internal static void Main(string[] args)
{
torch.random.manual_seed(1);
var cwd = Environment.CurrentDirectory;
var device = torch.cuda.is_available() ? torch.CUDA : torch.CPU;
Console.WriteLine($"Running TextClassification on {device.type.ToString()}");
using (var reader = TorchText.Data.AG_NEWSReader.AG_NEWS("train", (Device)device, _dataLocation)) {
var dataloader = reader.Enumerate();
var tokenizer = TorchText.Data.Utils.get_tokenizer("basic_english");
var counter = new TorchText.Vocab.Counter<string>();
foreach (var (label, text) in dataloader) {
counter.update(tokenizer(text));
}
var vocab = new TorchText.Vocab.Vocab(counter);
var model = new TextClassificationModel(vocab.Count, emsize, 4).to((Device)device);
var loss = cross_entropy_loss();
var lr = 5.0;
var optimizer = torch.optim.SGD(model.parameters(), lr);
var scheduler = torch.optim.lr_scheduler.StepLR(optimizer, 1, 0.2, last_epoch: 5);
foreach (var epoch in Enumerable.Range(1, epochs)) {
var sw = new Stopwatch();
sw.Start();
train(epoch, reader.GetBatches(tokenizer, vocab, batch_size), model, loss, optimizer);
sw.Stop();
Console.WriteLine($"\nEnd of epoch: {epoch} | lr: {scheduler.LearningRate:0.0000} | time: {sw.Elapsed.TotalSeconds:0.0}s\n");
scheduler.step();
}
using (var test_reader = TorchText.Data.AG_NEWSReader.AG_NEWS("test", (Device)device, _dataLocation)) {
var sw = new Stopwatch();
sw.Start();
var accuracy = evaluate(test_reader.GetBatches(tokenizer, vocab, eval_batch_size), model, loss);
sw.Stop();
Console.WriteLine($"\nEnd of training: test accuracy: {accuracy:0.00} | eval time: {sw.Elapsed.TotalSeconds:0.0}s\n");
scheduler.step();
}
}
}
static void Main(string[] args)
{
Torch.SetSeed(1);
var cwd = Environment.CurrentDirectory;
var device = Torch.IsCudaAvailable() ? Device.CUDA : Device.CPU;
Console.WriteLine($"Running SequenceToSequence on {device.Type.ToString()}");
var vocab_iter = TorchText.Datasets.WikiText2("train", _dataLocation);
var tokenizer = TorchText.Data.Utils.get_tokenizer("basic_english");
var counter = new TorchText.Vocab.Counter <string>();
foreach (var item in vocab_iter)
{
counter.update(tokenizer(item));
}
var vocab = new TorchText.Vocab.Vocab(counter);
var(train_iter, valid_iter, test_iter) = TorchText.Datasets.WikiText2(_dataLocation);
var train_data = Batchify(ProcessInput(train_iter, tokenizer, vocab), batch_size).to(device);
var valid_data = Batchify(ProcessInput(valid_iter, tokenizer, vocab), eval_batch_size).to(device);
var test_data = Batchify(ProcessInput(test_iter, tokenizer, vocab), eval_batch_size).to(device);
var bptt = 32;
var(data, targets) = GetBatch(train_data, 0, bptt);
var ntokens = vocab.Count;
var model = new TransformerModel(ntokens, emsize, nhead, nhid, nlayers, dropout).to(device);
var loss = cross_entropy_loss();
var lr = 2.50;
var optimizer = NN.Optimizer.SGD(model.parameters(), lr);
var scheduler = NN.Optimizer.StepLR(optimizer, 1, 0.95, last_epoch: 15);
var totalTime = new Stopwatch();
totalTime.Start();
foreach (var epoch in Enumerable.Range(1, epochs))
{
var sw = new Stopwatch();
sw.Start();
train(epoch, train_data, model, loss, bptt, ntokens, optimizer);
var val_loss = evaluate(valid_data, model, loss, lr, bptt, ntokens, optimizer);
sw.Stop();
Console.WriteLine($"\nEnd of epoch: {epoch} | lr: {scheduler.LearningRate:0.00} | time: {sw.Elapsed.TotalSeconds:0.0}s | loss: {val_loss:0.00}\n");
scheduler.step();
}
var tst_loss = evaluate(test_data, model, loss, lr, bptt, ntokens, optimizer);
totalTime.Stop();
Console.WriteLine($"\nEnd of training | time: {totalTime.Elapsed.TotalSeconds:0.0}s | loss: {tst_loss:0.00}\n");
}
