[Simba 2.0] MNIST data parser

(*
  This code is part of the article found at:
  https://slacky.one/article/simba-2_0-a-step-into-machine-learning
*)

function BytesToInt32(Bytes: TByteArray; StartIndex: Integer): Integer;
begin
  Result := (Bytes[StartIndex] shl 24) or (Bytes[StartIndex + 1] shl 16) or
            (Bytes[StartIndex + 2] shl 8) or Bytes[StartIndex + 3];
end;

function ParseMNISTFile(FileName: string): array of TSingleMatrix;
var
  FileData: TByteArray;
  MagicNumber, NumImages, NumRows, NumCols: Integer;
  i, r, c, Offset: Integer;
begin
  if not FileExists(FileName) then
  begin
    WriteLn('File not found: ', FileName);
    Exit;
  end;

  // Read the entire file into memory
  FileData := FileReadBytes(FileName);
  if Length(FileData) = 0 then
  begin
    WriteLn('Failed to read file or file is empty.');
    Exit;
  end;

  // Parse the header (16 bytes)
  MagicNumber := BytesToInt32(FileData, 0);
  NumImages   := BytesToInt32(FileData, 4);
  NumRows     := BytesToInt32(FileData, 8);
  NumCols     := BytesToInt32(FileData, 12);

  if MagicNumber <> 2051 then
  begin
    WriteLn('Invalid magic number: ', MagicNumber);
    Exit;
  end;

  // Allocate memory for images
  SetLength(Result, NumImages);
  for i := 0 to NumImages - 1 do
    SetLength(Result[i], NumRows, NumCols);

  // Parse image data
  Offset := 16; // Image data starts after the header
  for i := 0 to NumImages - 1 do
  begin
    for r := 0 to NumRows - 1 do
    begin
      for c := 0 to NumCols - 1 do
      begin
        Result[i][r][c] := FileData[Offset];
        Inc(Offset);
      end;
    end;
  end;
end;

function ParseMNISTLabels(FileName: string): array of Byte;
var
  FileData: TByteArray;
  MagicNumber, NumLabels, Offset: Integer;
  i: Integer;
begin
  if not FileExists(FileName) then
  begin
    WriteLn('File not found: ', FileName);
    Exit;
  end;

  // Read the entire file into memory
  FileData := FileReadBytes(FileName);
  if Length(FileData) = 0 then
  begin
    WriteLn('Failed to read file or file is empty.');
    Exit;
  end;

  // Parse the header (8 bytes)
  MagicNumber := BytesToInt32(FileData, 0);
  NumLabels := BytesToInt32(FileData, 4);

  if MagicNumber <> 2049 then
  begin
    WriteLn('Invalid magic number: ', MagicNumber);
    Exit;
  end;

  // Allocate memory for labels
  SetLength(Result, NumLabels);

  // Parse labels (starting at offset 8)
  Offset := 8;
  for i := 0 to NumLabels - 1 do
  begin
    Result[i] := FileData[Offset];
    Inc(Offset);
  end;
end;