daimond 0.1.0

data/ext/daimond_rust/Cargo.lock

@@ -0,0 +1,353 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 4
+
+[[package]]
+name = "aho-corasick"
+version = "1.1.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ddd31a130427c27518df266943a5308ed92d4b226cc639f5a8f1002816174301"
+dependencies = [
+ "memchr",
+]
+
+[[package]]
+name = "autocfg"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c08606f8c3cbf4ce6ec8e28fb0014a2c086708fe954eaa885384a6165172e7e8"
+
+[[package]]
+name = "bindgen"
+version = "0.69.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "271383c67ccabffb7381723dea0672a673f292304fcb45c01cc648c7a8d58088"
+dependencies = [
+ "bitflags",
+ "cexpr",
+ "clang-sys",
+ "itertools",
+ "lazy_static",
+ "lazycell",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "rustc-hash",
+ "shlex",
+ "syn",
+]
+
+[[package]]
+name = "bitflags"
+version = "2.10.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "812e12b5285cc515a9c72a5c1d3b6d46a19dac5acfef5265968c166106e31dd3"
+
+[[package]]
+name = "cexpr"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6fac387a98bb7c37292057cffc56d62ecb629900026402633ae9160df93a8766"
+dependencies = [
+ "nom",
+]
+
+[[package]]
+name = "cfg-if"
+version = "1.0.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9330f8b2ff13f34540b44e946ef35111825727b38d33286ef986142615121801"
+
+[[package]]
+name = "clang-sys"
+version = "1.8.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b023947811758c97c59bf9d1c188fd619ad4718dcaa767947df1cadb14f39f4"
+dependencies = [
+ "glob",
+ "libc",
+ "libloading",
+]
+
+[[package]]
+name = "daimond_rust"
+version = "0.1.0"
+dependencies = [
+ "magnus",
+ "ndarray",
+ "rb-sys",
+]
+
+[[package]]
+name = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
+[[package]]
+name = "glob"
+version = "0.3.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0cc23270f6e1808e30a928bdc84dea0b9b4136a8bc82338574f23baf47bbd280"
+
+[[package]]
+name = "itertools"
+version = "0.12.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ba291022dbbd398a455acf126c1e341954079855bc60dfdda641363bd6922569"
+dependencies = [
+ "either",
+]
+
+[[package]]
+name = "lazy_static"
+version = "1.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bbd2bcb4c963f2ddae06a2efc7e9f3591312473c50c6685e1f298068316e66fe"
+
+[[package]]
+name = "lazycell"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "830d08ce1d1d941e6b30645f1a0eb5643013d835ce3779a5fc208261dbe10f55"
+
+[[package]]
+name = "libc"
+version = "0.2.180"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "bcc35a38544a891a5f7c865aca548a982ccb3b8650a5b06d0fd33a10283c56fc"
+
+[[package]]
+name = "libloading"
+version = "0.8.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d7c4b02199fee7c5d21a5ae7d8cfa79a6ef5bb2fc834d6e9058e89c825efdc55"
+dependencies = [
+ "cfg-if",
+ "windows-link",
+]
+
+[[package]]
+name = "magnus"
+version = "0.6.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b1597ef40aa8c36be098249e82c9a20cf7199278ac1c1a1a995eeead6a184479"
+dependencies = [
+ "magnus-macros",
+ "rb-sys",
+ "rb-sys-env",
+ "seq-macro",
+]
+
+[[package]]
+name = "magnus-macros"
+version = "0.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5968c820e2960565f647819f5928a42d6e874551cab9d88d75e3e0660d7f71e3"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "matrixmultiply"
+version = "0.3.10"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a06de3016e9fae57a36fd14dba131fccf49f74b40b7fbdb472f96e361ec71a08"
+dependencies = [
+ "autocfg",
+ "rawpointer",
+]
+
+[[package]]
+name = "memchr"
+version = "2.7.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f52b00d39961fc5b2736ea853c9cc86238e165017a493d1d5c8eac6bdc4cc273"
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "ndarray"
