Python Trainer.test_minibatch方法代码示例

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def entrenar(checkpoint, entrRuedas, entrOperaciones, input_dim, num_output_classes, testRuedas, testOperaciones):
    minibatch_size = 100;
    epocs=900;
    minibatchIteraciones = int(len(entrOperaciones) / minibatch_size);

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

    netout = crearRed(input_dim, num_output_classes, feature);

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

    lr_per_minibatch=learning_rate_schedule(0.25, UnitType.minibatch)
    # Instantiate the trainer object to drive the model training
    learner = sgd(netout.parameters, lr=lr_per_minibatch)
    progress_printer = ProgressPrinter(log_to_file=checkpoint+".log", num_epochs=epocs);
    trainer = Trainer(netout, (ce, pe), learner, progress_printer)


    if os.path.isfile(checkpoint):
        trainer.restore_from_checkpoint(checkpoint);

    npentrRuedas = np.array(entrRuedas).astype(np.float32);
    npentrOperaciones = np.array(entrOperaciones).astype(np.float32);

    #iteramos una vez por cada "epoc"
    for i in range(0, epocs):
        p = np.random.permutation(len(entrRuedas));
        npentrOperaciones = npentrOperaciones[p];
        npentrRuedas = npentrRuedas[p];

        #ahora partimos los datos en "minibatches" y entrenamos
        for j in range(0, minibatchIteraciones):
            features = npentrRuedas[j*minibatch_size:(j+1)*minibatch_size];
            labels = npentrOperaciones[j*minibatch_size:(j+1)*minibatch_size];
            trainer.train_minibatch({feature: features, label: labels});
        trainer.summarize_training_progress()
        
    
    trainer.save_checkpoint(checkpoint);



    minibatchIteraciones = int(len(testOperaciones) / minibatch_size);
    avg_error = 0;
    for j in range(0, minibatchIteraciones):

        test_features = np.array(testRuedas[j*minibatch_size:(j+1)*minibatch_size]).astype(np.float32);
        test_labels = np.array(testOperaciones[j*minibatch_size:(j+1)*minibatch_size]).astype(np.float32);
        #test_features = np.array( entrRuedas[0:minibatch_size]).astype(np.float32);
        #test_labels = np.array(entrOperaciones[0:minibatch_size]).astype(np.float32);
        avg_error = avg_error + ( trainer.test_minibatch(
            {feature: test_features, label: test_labels}) / minibatchIteraciones)

    return avg_error

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
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

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def ffnet(data, labels):
    input_dim = 800
    num_output_classes = 3
    num_hidden_layers = 2
    hidden_layers_dim = 50

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

    netout = Sequential([For(range(num_hidden_layers), lambda i: Dense(hidden_layers_dim, activation=sigmoid)),
                         Dense(num_output_classes)])(feature)

    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


    features, labels = generate_stock_data(minibatch_size);

    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({feature: 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(
        {feature: test_features, label: test_labels})
    return avg_error

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
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

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def cifar_resnet_distributed(data_path, run_test, num_epochs, communicator=None, save_model_filename=None, load_model_filename=None, 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_reader(os.path.join(data_path, 'train_map.txt'), os.path.join(data_path, 'CIFAR-10_mean.xml'), True,
                                     distributed_communicator = communicator)

    features_si = minibatch_source[feats_stream_name]
    labels_si = minibatch_source[labels_stream_name]

    # Instantiate the resnet classification model, or load from file
    
    if load_model_filename:
        print("Loading model:", load_model_filename)
        classifier_output = persist.load_model(load_model_filename)
        image_input = classifier_output.arguments[0]
    else:
        image_input = input_variable(
            (num_channels, image_height, image_width), features_si.m_element_type)
        classifier_output = create_resnet_model(image_input, num_classes)

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

    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

    mb_size = 128
    num_mb_per_epoch = 100
    
    num_mbs = num_mb_per_epoch * num_epochs

    lr_per_sample = [1/mb_size]*80+[0.1/mb_size]*40+[0.01/mb_size]
    lr_schedule = learning_rate_schedule(lr_per_sample, units = mb_size * num_mb_per_epoch)
    momentum_time_constant = -mb_size/np.log(0.9)

    # create data parallel distributed trainer if needed
    dist_trainer = distributed.data_parallel_distributed_trainer(communicator, False) if communicator else None

