コード例 #1
0
def train(emb_size, vocab_size):
    global embeddings, words_to_train

    inp = input_variable(shape=(vocab_size, ))
    label = input_variable(shape=(vocab_size, ))

    init_width = 0.5 / emb_size
    emb = parameter(shape=(vocab_size, emb_size),
                    init=uniform(scale=init_width))
    embeddings = emb
    embinp = times(inp, emb)

    z = softmax(lrmodel(embinp, vocab_size))  # logistic regression model

    loss = -label * log(z) - ((1 - label) / (vocab_size - 1)) * log(1 - z)
    eval_error = classification_error(z, label)

    lr_per_sample = [0.003] * 4 + [0.0015] * 24 + [0.0003]
    lr_per_minibatch = [x * minibatch_size for x in lr_per_sample]
    lr_schedule = learning_rate_schedule(lr_per_minibatch, UnitType.minibatch)

    learner = sgd(z.parameters, lr=lr_schedule)
    trainer = Trainer(z, loss, eval_error, learner)

    return inp, label, trainer
コード例 #2
0
def train_sequence_classifier(debug_output=False):
    input_dim = 2000
    cell_dim = 25
    hidden_dim = 25
    embedding_dim = 50
    num_output_classes = 5

    # Input variables denoting the features and label data
    features = input_variable(shape=input_dim, is_sparse=True)
    label = input_variable(num_output_classes,
                           dynamic_axes=[Axis.default_batch_axis()])

    # Instantiate the sequence classification model
    classifier_output = LSTM_sequence_classifer_net(features,
                                                    num_output_classes,
                                                    embedding_dim, hidden_dim,
                                                    cell_dim)

    ce = cross_entropy_with_softmax(classifier_output, label)
    pe = classification_error(classifier_output, label)

    rel_path = r"../../../../Tests/EndToEndTests/Text/SequenceClassification/Data/Train.ctf"
    path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)

    reader = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        features: reader.streams.features,
        label: reader.streams.labels
    }

    lr_per_sample = learning_rate_schedule(0.0005, UnitType.sample)
    # Instantiate the trainer object to drive the model training
    trainer = Trainer(classifier_output, (ce, pe),
                      sgd(classifier_output.parameters, lr=lr_per_sample))

    # Get minibatches of sequences to train with and perform model training
    minibatch_size = 200
    training_progress_output_freq = 10

    if debug_output:
        training_progress_output_freq = training_progress_output_freq / 3

    for i in range(251):
        mb = reader.next_minibatch(minibatch_size, input_map=input_map)
        trainer.train_minibatch(mb)
        print_training_progress(trainer, i, training_progress_output_freq)

    import copy

    evaluation_average = copy.copy(
        trainer.previous_minibatch_evaluation_average)
    loss_average = copy.copy(trainer.previous_minibatch_loss_average)

    return evaluation_average, loss_average
コード例 #3
0
def train_sequence_classifier(debug_output=False):
    input_dim = 2000
    cell_dim = 25
    hidden_dim = 25
    embedding_dim = 50
    num_output_classes = 5

    # Input variables denoting the features and label data
    features = input_variable(shape=input_dim, is_sparse=True)
    label = input_variable(num_output_classes, dynamic_axes=[
                           Axis.default_batch_axis()])

    # Instantiate the sequence classification model
    classifier_output = LSTM_sequence_classifer_net(
        features, num_output_classes, embedding_dim, hidden_dim, cell_dim)

    ce = cross_entropy_with_softmax(classifier_output, label)
    pe = classification_error(classifier_output, label)

    rel_path = r"../../../../Tests/EndToEndTests/Text/SequenceClassification/Data/Train.ctf"
    path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)

    reader = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        features : reader.streams.features,
        label    : reader.streams.labels
    }

    lr_per_sample = learning_rate_schedule(0.0005, UnitType.sample)
    # Instantiate the trainer object to drive the model training
    trainer = Trainer(classifier_output, (ce, pe),
                      sgd(classifier_output.parameters, lr=lr_per_sample))

    # Get minibatches of sequences to train with and perform model training
    minibatch_size = 200
    training_progress_output_freq = 10

    if debug_output:
        training_progress_output_freq = training_progress_output_freq/3

    for i in range(251):
        mb = reader.next_minibatch(minibatch_size, input_map=input_map)
        trainer.train_minibatch(mb)
        print_training_progress(trainer, i, training_progress_output_freq)

    import copy

    evaluation_average = copy.copy(
        trainer.previous_minibatch_evaluation_average)
    loss_average = copy.copy(trainer.previous_minibatch_loss_average)

    return evaluation_average, loss_average
コード例 #4
0
def ffnet():
    inputs = 2
    outputs = 2
    layers = 2
    hidden_dimension = 50

    # input variables denoting the features and label data
    features = C.input_variable((inputs), np.float32)
    label = C.input_variable((outputs), np.float32)

    # Instantiate the feedforward classification model
    my_model = Sequential(
        [Dense(hidden_dimension, activation=C.sigmoid),
         Dense(outputs)])
    z = my_model(features)

    ce = C.cross_entropy_with_softmax(z, label)
    pe = C.classification_error(z, label)

    # Instantiate the trainer object to drive the model training
    lr_per_minibatch = learning_rate_schedule(0.125, UnitType.minibatch)
    progress_printer = ProgressPrinter(0)
    trainer = C.Trainer(z, (ce, pe), [sgd(z.parameters, lr=lr_per_minibatch)],
                        [progress_printer])

    # Get minibatches of training data and perform model training
    minibatch_size = 25
    num_minibatches_to_train = 1024

    aggregate_loss = 0.0
    for i in range(num_minibatches_to_train):
        train_features, labels = generate_random_data(minibatch_size, inputs,
                                                      outputs)
        # Specify the mapping of input variables in the model to actual minibatch data to be trained with
        trainer.train_minibatch({features: train_features, label: labels})
        sample_count = trainer.previous_minibatch_sample_count
        aggregate_loss += trainer.previous_minibatch_loss_average * sample_count

    last_avg_error = aggregate_loss / trainer.total_number_of_samples_seen

    test_features, test_labels = generate_random_data(minibatch_size, inputs,
                                                      outputs)
    avg_error = trainer.test_minibatch({
        features: test_features,
        label: test_labels
    })
    print(' error rate on an unseen minibatch: {}'.format(avg_error))
    return last_avg_error, avg_error
コード例 #5
0
def ffnet(debug_output=False):
    input_dim = 2
    num_output_classes = 2
    num_hidden_layers = 2
    hidden_layers_dim = 50