+version = "0.15.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "adb12d4e967ec485a5f71c6311fe28158e9d6f4bc4a447b474184d0f91a8fa32"
+dependencies = [
+ "matrixmultiply",
+ "num-complex",
+ "num-integer",
+ "num-traits",
+ "rawpointer",
+]
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
+[[package]]
+name = "num-complex"
+version = "0.4.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "73f88a1307638156682bada9d7604135552957b7818057dcef22705b4d509495"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-integer"
+version = "0.1.46"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7969661fd2958a5cb096e56c8e1ad0444ac2bbcd0061bd28660485a44879858f"
+dependencies = [
+ "num-traits",
+]
+
+[[package]]
+name = "num-traits"
+version = "0.2.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "071dfc062690e90b734c0b2273ce72ad0ffa95f0c74596bc250dcfd960262841"
+dependencies = [
+ "autocfg",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.106"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8fd00f0bb2e90d81d1044c2b32617f68fcb9fa3bb7640c23e9c748e53fb30934"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.44"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "21b2ebcf727b7760c461f091f9f0f539b77b8e87f2fd88131e7f1b433b3cece4"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "rawpointer"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "60a357793950651c4ed0f3f52338f53b2f809f32d83a07f72909fa13e4c6c1e3"
+
+[[package]]
+name = "rb-sys"
+version = "0.9.124"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "c85c4188462601e2aa1469def389c17228566f82ea72f137ed096f21591bc489"
+dependencies = [
+ "rb-sys-build",
+]
+
+[[package]]
+name = "rb-sys-build"
+version = "0.9.124"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "568068db4102230882e6d4ae8de6632e224ca75fe5970f6e026a04e91ed635d3"
+dependencies = [
+ "bindgen",
+ "lazy_static",
+ "proc-macro2",
+ "quote",
+ "regex",
+ "shell-words",
+ "syn",
+]
+
+[[package]]
+name = "rb-sys-env"
+version = "0.1.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a35802679f07360454b418a5d1735c89716bde01d35b1560fc953c1415a0b3bb"
+
+[[package]]
+name = "regex"
+version = "1.12.2"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "843bc0191f75f3e22651ae5f1e72939ab2f72a4bc30fa80a066bd66edefc24d4"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-automata",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-automata"
+version = "0.4.13"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5276caf25ac86c8d810222b3dbb938e512c55c6831a10f3e6ed1c93b84041f1c"
+dependencies = [
+ "aho-corasick",
+ "memchr",
+ "regex-syntax",
+]
+
+[[package]]
+name = "regex-syntax"
+version = "0.8.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7a2d987857b319362043e95f5353c0535c1f58eec5336fdfcf626430af7def58"
+
+[[package]]
+name = "rustc-hash"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "08d43f7aa6b08d49f382cde6a7982047c3426db949b1424bc4b7ec9ae12c6ce2"
+
+[[package]]
+name = "seq-macro"
+version = "0.3.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1bc711410fbe7399f390ca1c3b60ad0f53f80e95c5eb935e52268a0e2cd49acc"
+
+[[package]]
+name = "shell-words"
+version = "1.1.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc6fe69c597f9c37bfeeeeeb33da3530379845f10be461a66d16d03eca2ded77"
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "syn"
+version = "2.0.114"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d4d107df263a3013ef9b1879b0df87d706ff80f65a86ea879bd9c31f9b307c2a"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.22"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9312f7c4f6ff9069b165498234ce8be658059c6728633667c526e27dc2cf1df5"
+
+[[package]]
+name = "windows-link"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "f0805222e57f7521d6a62e36fa9163bc891acd422f971defe97d64e70d0a4fe5"

