Updated to add logistic regression godot example

examples/godot_logistic_regression/gdnative_shared/src/KomputeGdNative.cpp

@@ -0,0 +1,15 @@
+#include "KomputeSummator.hpp"
+
+extern "C" void GDN_EXPORT godot_gdnative_init(godot_gdnative_init_options *o) {
+    godot::Godot::gdnative_init(o);
+}
+
+extern "C" void GDN_EXPORT godot_gdnative_terminate(godot_gdnative_terminate_options *o) {
+    godot::Godot::gdnative_terminate(o);
+}
+
+extern "C" void GDN_EXPORT godot_nativescript_init(void *handle) {
+    godot::Godot::nativescript_init(handle);
+
+    godot::register_class<godot::KomputeSummator>();
+}

examples/godot_logistic_regression/gdnative_shared/src/KomputeSummator.cpp

@@ -0,0 +1,142 @@
+/* summator.cpp */
+
+#include <vector>
+#include <string>
+#include <iostream>
+
+#include "KomputeSummator.hpp"
+
+namespace godot {
+
+KomputeSummator::KomputeSummator() {
+    std::cout << "CALLING CONSTRUCTOR" << std::endl;
+    this->_init();
+}
+
+void KomputeSummator::train(Array yArr, Array xIArr, Array xJArr) {
+
+    assert(y.size() == xI.size());
+    assert(xI.size() == xJ.size());
+
+    std::vector<float> yData;
+    std::vector<float> xIData;
+    std::vector<float> xJData;
+    std::vector<float> zerosData;
+
+    for (size_t i = 0; i < yArr.size(); i++) {
+        yData.push_back(yArr[i]);
+        xIData.push_back(xIArr[i]);
+        xJData.push_back(xJArr[i]);
+        zerosData.push_back(0);
+    }
+
+    uint32_t ITERATIONS = 100;
+    float learningRate = 0.1;
+
+    std::shared_ptr<kp::Tensor> xI{ new kp::Tensor(xIData) };
+    std::shared_ptr<kp::Tensor> xJ{ new kp::Tensor(xJData) };
+
+    std::shared_ptr<kp::Tensor> y{ new kp::Tensor(yData) };
+
+    std::shared_ptr<kp::Tensor> wIn{ new kp::Tensor({ 0.001, 0.001 }) };
+    std::shared_ptr<kp::Tensor> wOutI{ new kp::Tensor(zerosData) };
+    std::shared_ptr<kp::Tensor> wOutJ{ new kp::Tensor(zerosData) };
+
+    std::shared_ptr<kp::Tensor> bIn{ new kp::Tensor({ 0 }) };
+    std::shared_ptr<kp::Tensor> bOut{ new kp::Tensor(zerosData) };
+
+    std::shared_ptr<kp::Tensor> lOut{ new kp::Tensor(zerosData) };
+
+    std::vector<std::shared_ptr<kp::Tensor>> params = { xI,  xJ,    y,
+                                                        wIn, wOutI, wOutJ,
+                                                        bIn, bOut,  lOut };
+
+    {
+        kp::Manager mgr;
+
+        if (std::shared_ptr<kp::Sequence> sq =
+              mgr.getOrCreateManagedSequence("createTensors").lock()) {
+
+            sq->begin();
+
+            sq->record<kp::OpTensorCreate>(params);
+
+            sq->end();
+            sq->eval();
+
+            // Record op algo base
+            sq->begin();
+
+            sq->record<kp::OpTensorSyncDevice>({ wIn, bIn });
+
+            sq->record<kp::OpAlgoBase<>>(
+              params, std::vector<char>(LR_SHADER.begin(), LR_SHADER.end()));
+
+            sq->record<kp::OpTensorSyncLocal>({ wOutI, wOutJ, bOut, lOut });
+
+            sq->end();
+
+            // Iterate across all expected iterations
+            for (size_t i = 0; i < ITERATIONS; i++) {
+
+                sq->eval();
+
+                for (size_t j = 0; j < bOut->size(); j++) {
+                    wIn->data()[0] -= learningRate * wOutI->data()[j];
+                    wIn->data()[1] -= learningRate * wOutJ->data()[j];
+                    bIn->data()[0] -= learningRate * bOut->data()[j];
+                }
+            }
+        }
+    }
+
+    SPDLOG_INFO("RESULT: <<<<<<<<<<<<<<<<<<<");
+    SPDLOG_INFO(wIn->data()[0]);
+    SPDLOG_INFO(wIn->data()[1]);
+    SPDLOG_INFO(bIn->data()[0]);
+
+    this->mWeights = kp::Tensor(wIn->data());
+    this->mBias = kp::Tensor(bIn->data());
+}
+
+Array KomputeSummator::predict(Array xI, Array xJ) {
+    assert(xI.size() == xJ.size());
+
+    Array retArray;
+
+    // We run the inference in the CPU for simplicity
+    // BUt you can also implement the inference on GPU 
+    // GPU implementation would speed up minibatching
+    for (size_t i = 0; i < xI.size(); i++) {
+        float xIVal = xI[i];
+        float xJVal = xJ[i];
+        float result = (xIVal * this->mWeights.data()[0]
+                + xJVal * this->mWeights.data()[1]
+                + this->mBias.data()[0]);
+
+        // Instead of using sigmoid we'll just return full numbers
+        Variant var = result > 0 ? 1 : 0;
+        retArray.push_back(var);
+    }
+
+    return retArray;
+}
+
+void KomputeSummator::_init() {
+    std::cout << "CALLING INIT" << std::endl;
+}
+
+void KomputeSummator::_process(float delta) {
+
+}
+
+void KomputeSummator::_register_methods() {
+    register_method((char *)"_process", &KomputeSummator::_process);
+    register_method((char *)"_init", &KomputeSummator::_init);
+
+    register_method((char *)"train", &KomputeSummator::train);
+    register_method((char *)"predict", &KomputeSummator::predict);
+}
+
+}
+