    # Input variables denoting the features and label data
    input = input_variable((input_dim), np.float32)
    label = input_variable((num_output_classes), np.float32)

    # Instantiate the feedforward classification model
    netout = fully_connected_classifier_net(input, num_output_classes,
                                            hidden_layers_dim,
                                            num_hidden_layers, sigmoid)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(netout, ce, pe, [sgd(netout.parameters(), lr=0.02)])

    # Get minibatches of training data and perform model training
    minibatch_size = 25
    num_samples_per_sweep = 10000
    num_sweeps_to_train_with = 2
    num_minibatches_to_train = (num_samples_per_sweep *
                                num_sweeps_to_train_with) / minibatch_size
    training_progress_output_freq = 60

    if debug_output:
        training_progress_output_freq = training_progress_output_freq / 3

    for i in range(0, int(num_minibatches_to_train)):
        features, labels = generate_random_data(minibatch_size, input_dim,
                                                num_output_classes)
        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        trainer.train_minibatch({input: features, label: labels})
        print_training_progress(trainer, i, training_progress_output_freq)

    test_features, test_labels = generate_random_data(minibatch_size,
                                                      input_dim,
                                                      num_output_classes)
    avg_error = trainer.test_minibatch({
        input: test_features,
        label: test_labels
    })
    return avg_error
コード例 #6
0
ファイル: learn_one.py プロジェクト: m3rik/nn
    def fit(self, X, y):
        X = np.array(X).astype(np.float32)
        y = np.array(y).astype(np.float32)
        learning_rate = 0.005
        lr_schedule = learning_rate_schedule(learning_rate, UnitType.minibatch)
        learner = sgd(self.z.parameters, lr_schedule)
        trainer = Trainer(self.z, self.loss, self.eval, [learner])

        # Initialize the parameters for the trainer
        minibatch_size = 1
        num_samples_to_train = len(X) * 5
        num_minibatches_to_train = int(num_samples_to_train / minibatch_size)

        count = 0
        for i in range(0, num_minibatches_to_train):
            # Specify input variables mapping in the model to actual minibatch data to be trained with
            trainer.train_minibatch({self.input_var: X[count:count+1], self.label_var: y[count:count+1]})
            count = (count + 1) % len(X)
コード例 #7
0
ファイル: FeedForwardNet.py プロジェクト: hahatt/CNTK
def ffnet(debug_output=False):
    input_dim = 2
    num_output_classes = 2
    num_hidden_layers = 2
    hidden_layers_dim = 50

    # Input variables denoting the features and label data
    input = input_variable((input_dim), np.float32)
    label = input_variable((num_output_classes), np.float32)

    # Instantiate the feedforward classification model
    netout = fully_connected_classifier_net(
        input, num_output_classes, hidden_layers_dim, num_hidden_layers, sigmoid)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(netout, ce, pe, [sgd(netout.parameters(), lr=0.02)])

    # Get minibatches of training data and perform model training
    minibatch_size = 25
    num_samples_per_sweep = 10000
    num_sweeps_to_train_with = 2
    num_minibatches_to_train = (
        num_samples_per_sweep * num_sweeps_to_train_with) / minibatch_size
    training_progress_output_freq = 60

    if debug_output:
        training_progress_output_freq = training_progress_output_freq/3

    for i in range(0, int(num_minibatches_to_train)):
        features, labels = generate_random_data(
            minibatch_size, input_dim, num_output_classes)
        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        trainer.train_minibatch({input: features, label: labels})
        print_training_progress(trainer, i, training_progress_output_freq)

    test_features, test_labels = generate_random_data(
        minibatch_size, input_dim, num_output_classes)
    avg_error = trainer.test_minibatch(
        {input: test_features, label: test_labels})
    return avg_error
コード例 #8
0
ファイル: FeedForwardNet.py プロジェクト: w1y2l32009/CNTK
def ffnet():
    input_dim = 2
    num_output_classes = 2
    num_hidden_layers = 2
    hidden_layers_dim = 50

    # Input variables denoting the features and label data
    input = input_variable((input_dim), np.float32)
    label = input_variable((num_output_classes), np.float32)

    # Instantiate the feedforward classification model
    netout = fully_connected_classifier_net(input, num_output_classes,
                                            hidden_layers_dim,
                                            num_hidden_layers, sigmoid)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    lr_per_minibatch = learning_rate_schedule(0.5, UnitType.minibatch)
    # Instantiate the trainer object to drive the model training
    learner = sgd(netout.parameters, lr=lr_per_minibatch)
    progress_printer = ProgressPrinter(128)
    trainer = Trainer(netout, (ce, pe), learner, progress_printer)

    # Get minibatches of training data and perform model training
    minibatch_size = 25

    for i in range(1024):
        features, labels = generate_random_data(minibatch_size, input_dim,
                                                num_output_classes)
        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        trainer.train_minibatch({input: features, label: labels})

    trainer.summarize_training_progress()
    test_features, test_labels = generate_random_data(minibatch_size,
                                                      input_dim,
                                                      num_output_classes)
    avg_error = trainer.test_minibatch({
        input: test_features,
        label: test_labels
    })
    return avg_error
コード例 #9
0
ファイル: simplenet.py プロジェクト: BorisJineman/CNTK
def ffnet():
    inputs = 2
    outputs = 2
    layers = 2
    hidden_dimension = 50

    # input variables denoting the features and label data
    features = C.input_variable((inputs), np.float32)
    label = C.input_variable((outputs), np.float32)

    # Instantiate the feedforward classification model
    my_model = Sequential ([
                    Dense(hidden_dimension, activation=C.sigmoid),
                    Dense(outputs)])
    z = my_model(features)

    ce = C.cross_entropy_with_softmax(z, label)
    pe = C.classification_error(z, label)