data/ext/daimond_rust/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+name = "daimond_rust"
+version = "0.1.0"
+edition = "2021"
+build = "build.rs"
+
+[lib]
+crate-type = ["cdylib"]
+
+[dependencies]
+magnus = { version = "0.6", features = ["rb-sys"] }
+rb-sys = "0.9"
+ndarray = "0.15"

data/ext/daimond_rust/build.rs

@@ -0,0 +1,3 @@
+fn main() {
+    // Автоматически находит Ruby
+}

data/ext/daimond_rust/src/lib.rs

@@ -0,0 +1,103 @@
+use magnus::{prelude::*, Ruby, RArray, Value};
+use ndarray::Array2;
+use std::f64;
+
+// === Flat MatMul ===
+fn fast_matmul_flat(
+    a: Vec<f64>,
+    b: Vec<f64>,
+    m: usize,
+    k: usize,
+    n: usize
+) -> Vec<f64> {
+    let a_arr = Array2::from_shape_vec((m, k), a).unwrap();
+    let b_arr = Array2::from_shape_vec((k, n), b).unwrap();
+    let c_arr = a_arr.dot(&b_arr);
+    c_arr.into_raw_vec()
+}
+
+// === Conv2D ===
+fn conv2d_forward(
+    input: Vec<f64>,
+    weight: Vec<f64>,
+    bias: Vec<f64>,
+    batch: usize,
+    in_c: usize,
+    out_c: usize,
+    h: usize,
+    w: usize,
+    k: usize,
+) -> Vec<f64> {
+    let h_out = h - k + 1;
+    let w_out = w - k + 1;
+    let mut output = vec![0.0; batch * out_c * h_out * w_out];
+
+    for b in 0..batch {
+        for oc in 0..out_c {
+            for i in 0..h_out {
+                for j in 0..w_out {
+                    let mut sum = bias[oc];
+                    for ic in 0..in_c {
+                        for ki in 0..k {
+                            for kj in 0..k {
+                                let in_idx = ((b * in_c + ic) * h + i + ki) * w + j + kj;
+                                let w_idx = ((oc * in_c + ic) * k + ki) * k + kj;
+                                sum += input[in_idx] * weight[w_idx];
+                            }
+                        }
+                    }
+                    let out_idx = ((b * out_c + oc) * h_out + i) * w_out + j;
+                    output[out_idx] = sum;
+                }
+            }
+        }
+    }
+    output
+}
+
+// === MaxPool2D ===
+fn maxpool2d_forward(
+    input: Vec<f64>,
+    batch: usize,
+    channels: usize,
+    h: usize,
+    w: usize,
+    k: usize,
+) -> Vec<f64> {
+    let h_out = h / k;
+    let w_out = w / k;
+    let mut output = vec![0.0; batch * channels * h_out * w_out];
+
+    for b in 0..batch {
+        for c in 0..channels {
+            for i in 0..h_out {
+                for j in 0..w_out {
+                    let mut max_val = f64::MIN;
+                    for ki in 0..k {
+                        for kj in 0..k {
+                            let in_idx = ((b * channels + c) * h + i * k + ki) * w + j * k + kj;
+                            max_val = max_val.max(input[in_idx]);
+                        }
+                    }
+                    let out_idx = ((b * channels + c) * h_out + i) * w_out + j;
+                    output[out_idx] = max_val;
+                }
+            }
+        }
+    }
+    output
+}
+
+// === Инициализация ===
+#[magnus::init]
+fn init(ruby: &Ruby) -> Result<(), magnus::Error> {
+    let module = ruby.define_module("Daimond")?
+        .define_module("Rust")?;
+
+    // Только flat-версии (быстрее и проще)
+    module.define_singleton_method("fast_matmul_flat", magnus::function!(fast_matmul_flat, 5))?;
+    module.define_singleton_method("conv2d_native", magnus::function!(conv2d_forward, 9))?;
+    module.define_singleton_method("maxpool2d_native", magnus::function!(maxpool2d_forward, 6))?;
+
+    Ok(())
+}