    # Instantiate the trainer object to drive the model training
    trainer = Trainer(classifier_output, ce, pe,
                      [momentum_sgd(classifier_output.parameters, lr_schedule, momentum_time_constant, l2_regularization_weight=0.0001)],
                      distributed_trainer = dist_trainer)
    
    # Get minibatches of images to train with and perform model training
    training_progress_output_freq = 100 if communicator else 20

    if debug_output:
        training_progress_output_freq = training_progress_output_freq/4
        
    for i in range(0, num_mbs):
    
        # NOTE: depends on network, the mb_size can be changed dynamically here
        mb = minibatch_source.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)
        
    if save_model_filename:
        print("Saving model:", save_model_filename)
        persist.save_model(classifier_output, save_model_filename)

    if run_test:
        test_minibatch_source = create_reader(os.path.join(data_path, 'test_map.txt'), os.path.join(data_path, 'CIFAR-10_mean.xml'), False)
        features_si = test_minibatch_source[feats_stream_name]
        labels_si = test_minibatch_source[labels_stream_name]

        mb_size = 128
        num_mbs = 100

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

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def conv3d_ucf11(train_reader, test_reader, max_epochs=30):
    # Replace 0 with 1 to get detailed log.
    set_computation_network_trace_level(0)

    # These values must match for both train and test reader.
    image_height       = train_reader.height
    image_width        = train_reader.width
    num_channels       = train_reader.channel_count
    sequence_length    = train_reader.sequence_length
    num_output_classes = train_reader.label_count

    # Input variables denoting the features and label data
    input_var = input_variable((num_channels, sequence_length, image_height, image_width), np.float32)
    label_var = input_variable(num_output_classes, np.float32)

    # Instantiate simple 3D Convolution network inspired by VGG network 
    # and http://vlg.cs.dartmouth.edu/c3d/c3d_video.pdf
    with default_options (activation=relu):
        z = Sequential([
            Convolution3D((3,3,3), 64, pad=True),
            MaxPooling((1,2,2), (1,2,2)),
            For(range(3), lambda i: [
                Convolution3D((3,3,3), [96, 128, 128][i], pad=True),
                Convolution3D((3,3,3), [96, 128, 128][i], pad=True),
                MaxPooling((2,2,2), (2,2,2))
            ]),
            For(range(2), lambda : [
                Dense(1024), 
                Dropout(0.5)
            ]),
            Dense(num_output_classes, activation=None)
        ])(input_var)
    
    # loss and classification error.
    ce = cross_entropy_with_softmax(z, label_var)
    pe = classification_error(z, label_var)

    # training config
    epoch_size     = 1322                  # for now we manually specify epoch size
    minibatch_size = 4

    # Set learning parameters
    lr_per_sample          = [0.01]*10+[0.001]*10+[0.0001]
    lr_schedule            = learning_rate_schedule(lr_per_sample, epoch_size=epoch_size, unit=UnitType.sample)
    momentum_time_constant = 4096
    mm_schedule            = momentum_as_time_constant_schedule([momentum_time_constant], epoch_size=epoch_size)

    # Instantiate the trainer object to drive the model training
    learner = momentum_sgd(z.parameters, lr_schedule, mm_schedule, True)
    progress_printer = ProgressPrinter(tag='Training', num_epochs=max_epochs)
    trainer = Trainer(z, (ce, pe), learner, progress_printer)

    log_number_of_parameters(z) ; print()

    # Get minibatches of images to train with and perform model training
    for epoch in range(max_epochs):       # loop over epochs
        train_reader.reset()

        while train_reader.has_more():
            videos, labels, current_minibatch = train_reader.next_minibatch(minibatch_size)
            trainer.train_minibatch({input_var : videos, label_var : labels})

        trainer.summarize_training_progress()
    
    # Test data for trained model
    epoch_size     = 332
    minibatch_size = 2

    # process minibatches and evaluate the model
    metric_numer    = 0
    metric_denom    = 0
    minibatch_index = 0

    test_reader.reset()    
    while test_reader.has_more():
        videos, labels, current_minibatch = test_reader.next_minibatch(minibatch_size)
        # minibatch data to be trained with
        metric_numer += trainer.test_minibatch({input_var : videos, label_var : labels}) * current_minibatch
        metric_denom += current_minibatch
        # Keep track of the number of samples processed so far.
        minibatch_index += 1

    print("")
    print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
    print("")

    return metric_numer/metric_denom

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def train_and_evaluate(reader_train, reader_test, network_name):

    set_computation_network_trace_level(0)

    # Input variables denoting the features and label data
    input_var = input_variable((num_channels, image_height, image_width))
    label_var = input_variable((num_classes))

    # create model, and configure learning parameters 
    if network_name == 'resnet20': 
        z = create_cifar10_model(input_var, 3, num_classes)
        lr_per_mb = [1.0]*80+[0.1]*40+[0.01]
    elif network_name == 'resnet110': 
        z = create_cifar10_model(input_var, 18, num_classes)
        lr_per_mb = [0.1]*1+[1.0]*80+[0.1]*40+[0.01]
    else: 
        return RuntimeError("Unknown model name!")