    # Instantiate the trainer object to drive the model training
    lr_per_minibatch = learning_rate_schedule(0.125, UnitType.minibatch)
    progress_printer = ProgressPrinter(0)
    trainer = C.Trainer(z, (ce, pe), [sgd(z.parameters, lr=lr_per_minibatch)], [progress_printer])

    # Get minibatches of training data and perform model training
    minibatch_size = 25
    num_minibatches_to_train = 1024

    aggregate_loss = 0.0
    for i in range(num_minibatches_to_train):
        train_features, labels = generate_random_data(minibatch_size, inputs, outputs)
        # Specify the mapping of input variables in the model to actual minibatch data to be trained with
        trainer.train_minibatch({features : train_features, label : labels})
        sample_count = trainer.previous_minibatch_sample_count
        aggregate_loss += trainer.previous_minibatch_loss_average * sample_count

    last_avg_error = aggregate_loss / trainer.total_number_of_samples_seen

    test_features, test_labels = generate_random_data(minibatch_size, inputs, outputs)
    avg_error = trainer.test_minibatch({features : test_features, label : test_labels})
    print(' error rate on an unseen minibatch: {}'.format(avg_error))
    return last_avg_error, avg_error
コード例 #10
0
ファイル: FeedForwardNet.py プロジェクト: BorisJineman/CNTK
def ffnet():
    input_dim = 2
    num_output_classes = 2
    num_hidden_layers = 2
    hidden_layers_dim = 50

    # Input variables denoting the features and label data
    input = input_variable((input_dim), np.float32)
    label = input_variable((num_output_classes), np.float32)

    # Instantiate the feedforward classification model
    netout = fully_connected_classifier_net(
        input, num_output_classes, hidden_layers_dim, num_hidden_layers, sigmoid)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    lr_per_minibatch=learning_rate_schedule(0.5, UnitType.minibatch)
    # Instantiate the trainer object to drive the model training
    learner = sgd(netout.parameters, lr=lr_per_minibatch)
    progress_printer = ProgressPrinter(128)
    trainer = Trainer(netout, (ce, pe), learner, progress_printer)

    # Get minibatches of training data and perform model training
    minibatch_size = 25

    for i in range(1024):
        features, labels = generate_random_data(
            minibatch_size, input_dim, num_output_classes)
        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        trainer.train_minibatch({input: features, label: labels})

    trainer.summarize_training_progress()
    test_features, test_labels = generate_random_data(
        minibatch_size, input_dim, num_output_classes)
    avg_error = trainer.test_minibatch(
        {input: test_features, label: test_labels})
    return avg_error
コード例 #11
0
def simple_mnist(tensorboard_logdir=None):
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    input = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant(0.00390625), input)
    z = fully_connected_classifier_net(scaled_input, num_output_classes,
                                       hidden_layers_dim, num_hidden_layers,
                                       relu)

    ce = cross_entropy_with_softmax(z, label)
    pe = classification_error(z, label)

    data_dir = os.path.join(abs_path, "..", "..", "..", "DataSets", "MNIST")

    path = os.path.normpath(os.path.join(data_dir,
                                         "Train-28x28_cntk_text.txt"))
    check_path(path)

    reader_train = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        input: reader_train.streams.features,
        label: reader_train.streams.labels
    }

    # Training config
    minibatch_size = 64
    num_samples_per_sweep = 60000
    num_sweeps_to_train_with = 10

    # Instantiate progress writers.
    #training_progress_output_freq = 100
    progress_writers = [
        ProgressPrinter(
            #freq=training_progress_output_freq,
            tag='Training',
            num_epochs=num_sweeps_to_train_with)
    ]

    if tensorboard_logdir is not None:
        progress_writers.append(
            TensorBoardProgressWriter(freq=10,
                                      log_dir=tensorboard_logdir,
                                      model=z))

    # Instantiate the trainer object to drive the model training
    lr_per_minibatch = learning_rate_schedule(0.2, UnitType.minibatch)
    trainer = Trainer(z, (ce, pe), sgd(z.parameters, lr=lr_per_minibatch),
                      progress_writers)

    training_session(trainer=trainer,
                     mb_source=reader_train,
                     mb_size=minibatch_size,
                     var_to_stream=input_map,
                     max_samples=num_samples_per_sweep *
                     num_sweeps_to_train_with,
                     progress_frequency=num_samples_per_sweep).train()

    # Load test data
    path = os.path.normpath(os.path.join(data_dir, "Test-28x28_cntk_text.txt"))
    check_path(path)

    reader_test = create_reader(path, False, input_dim, num_output_classes)

    input_map = {
        input: reader_test.streams.features,
        label: reader_test.streams.labels
    }

    # Test data for trained model
    test_minibatch_size = 1024
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = reader_test.next_minibatch(test_minibatch_size,
                                        input_map=input_map)
        eval_error = trainer.test_minibatch(mb)
        test_result = test_result + eval_error

    # Average of evaluation errors of all test minibatches
    return test_result / num_minibatches_to_test
コード例 #12
0
def train_sequence_classifier():
    input_dim = 2000
    cell_dim = 25
    hidden_dim = 25
    embedding_dim = 50
    num_output_classes = 5

    # Input variables denoting the features and label data
    features = input_variable(shape=input_dim, is_sparse=True)
    label = input_variable(num_output_classes,
                           dynamic_axes=[Axis.default_batch_axis()])

    # Instantiate the sequence classification model
    classifier_output = LSTM_sequence_classifer_net(features,
                                                    num_output_classes,
                                                    embedding_dim, hidden_dim,
                                                    cell_dim)

    ce = cross_entropy_with_softmax(classifier_output, label)
    pe = classification_error(classifier_output, label)

    rel_path = r"../../../../Tests/EndToEndTests/Text/SequenceClassification/Data/Train.ctf"
    path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)
    feature_stream_name = 'features'
    labels_stream_name = 'labels'

    mb_source = text_format_minibatch_source(path, [
        StreamConfiguration(feature_stream_name, input_dim, True, 'x'),
        StreamConfiguration(labels_stream_name, num_output_classes, False, 'y')
    ], 0)

    features_si = mb_source.stream_info(features)
    labels_si = mb_source.stream_info(label)

