data.addSample(Vec32::of(1, 0), Vec32::of(1));
     data.addSample(Vec32::of(1, 1), Vec32::of(0));
 
+    // The is the data loader, it will take care of batching
+    size_t batchSize = 2;
+    bool shuffle = true;
+    DataLoader loader(data, batchSize, shuffle);
+
     auto network = SequentialBuilder<Type::float32>::begin()
                     .add(Linear32::create(2, 15))
                     .add(ReLU32::create())
@@ -22,20 +27,20 @@ int main() {
                     .build();
     // clang-format on
 
-    auto optimizer = Adam32(network->parameters(), 0.05);
+    auto optimizer = Adam32(network->parameters(), 0.1);
     auto lossFunction = Loss::MSE<T>;
 
     for (size_t epoch = 0; epoch < 100; epoch++) { // We train for 100 epochs
         auto epochLoss = Val32::create(0);
 
-        optimizer.reset(); // Reset the gradients
-        for (auto &[x, y] : data) {
+        optimizer.reset();                                                // Reset the gradients
+        for (const auto &[x, y] : loader) {                               // For each batch
             auto pred = network->forward(x);                              // We get some prediction
             epochLoss = epochLoss + Loss::compute(lossFunction, pred, y); // And calculate its error
         }
         optimizer.step(); // Update the parameters
 
-        auto averageLoss = epochLoss / Val32::create(data.size());
+        auto averageLoss = epochLoss / Val32::create(loader.getTotalBatches());
         std::cout << "Epoch: " << epoch + 1 << " Loss: " << averageLoss->getValue() << std::endl;
     }
 

diff --git a/include/ShkyeraGrad.hpp b/include/ShkyeraGrad.hpp
@@ -17,6 +17,7 @@
 #include "nn/Neuron.hpp"
 #include "nn/Sequential.hpp"
 
+#include "nn/data/DataLoader.hpp"
 #include "nn/data/Dataset.hpp"
 
 #include "nn/optimizers/AdaMax.hpp"

diff --git a/include/core/Utils.hpp b/include/core/Utils.hpp
@@ -53,6 +53,8 @@ std::enable_if_t<std::is_integral_v<T>, std::vector<T>> sample(T from, T to, siz
     return sampled;
 }
 
+template <typename T> void shuffle(std::vector<T> &vec) { std::shuffle(vec.begin(), vec.end(), rand_dev); }
+
 template <typename Clock = std::chrono::high_resolution_clock> auto startTimer() { return Clock::now(); }
 
 template <typename Clock = std::chrono::high_resolution_clock>