data/lib/daimond/data/data_loader.rb

@@ -0,0 +1,41 @@
+module Daimond
+  module Data
+    class DataLoader
+      def initialize(images, labels, batch_size: 32, shuffle: true)
+        @images = images
+        @labels = labels
+        @batch_size = batch_size
+        @shuffle = shuffle
+        @n_samples = images.length
+        reset
+      end
+
+      def reset
+        @indices = (0...@n_samples).to_a
+        @indices.shuffle! if @shuffle
+        @position = 0
+      end
+
+      def each_batch
+        reset
+        while @position < @n_samples
+          batch_indices = @indices[@position, @batch_size]
+          @position += @batch_size
+
+          batch_images = batch_indices.map { |i| @images[i] }
+          batch_labels = batch_indices.map { |i| @labels[i] }
+
+          # Конвертируем в Tensor [batch_size, 784]
+          x = Tensor.new(Numo::DFloat[*batch_images])
+          y = Tensor.new(Numo::Int32[*batch_labels])
+
+          yield x, y
+        end
+      end
+
+      def batches_count
+        (@n_samples.to_f / @batch_size).ceil
+      end
+    end
+  end
+end

data/lib/daimond/data/mnist.rb

@@ -0,0 +1,56 @@
+require 'open-uri'
+require 'zlib'
+require 'fileutils'
+
+module Daimond
+  module Data
+    class MNIST
+      URL_BASE = 'https://ossci-datasets.s3.amazonaws.com/mnist/'
+      FILES = {
+        train_images: 'train-images-idx3-ubyte.gz',
+        train_labels: 'train-labels-idx1-ubyte.gz',
+        test_images: 't10k-images-idx3-ubyte.gz',
+        test_labels: 't10k-labels-idx1-ubyte.gz'
+      }
+
+      def self.download(file, path: 'data/mnist')
+        ::FileUtils.mkdir_p(path)  # <-- Здесь изменение: создаёт и data, и data/mnist
+        filepath = File.join(path, file)
+
+        unless File.exist?(filepath)
+          puts "Downloading #{file}..."
+          URI.open("#{URL_BASE}#{file}") do |f|
+            File.open(filepath, 'wb') { |out| out.write(f.read) }
+          end
+        end
+        filepath
+      end
+
+      def self.load_images(file)
+        filepath = download(file)
+        Zlib::GzipReader.open(filepath) do |f|
+          magic = f.read(4).unpack('N').first
+          n_images = f.read(4).unpack('N').first
+          n_rows = f.read(4).unpack('N').first
+          n_cols = f.read(4).unpack('N').first
+
+          images = f.read(n_images * n_rows * n_cols).unpack('C*')
+          # Нормализация в [0, 1] и reshape в [n_images, 784]
+          images.each_slice(n_rows * n_cols).map do |img|
+            img.map { |pixel| pixel / 255.0 }
+          end
+        end
+      end
+
+      def self.load_labels(file)
+        filepath = download(file)
+        Zlib::GzipReader.open(filepath) do |f|
+          magic = f.read(4).unpack('N').first
+          n_labels = f.read(4).unpack('N').first
+          labels = f.read(n_labels).unpack('C*')
+          labels
+        end
+      end
+    end
+  end
+end

data/lib/daimond/loss/cross_entropy.rb

@@ -0,0 +1,45 @@
+require_relative '../tensor'
+require 'numo/narray'
+
+module Daimond
+  module Loss
+    class CrossEntropyLoss
+      def initialize
+      end
+
+      def forward(pred, target)
+        # pred: [batch_size, 10] после softmax
+        # target: [batch_size] метки классов (0-9)
+        batch_size = pred.shape[0]
+
+        # Вычисляем loss для мониторинга (не используется в backward)
+        log_probs = Numo::NMath.log(pred.data)
+        correct_log_probs = Numo::DFloat.zeros(batch_size)
+
+        batch_size.times do |i|
+          correct_log_probs[i] = log_probs[i, target.data[i]]
+        end
+
+        loss_value = -correct_log_probs.mean
+
+        out = Tensor.new(Numo::DFloat[loss_value], prev: [pred], op: 'cross_entropy')
+
+        # Backward: gradient of cross_entropy + softmax = pred - one_hot(target)
+        out._backward = lambda do
+          grad_input = pred.data.dup  # softmax output
+          batch_size.times do |i|
+            grad_input[i, target.data[i]] -= 1.0
+          end
+          grad_input /= batch_size
+          pred.grad += grad_input
+        end
+
+        out
+      end
+
+      def call(pred, target)
+        forward(pred, target)
+      end
+    end
+  end
+end