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(classifier_output, ce, pe,
                      [sgd(classifier_output.parameters(), lr=0.0005)])

    # Get minibatches of sequences to train with and perform model training
    minibatch_size = 200
    training_progress_output_freq = 10
    i = 0
    while True:
        mb = mb_source.get_next_minibatch(minibatch_size)

        if len(mb) == 0:
            break

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {
            features: mb[features_si].m_data,
            label: mb[labels_si].m_data
        }
        trainer.train_minibatch(arguments)

        print_training_progress(trainer, i, training_progress_output_freq)

        i += 1

    import copy

    evaluation_average = copy.copy(
        trainer.previous_minibatch_evaluation_average())
    loss_average = copy.copy(trainer.previous_minibatch_loss_average())

    return evaluation_average, loss_average
コード例 #13
0
ファイル: SimpleMNIST.py プロジェクト: rlugojr/CNTK
def simple_mnist():
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    features = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant(0.00390625), features)
    netout = fully_connected_classifier_net(
        scaled_input, num_output_classes, hidden_layers_dim, num_hidden_layers, relu)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    try:
        rel_path = os.path.join(os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
                                *"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(*"../Image/DataSets/MNIST/Train-28x28_cntk_text.txt".split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_train = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        features: reader_train.streams.features,
        label: reader_train.streams.labels
    }

    # Instantiate progress writers.
    logdir = os.path.join(os.path.dirname(os.path.abspath(__file__)), "mnist_log")
    tensorboard_writer = TensorBoardProgressWriter(freq=1, log_dir=logdir, model=netout)
    progress_printer = ProgressPrinter(freq=10, tag='Training')

    # Instantiate the trainer object to drive the model training
    lr_per_minibatch = learning_rate_schedule(0.2, UnitType.minibatch)
    learner = sgd(netout.parameters, lr=lr_per_minibatch)
    trainer = Trainer(netout, (ce, pe), learner, [tensorboard_writer, progress_printer])

    # Get minibatches of images to train with and perform model training
    minibatch_size = 64
    num_samples_per_sweep = 6000
    num_sweeps_to_train_with = 2
    num_minibatches_to_train = (num_samples_per_sweep * num_sweeps_to_train_with) / minibatch_size

    for minibatch_idx in range(0, int(num_minibatches_to_train)):
        trainer.train_minibatch(reader_train.next_minibatch(minibatch_size, input_map=input_map))

        # Log max/min/mean of each parameter tensor, so that we can confirm that the parameters change indeed.
        # Don't want to do that very often though, otherwise will spend too much time computing min/max/mean.
        if minibatch_idx % 10 == 9:
            for p in netout.parameters:
                tensorboard_writer.write_value(p.uid + "/max", reduce_max(p).eval(), minibatch_idx)
                tensorboard_writer.write_value(p.uid + "/min", reduce_min(p).eval(), minibatch_idx)
                tensorboard_writer.write_value(p.uid + "/mean", reduce_mean(p).eval(), minibatch_idx)

    trainer.summarize_training_progress()

    # Load test data
    try:
        rel_path = os.path.join(os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
                                *"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(*"../Image/DataSets/MNIST/Test-28x28_cntk_text.txt".split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_test = create_reader(path, False, input_dim, num_output_classes)

    input_map = {
        features: reader_test.streams.features,
        label: reader_test.streams.labels
    }

    # Test data for trained model
    test_minibatch_size = 1024
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = reader_test.next_minibatch(test_minibatch_size, input_map=input_map)
        test_result += trainer.test_minibatch(mb)

    # Average of evaluation errors of all test minibatches
    trainer.summarize_test_progress()
    return test_result / num_minibatches_to_test
コード例 #14
0
ファイル: SequenceClassification.py プロジェクト: hahatt/CNTK
def train_sequence_classifier(debug_output=False):
    input_dim = 2000
    cell_dim = 25
    hidden_dim = 25
    embedding_dim = 50
    num_output_classes = 5

    # Input variables denoting the features and label data
    features = input_variable(shape=input_dim, is_sparse=True)
    label = input_variable(num_output_classes, dynamic_axes=[
                           Axis.default_batch_axis()])

    # Instantiate the sequence classification model
    classifier_output = LSTM_sequence_classifer_net(
        features, num_output_classes, embedding_dim, hidden_dim, cell_dim)

    ce = cross_entropy_with_softmax(classifier_output, label)
    pe = classification_error(classifier_output, label)

    rel_path = r"../../../../Tests/EndToEndTests/Text/SequenceClassification/Data/Train.ctf"
    path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)
    feature_stream_name = 'features'
    labels_stream_name = 'labels'

    mb_source = text_format_minibatch_source(path, [
        StreamConfiguration(feature_stream_name, input_dim, True, 'x'),
        StreamConfiguration(labels_stream_name, num_output_classes, False, 'y')], 0)

    features_si = mb_source[features]
    labels_si = mb_source[label]

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(classifier_output, ce, pe,
                      [sgd(classifier_output.parameters(), lr=0.0005)])

    # Get minibatches of sequences to train with and perform model training
    minibatch_size = 200
    training_progress_output_freq = 10
    i = 0

    if debug_output:
        training_progress_output_freq = training_progress_output_freq/3

    while True:
        mb = mb_source.get_next_minibatch(minibatch_size)

        if len(mb) == 0:
            break

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {features: mb[features_si],
                     label: mb[labels_si]}
        trainer.train_minibatch(arguments)

        print_training_progress(trainer, i, training_progress_output_freq)
        i += 1

    import copy

    evaluation_average = copy.copy(
        trainer.previous_minibatch_evaluation_average())
    loss_average = copy.copy(trainer.previous_minibatch_loss_average())

    return evaluation_average, loss_average
コード例 #15
0
ファイル: SimpleMNIST.py プロジェクト: yzhang87/CNTK
def simple_mnist(debug_output=False):
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    input = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant((), 0.00390625), input)
    netout = fully_connected_classifier_net(
        scaled_input, num_output_classes, hidden_layers_dim, num_hidden_layers, sigmoid
    )