examples/godot_logistic_regression/gdnative_shared/src/KomputeSummator.hpp

@@ -0,0 +1,89 @@
+#pragma once
+
+#include <Godot.hpp>
+#include <Node2D.hpp>
+#include <Array.hpp>
+
+#include <memory>
+
+#include "kompute/Kompute.hpp"
+
+namespace godot {
+class KomputeSummator : public Node2D {
+private:
+    GODOT_CLASS(KomputeSummator, Node2D);
+
+public:
+    KomputeSummator();
+
+    void train(Array y, Array xI, Array xJ);
+    Array predict(Array xI, Array xJ);
+
+    void _process(float delta);
+    void _init();
+
+    static void _register_methods();
+
+private:
+    kp::Tensor mWeights;
+    kp::Tensor mBias;
+};
+
+static std::string LR_SHADER = R"(
+#version 450
+
+layout (constant_id = 0) const uint M = 0;
+
+layout (local_size_x = 1) in;
+
+layout(set = 0, binding = 0) buffer bxi { float xi[]; };
+layout(set = 0, binding = 1) buffer bxj { float xj[]; };
+layout(set = 0, binding = 2) buffer by { float y[]; };
+layout(set = 0, binding = 3) buffer bwin { float win[]; };
+layout(set = 0, binding = 4) buffer bwouti { float wouti[]; };
+layout(set = 0, binding = 5) buffer bwoutj { float woutj[]; };
+layout(set = 0, binding = 6) buffer bbin { float bin[]; };
+layout(set = 0, binding = 7) buffer bbout { float bout[]; };
+layout(set = 0, binding = 8) buffer blout { float lout[]; };
+
+float m = float(M);
+
+float sigmoid(float z) {
+    return 1.0 / (1.0 + exp(-z));
+}
+
+float inference(vec2 x, vec2 w, float b) {
+    // Compute the linear mapping function
+    float z = dot(w, x) + b;
+    // Calculate the y-hat with sigmoid 
+    float yHat = sigmoid(z);
+    return yHat;
+}
+
+float calculateLoss(float yHat, float y) {
+    return -(y * log(yHat)  +  (1.0 - y) * log(1.0 - yHat));
+}
+
+void main() {
+    uint idx = gl_GlobalInvocationID.x;
+
+    vec2 wCurr = vec2(win[0], win[1]);
+    float bCurr = bin[0];
+
+    vec2 xCurr = vec2(xi[idx], xj[idx]);
+    float yCurr = y[idx];
+
+    float yHat = inference(xCurr, wCurr, bCurr);
+
+    float dZ = yHat - yCurr;
+    vec2 dW = (1. / m) * xCurr * dZ;
+    float dB = (1. / m) * dZ;
+    wouti[idx] = dW.x;
+    woutj[idx] = dW.y;
+    bout[idx] = dB;
+
+    lout[idx] = calculateLoss(yHat, yCurr);
+}
+)";
+
+}