train_cnn.py 文件源码

def main(options):

    #load the config params
    gpu = options['gpu']
    data_path = options['path_dataset']
    embeddings_path = options['path_vectors']
    n_epoch = options['epochs']
    batchsize = options['batchsize']
    test = options['test']
    embed_dim = options['embed_dim']
    freeze = options['freeze_embeddings']

    #load the data
    data_processor = DataProcessor(data_path, test)
    data_processor.prepare_dataset()
    train_data = data_processor.train_data
    dev_data = data_processor.dev_data
    test_data = data_processor.test_data

    vocab = data_processor.vocab
    cnn = CNN(n_vocab=len(vocab), input_channel=1,
                  output_channel=10, n_label=2, embed_dim=embed_dim, freeze=freeze)
    cnn.load_embeddings(embeddings_path, data_processor.vocab)
    model = L.Classifier(cnn)
    if gpu >= 0:
        model.to_gpu()

    #setup the optimizer
    optimizer = O.Adam()
    optimizer.setup(model)


    train_iter = chainer.iterators.SerialIterator(train_data, batchsize)
    dev_iter = chainer.iterators.SerialIterator(dev_data, batchsize,repeat=False, shuffle=False)
    test_iter = chainer.iterators.SerialIterator(test_data, batchsize,repeat=False, shuffle=False) 
    batch1 = train_iter.next()
    batch2 = dev_iter.next()
    updater = training.StandardUpdater(train_iter, optimizer, converter=util.concat_examples, device=gpu)
    trainer = training.Trainer(updater, (n_epoch, 'epoch'))

    # Evaluation
    eval_model = model.copy()
    eval_model.predictor.train = False
    trainer.extend(extensions.Evaluator(dev_iter, eval_model, device=gpu, converter=util.concat_examples))

    test_model = model.copy()
    test_model.predictor.train = False

    trainer.extend(extensions.LogReport())
    trainer.extend(extensions.PrintReport(
        ['epoch', 'main/loss', 'validation/main/loss',
         'main/accuracy', 'validation/main/accuracy']))
    trainer.extend(extensions.ProgressBar(update_interval=10))


    trainer.run()