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    try:
        rel_path = os.path.join(
            os.environ["CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY"],
            *"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/")
        )
    except KeyError:
        rel_path = os.path.join(*"../../../../Examples/Image/Datasets/MNIST/Train-28x28_cntk_text.txt".split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    feature_stream_name = "features"
    labels_stream_name = "labels"

    mb_source = text_format_minibatch_source(
        path,
        [
            StreamConfiguration(feature_stream_name, input_dim),
            StreamConfiguration(labels_stream_name, num_output_classes),
        ],
    )
    features_si = mb_source[feature_stream_name]
    labels_si = mb_source[labels_stream_name]

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(netout, ce, pe, [sgd(netout.parameters(), lr=0.003125)])

    # Get minibatches of images to train with and perform model training
    minibatch_size = 32
    num_samples_per_sweep = 60000
    num_sweeps_to_train_with = 1
    num_minibatches_to_train = (num_samples_per_sweep * num_sweeps_to_train_with) / minibatch_size
    training_progress_output_freq = 80

    if debug_output:
        training_progress_output_freq = training_progress_output_freq / 4

    for i in range(0, int(num_minibatches_to_train)):
        mb = mb_source.get_next_minibatch(minibatch_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {input: mb[features_si], label: mb[labels_si]}
        trainer.train_minibatch(arguments)

        print_training_progress(trainer, i, training_progress_output_freq)

    # Load test data
    try:
        rel_path = os.path.join(
            os.environ["CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY"], *"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/")
        )
    except KeyError:
        rel_path = os.path.join(*"../../../../Examples/Image/Datasets/MNIST/Test-28x28_cntk_text.txt".split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    test_mb_source = text_format_minibatch_source(
        path,
        [
            StreamConfiguration(feature_stream_name, input_dim),
            StreamConfiguration(labels_stream_name, num_output_classes),
        ],
        randomize=False,
    )
    features_si = test_mb_source[feature_stream_name]
    labels_si = test_mb_source[labels_stream_name]

    # Test data for trained model
    test_minibatch_size = 512
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = test_mb_source.get_next_minibatch(test_minibatch_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be tested with
        arguments = {input: mb[features_si], label: mb[labels_si]}
        eval_error = trainer.test_minibatch(arguments)
        test_result = test_result + eval_error

    # Average of evaluation errors of all test minibatches
    return test_result / num_minibatches_to_test
コード例 #16
0
ファイル: logistic_regression.py プロジェクト: itoupeter/CNTK
    input_dim = input_var.shape[0]
    weight_param = parameter(shape=(input_dim, output_dim))
    bias_param = parameter(shape=(output_dim))
    mydict['w'], mydict['b'] = weight_param, bias_param
    return times(input_var, weight_param) + bias_param


output_dim = num_output_classes
z = linear_layer(input, output_dim)
label = input_variable((num_output_classes), np.float32)
loss = cross_entropy_with_softmax(z, label)
eval_error = classification_error(z, label)

learning_rate = 0.5
lr_schedule = learning_rate_schedule(learning_rate, UnitType.minibatch)
learner = sgd(z.parameters, lr_schedule)
trainer = Trainer(z, (loss, eval_error), [learner])


def moving_average(a, w=10):
    if len(a) < w:
        return a[:]
    return [
        val if idx < w else sum(a[(idx - w):idx]) / w
        for idx, val in enumerate(a)
    ]


def print_training_progress(trainer, mb, frequency, verbose=True):
    training_loss, eval_error = "NA", "NA"
コード例 #17
0
def simple_mnist(debug_output=False):
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    input = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant((), 0.00390625), input)
    netout = fully_connected_classifier_net(scaled_input, num_output_classes,
                                            hidden_layers_dim,
                                            num_hidden_layers, sigmoid)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    try:
        rel_path = os.path.join(
            os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
            *"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(
            *"../../../../Examples/Image/MNIST/Data/Train-28x28_cntk_text.txt".
            split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    feature_stream_name = 'features'
    labels_stream_name = 'labels'

    mb_source = text_format_minibatch_source(path, [
        StreamConfiguration(feature_stream_name, input_dim),
        StreamConfiguration(labels_stream_name, num_output_classes)
    ])
    features_si = mb_source.stream_info(feature_stream_name)
    labels_si = mb_source.stream_info(labels_stream_name)

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(netout, ce, pe, [sgd(netout.parameters(), lr=0.003125)])

    # Get minibatches of images to train with and perform model training
    minibatch_size = 32
    num_samples_per_sweep = 60000
    num_sweeps_to_train_with = 1
    num_minibatches_to_train = (num_samples_per_sweep *
                                num_sweeps_to_train_with) / minibatch_size
    training_progress_output_freq = 20
    for i in range(0, int(num_minibatches_to_train)):
        mb = mb_source.get_next_minibatch(minibatch_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {
            input: mb[features_si].m_data,
            label: mb[labels_si].m_data
        }
        trainer.train_minibatch(arguments)

        if debug_output:
            print_training_progress(trainer, i, training_progress_output_freq)

    # Load test data
    try:
        rel_path = os.path.join(
            os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
            *"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(
            *"../../../../Examples/Image/MNIST/Data/Test-28x28_cntk_text.txt".
            split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    test_mb_source = text_format_minibatch_source(path, [
        StreamConfiguration(feature_stream_name, input_dim),
        StreamConfiguration(labels_stream_name, num_output_classes)
    ])
    features_si = test_mb_source.stream_info(feature_stream_name)
    labels_si = test_mb_source.stream_info(labels_stream_name)

    # Test data for trained model
    test_minibatch_size = 512
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = test_mb_source.get_next_minibatch(test_minibatch_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be tested with
        arguments = {
            input: mb[features_si].m_data,
            label: mb[labels_si].m_data
        }
        eval_error = trainer.test_minibatch(arguments)
        test_result = test_result + eval_error

    # Average of evaluation errors of all test minibatches
    return test_result / num_minibatches_to_test
コード例 #18
0
def simple_mnist():
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    features = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant(0.00390625), features)
    netout = fully_connected_classifier_net(scaled_input, num_output_classes,
                                            hidden_layers_dim,
                                            num_hidden_layers, relu)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    try:
        rel_path = os.path.join(
            os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
            *"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(
            *"../Image/DataSets/MNIST/Train-28x28_cntk_text.txt".split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_train = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        features: reader_train.streams.features,
        label: reader_train.streams.labels
    }

    # Instantiate progress writers.
    logdir = os.path.join(os.path.dirname(os.path.abspath(__file__)),
                          "mnist_log")
    tensorboard_writer = TensorBoardProgressWriter(freq=1,
                                                   log_dir=logdir,
                                                   model=netout)
    progress_printer = ProgressPrinter(freq=10, tag='Training')

    # Instantiate the trainer object to drive the model training
    lr_per_minibatch = learning_rate_schedule(0.2, UnitType.minibatch)
    learner = sgd(netout.parameters, lr=lr_per_minibatch)
    trainer = Trainer(netout, (ce, pe), learner,
                      [tensorboard_writer, progress_printer])

    # Get minibatches of images to train with and perform model training
    minibatch_size = 64
    num_samples_per_sweep = 6000
    num_sweeps_to_train_with = 2
    num_minibatches_to_train = (num_samples_per_sweep *
                                num_sweeps_to_train_with) / minibatch_size

    for minibatch_idx in range(0, int(num_minibatches_to_train)):
        trainer.train_minibatch(
            reader_train.next_minibatch(minibatch_size, input_map=input_map))

        # Log max/min/mean of each parameter tensor, so that we can confirm that the parameters change indeed.
        # Don't want to do that very often though, otherwise will spend too much time computing min/max/mean.
        if minibatch_idx % 10 == 9:
            for p in netout.parameters:
                tensorboard_writer.write_value(p.uid + "/max",
                                               reduce_max(p).eval(),
                                               minibatch_idx)
                tensorboard_writer.write_value(p.uid + "/min",
                                               reduce_min(p).eval(),
                                               minibatch_idx)
                tensorboard_writer.write_value(p.uid + "/mean",
                                               reduce_mean(p).eval(),
                                               minibatch_idx)

    trainer.summarize_training_progress()

    # Load test data
    try:
        rel_path = os.path.join(
            os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
            *"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(
            *"../Image/DataSets/MNIST/Test-28x28_cntk_text.txt".split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_test = create_reader(path, False, input_dim, num_output_classes)

    input_map = {
        features: reader_test.streams.features,
        label: reader_test.streams.labels
    }

    # Test data for trained model
    test_minibatch_size = 1024
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = reader_test.next_minibatch(test_minibatch_size,
                                        input_map=input_map)
        test_result += trainer.test_minibatch(mb)

    # Average of evaluation errors of all test minibatches
    trainer.summarize_test_progress()
    return test_result / num_minibatches_to_test
コード例 #19
0
ファイル: SimpleMNIST.py プロジェクト: lab3000/GalvanizeU
def simple_mnist(debug_output=False):
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    input = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant(0.00390625), input)
    netout = fully_connected_classifier_net(scaled_input, num_output_classes,
                                            hidden_layers_dim,
                                            num_hidden_layers, relu)

    ce = cross_entropy_with_softmax(netout, label)
    pe = classification_error(netout, label)

    try:
        rel_path = os.path.join(
            os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
            *"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(
            *
            "../../../../Examples/Image/DataSets/MNIST/Train-28x28_cntk_text.txt"
            .split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_train = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        input: reader_train.streams.features,
        label: reader_train.streams.labels
    }

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(netout, ce, pe, sgd(netout.parameters, lr=0.003125))

    # Get minibatches of images to train with and perform model training
    minibatch_size = 64
    num_samples_per_sweep = 60000
    num_sweeps_to_train_with = 10
    num_minibatches_to_train = (num_samples_per_sweep *
                                num_sweeps_to_train_with) / minibatch_size
    training_progress_output_freq = 500

    if debug_output:
        training_progress_output_freq = training_progress_output_freq / 4

    for i in range(0, int(num_minibatches_to_train)):
        mb = reader_train.next_minibatch(minibatch_size, input_map=input_map)
        trainer.train_minibatch(mb)
        print_training_progress(trainer, i, training_progress_output_freq)

    # Load test data
    try:
        rel_path = os.path.join(
            os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
            *"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(
            *
            "../../../../Examples/Image/DataSets/MNIST/Test-28x28_cntk_text.txt"
            .split("/"))
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_test = create_reader(path, False, input_dim, num_output_classes)

    input_map = {
        input: reader_test.streams.features,
        label: reader_test.streams.labels
    }

    # Test data for trained model
    test_minibatch_size = 1024
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = reader_test.next_minibatch(test_minibatch_size,
                                        input_map=input_map)
        eval_error = trainer.test_minibatch(mb)
        test_result = test_result + eval_error

    # Average of evaluation errors of all test minibatches
    return test_result / num_minibatches_to_test
コード例 #20
0
ファイル: CifarResNet.py プロジェクト: zengjianping/CNTK
def cifar_resnet(base_path, debug_output=False):
    image_height = 32
    image_width = 32
    num_channels = 3
    num_classes = 10
    feats_stream_name = 'features'
    labels_stream_name = 'labels'

    minibatch_source = create_mb_source(feats_stream_name, labels_stream_name,
                                        image_height, image_width,
                                        num_channels, num_classes, base_path)
    features_si = minibatch_source[feats_stream_name]
    labels_si = minibatch_source[labels_stream_name]

    # Input variables denoting the features and label data
    image_input = input_variable((num_channels, image_height, image_width),
                                 features_si.m_element_type)
    label_var = input_variable((num_classes), features_si.m_element_type)

    # Instantiate the resnet classification model
    classifier_output = resnet_classifer(image_input, num_classes)

    ce = cross_entropy_with_softmax(classifier_output, label_var)
    pe = classification_error(classifier_output, label_var)

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(classifier_output, ce, pe,
                      [sgd(classifier_output.parameters(), lr=0.0078125)])

    # Get minibatches of images to train with and perform model training
    mb_size = 32
    training_progress_output_freq = 60
    num_mbs = 1000

    if debug_output:
        training_progress_output_freq = training_progress_output_freq / 3

    for i in range(0, num_mbs):
        mb = minibatch_source.get_next_minibatch(mb_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {image_input: mb[features_si], label_var: mb[labels_si]}
        trainer.train_minibatch(arguments)

        print_training_progress(trainer, i, training_progress_output_freq)

    test_minibatch_source = create_test_mb_source(feats_stream_name,
                                                  labels_stream_name,
                                                  image_height, image_width,
                                                  num_channels, num_classes,
                                                  base_path)
    features_si = test_minibatch_source[feats_stream_name]
    labels_si = test_minibatch_source[labels_stream_name]

    mb_size = 64
    num_mbs = 300

    total_error = 0.0
    for i in range(0, num_mbs):
        mb = test_minibatch_source.get_next_minibatch(mb_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {image_input: mb[features_si], label_var: mb[labels_si]}
        error = trainer.test_minibatch(arguments)
        total_error += error

    return total_error / num_mbs
コード例 #21
0
ファイル: SimpleMNIST.py プロジェクト: yeswici/CNTK
def simple_mnist(debug_output=False):
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    input = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant(0.00390625), input)
    z = fully_connected_classifier_net(
        scaled_input, num_output_classes, hidden_layers_dim, num_hidden_layers, relu)

    ce = cross_entropy_with_softmax(z, label)
    pe = classification_error(z, label)

    data_dir = os.path.join(abs_path, "..", "..", "..", "DataSets", "MNIST")

    path = os.path.normpath(os.path.join(data_dir, "Train-28x28_cntk_text.txt"))
    check_path(path)

    reader_train = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        input  : reader_train.streams.features,
        label  : reader_train.streams.labels
    }

    lr_per_minibatch=learning_rate_schedule(0.2, UnitType.minibatch)
    # Instantiate the trainer object to drive the model training
    trainer = Trainer(z, ce, pe, sgd(z.parameters, lr=lr_per_minibatch))

    # Get minibatches of images to train with and perform model training
    minibatch_size = 64
    num_samples_per_sweep = 60000
    num_sweeps_to_train_with = 10
    num_minibatches_to_train = (num_samples_per_sweep * num_sweeps_to_train_with) / minibatch_size
    training_progress_output_freq = 500

    if debug_output:
        training_progress_output_freq = training_progress_output_freq/4

    for i in range(0, int(num_minibatches_to_train)):
        mb = reader_train.next_minibatch(minibatch_size, input_map=input_map)
        trainer.train_minibatch(mb)
        print_training_progress(trainer, i, training_progress_output_freq)

    # Load test data
    path = os.path.normpath(os.path.join(data_dir, "Test-28x28_cntk_text.txt"))
    check_path(path)

    reader_test = create_reader(path, False, input_dim, num_output_classes)

    input_map = {
        input  : reader_test.streams.features,
        label  : reader_test.streams.labels
    }

    # Test data for trained model
    test_minibatch_size = 1024
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = reader_test.next_minibatch(test_minibatch_size, input_map=input_map)
        eval_error = trainer.test_minibatch(mb)
        test_result = test_result + eval_error

    # Average of evaluation errors of all test minibatches
    return test_result / num_minibatches_to_test
コード例 #22
0
ファイル: CifarResNet.py プロジェクト: hahatt/CNTK
def cifar_resnet(base_path, debug_output=False):
    image_height = 32
    image_width = 32
    num_channels = 3
    num_classes = 10
    feats_stream_name = 'features'
    labels_stream_name = 'labels'

    minibatch_source = create_mb_source(feats_stream_name, labels_stream_name, 
                        image_height, image_width, num_channels, num_classes, base_path)
    features_si = minibatch_source[feats_stream_name]
    labels_si = minibatch_source[labels_stream_name]

    # Input variables denoting the features and label data
    image_input = input_variable(
        (num_channels, image_height, image_width), features_si.m_element_type)
    label_var = input_variable((num_classes), features_si.m_element_type)

    # Instantiate the resnet classification model
    classifier_output = resnet_classifer(image_input, num_classes)

    ce = cross_entropy_with_softmax(classifier_output, label_var)
    pe = classification_error(classifier_output, label_var)

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(classifier_output, ce, pe,
                      [sgd(classifier_output.parameters(), lr=0.0078125)])

    # Get minibatches of images to train with and perform model training
    mb_size = 32
    training_progress_output_freq = 60
    num_mbs = 1000

    if debug_output:
        training_progress_output_freq = training_progress_output_freq/3

    for i in range(0, num_mbs):
        mb = minibatch_source.get_next_minibatch(mb_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {
                image_input: mb[features_si], 
                label_var: mb[labels_si]
                }
        trainer.train_minibatch(arguments)

        print_training_progress(trainer, i, training_progress_output_freq)

    test_minibatch_source = create_test_mb_source(feats_stream_name, labels_stream_name,
                    image_height, image_width, num_channels, num_classes, base_path)
    features_si = test_minibatch_source[feats_stream_name]
    labels_si = test_minibatch_source[labels_stream_name]

    mb_size = 64
    num_mbs = 300

    total_error = 0.0
    for i in range(0, num_mbs):
        mb = test_minibatch_source.get_next_minibatch(mb_size)

        # Specify the mapping of input variables in the model to actual
        # minibatch data to be trained with
        arguments = {
                image_input: mb[features_si], 
                label_var: mb[labels_si]
                }
        error = trainer.test_minibatch(arguments)
        total_error += error

    return total_error / num_mbs
コード例 #23
0
#available activation function: relu, leaky_relu, sigmoid, tanh

if nettype == "cls":
    model = create_model(input, output_dim, [25, 25, 25], sigmoid)
    ce = cross_entropy_with_softmax(model, label)
    lr_per_minibatch=learning_rate_schedule(0.25, UnitType.minibatch)
else:
    if output_dim == 3:
        model = create_model(input, output_dim, [100, 80, 50, 20], sigmoid)
    else:
        model = create_model(input, output_dim, [50, 30, 20], sigmoid)
    lr_per_minibatch=learning_rate_schedule(0.25, UnitType.minibatch)
    ce = squared_error(model, label)

pe = classification_error(model, label)
trainer = Trainer(model, (ce, pe), sgd(model.parameters, lr=lr_per_minibatch))

mini_batch_sz = 25    
error = 0.0;
expFactor = 0.001;

for ep in range(epochs):
    for i in range(0, N, mini_batch_sz):
        j = i + mini_batch_sz
        trainer.train_minibatch({input: features[i:j], label: labels[i:j]})
        error = (1-expFactor)*error + expFactor*trainer.previous_minibatch_loss_average * mini_batch_sz;
    if (ep+1) % refreshFreq == 0:
        LogReport(ep+1, error)

if ep % refreshFreq != 0 :
    LogReport(ep, 1.00)
コード例 #24
0
ファイル: SimpleMNIST.py プロジェクト: Microsoft/CNTK
def simple_mnist(debug_output=False):
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    input = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant(0.00390625), input)
    z = fully_connected_classifier_net(
        scaled_input, num_output_classes, hidden_layers_dim, num_hidden_layers, relu)

    ce = cross_entropy_with_softmax(z, label)
    pe = classification_error(z, label)

    try:
        rel_path = os.path.join(os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
                                *"Image/MNIST/v0/Train-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(abs_path, "..", "..", "..", "..", "..", "Examples", "Image", "DataSets", "MNIST", "Train-28x28_cntk_text.txt")
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_train = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        input  : reader_train.streams.features,
        label  : reader_train.streams.labels
    }

    lr_per_minibatch=learning_rate_schedule(0.2, UnitType.minibatch)
    # Instantiate the trainer object to drive the model training
    trainer = Trainer(z, ce, pe, sgd(z.parameters, lr=lr_per_minibatch))

    # Get minibatches of images to train with and perform model training
    minibatch_size = 64
    num_samples_per_sweep = 60000
    num_sweeps_to_train_with = 10
    num_minibatches_to_train = (num_samples_per_sweep * num_sweeps_to_train_with) / minibatch_size
    training_progress_output_freq = 500



    if debug_output:
        training_progress_output_freq = training_progress_output_freq/4

    for i in range(0, int(num_minibatches_to_train)):
        mb = reader_train.next_minibatch(minibatch_size, input_map=input_map)
        trainer.train_minibatch(mb)
        print_training_progress(trainer, i, training_progress_output_freq)

    # Load test data
    try:
        rel_path = os.path.join(os.environ['CNTK_EXTERNAL_TESTDATA_SOURCE_DIRECTORY'],
                                *"Image/MNIST/v0/Test-28x28_cntk_text.txt".split("/"))
    except KeyError:
        rel_path = os.path.join(abs_path, "..", "..", "..", "..", "..", "Examples", "Image", "DataSets", "MNIST", "Test-28x28_cntk_text.txt")
    path = os.path.normpath(os.path.join(abs_path, rel_path))
    check_path(path)

    reader_test = create_reader(path, False, input_dim, num_output_classes)

    input_map = {
        input  : reader_test.streams.features,
        label  : reader_test.streams.labels
    }

    # Test data for trained model
    test_minibatch_size = 1024
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = reader_test.next_minibatch(test_minibatch_size, input_map=input_map)
        eval_error = trainer.test_minibatch(mb)
        test_result = test_result + eval_error

    # Average of evaluation errors of all test minibatches
    return test_result / num_minibatches_to_test
コード例 #25
0
ファイル: SimpleMNIST.py プロジェクト: BorisJineman/CNTK
def simple_mnist(tensorboard_logdir=None):
    input_dim = 784
    num_output_classes = 10
    num_hidden_layers = 1
    hidden_layers_dim = 200

    # Input variables denoting the features and label data
    input = input_variable(input_dim, np.float32)
    label = input_variable(num_output_classes, np.float32)

    # Instantiate the feedforward classification model
    scaled_input = element_times(constant(0.00390625), input)
    z = fully_connected_classifier_net(
        scaled_input, num_output_classes, hidden_layers_dim, num_hidden_layers, relu)

    ce = cross_entropy_with_softmax(z, label)
    pe = classification_error(z, label)

    data_dir = os.path.join(abs_path, "..", "..", "..", "DataSets", "MNIST")

    path = os.path.normpath(os.path.join(data_dir, "Train-28x28_cntk_text.txt"))
    check_path(path)

    reader_train = create_reader(path, True, input_dim, num_output_classes)

    input_map = {
        input  : reader_train.streams.features,
        label  : reader_train.streams.labels
    }

    # Training config
    minibatch_size = 64
    num_samples_per_sweep = 60000
    num_sweeps_to_train_with = 10

    # Instantiate progress writers.
    #training_progress_output_freq = 100
    progress_writers = [ProgressPrinter(
        #freq=training_progress_output_freq,
        tag='Training',
        num_epochs=num_sweeps_to_train_with)]

    if tensorboard_logdir is not None:
        progress_writers.append(TensorBoardProgressWriter(freq=10, log_dir=tensorboard_logdir, model=z))

    # Instantiate the trainer object to drive the model training
    lr_per_minibatch = learning_rate_schedule(0.2, UnitType.minibatch)
    trainer = Trainer(z, (ce, pe), sgd(z.parameters, lr=lr_per_minibatch), progress_writers)

    training_session(
        trainer=trainer,
        mb_source = reader_train,
        mb_size = minibatch_size,
        var_to_stream = input_map,
        max_samples = num_samples_per_sweep * num_sweeps_to_train_with,
        progress_frequency=num_samples_per_sweep
    ).train()
    
    # Load test data
    path = os.path.normpath(os.path.join(data_dir, "Test-28x28_cntk_text.txt"))
    check_path(path)

    reader_test = create_reader(path, False, input_dim, num_output_classes)

    input_map = {
        input  : reader_test.streams.features,
        label  : reader_test.streams.labels
    }

    # Test data for trained model
    test_minibatch_size = 1024
    num_samples = 10000
    num_minibatches_to_test = num_samples / test_minibatch_size
    test_result = 0.0
    for i in range(0, int(num_minibatches_to_test)):
        mb = reader_test.next_minibatch(test_minibatch_size, input_map=input_map)
        eval_error = trainer.test_minibatch(mb)
        test_result = test_result + eval_error

    # Average of evaluation errors of all test minibatches
    return test_result / num_minibatches_to_test