    # loss and metric
    ce = cross_entropy_with_softmax(z, label_var)
    pe = classification_error(z, label_var)

    # shared training parameters 
    epoch_size = 50000                    # for now we manually specify epoch size
    minibatch_size = 128
    max_epochs = 160
    momentum_time_constant = -minibatch_size/np.log(0.9)
    l2_reg_weight = 0.0001

    # Set learning parameters
    lr_per_sample = [lr/minibatch_size for lr in lr_per_mb]
    lr_schedule = learning_rate_schedule(lr_per_sample, epoch_size=epoch_size)
    mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)
    
    # trainer object
    learner     = momentum_sgd(z.parameters, lr_schedule, mm_schedule,
                               l2_regularization_weight = l2_reg_weight)
    trainer     = Trainer(z, ce, pe, learner)

    # define mapping from reader streams to network inputs
    input_map = {
        input_var: reader_train.streams.features,
        label_var: reader_train.streams.labels
    }

    log_number_of_parameters(z) ; print()
    progress_printer = ProgressPrinter(tag='Training')

    # perform model training
    for epoch in range(max_epochs):       # loop over epochs
        sample_count = 0
        while sample_count < epoch_size:  # loop over minibatches in the epoch
            data = reader_train.next_minibatch(min(minibatch_size, epoch_size-sample_count), input_map=input_map) # fetch minibatch.
            trainer.train_minibatch(data)                                   # update model with it
            sample_count += data[label_var].num_samples                     # count samples processed so far
            progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
        progress_printer.epoch_summary(with_metric=True)
        persist.save_model(z, os.path.join(model_path, network_name + "_{}.dnn".format(epoch)))
    
    # Evaluation parameters
    epoch_size     = 10000
    minibatch_size = 16

    # process minibatches and evaluate the model
    metric_numer    = 0
    metric_denom    = 0
    sample_count    = 0
    minibatch_index = 0

    while sample_count < epoch_size:
        current_minibatch = min(minibatch_size, epoch_size - sample_count)
        # Fetch next test min batch.
        data = reader_test.next_minibatch(current_minibatch, input_map=input_map)
        # minibatch data to be trained with
        metric_numer += trainer.test_minibatch(data) * current_minibatch
        metric_denom += current_minibatch
        # Keep track of the number of samples processed so far.
        sample_count += data[label_var].num_samples
        minibatch_index += 1

    print("")
    print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
    print("")

    return metric_numer/metric_denom

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]

#.........这里部分代码省略.........
    ce = cross_entropy_with_softmax(z, label_sequence)
    errs = classification_error(z, label_sequence)

    # Instantiate the trainer object to drive the model training
    lr = 0.007
    momentum_time_constant = 1100
    momentum_per_sample = momentums_per_sample(math.exp(-1.0 / momentum_time_constant))
    clipping_threshold_per_sample = 2.3
    gradient_clipping_with_truncation = True

    trainer = Trainer(
        z,
        ce,
        errs,
        [
            momentum_sgd(
                z.parameters(),
                lr,
                momentum_per_sample,
                clipping_threshold_per_sample,
                gradient_clipping_with_truncation,
            )
        ],
    )

    rel_path = r"../../../../Examples/SequenceToSequence/CMUDict/Data/cmudict-0.7b.train-dev-20-21.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_vocab_dim, True, "S0"),
            StreamConfiguration(labels_stream_name, label_vocab_dim, True, "S1"),
        ],
        10000,
    )
    features_si = mb_source[feature_stream_name]
    labels_si = mb_source[labels_stream_name]

    # Get minibatches of sequences to train with and perform model training
    minibatch_size = 72
    training_progress_output_freq = 30
    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 = {raw_input: mb[features_si], raw_labels: mb[labels_si]}
        trainer.train_minibatch(arguments)

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

    rel_path = r"../../../../Examples/SequenceToSequence/CMUDict/Data/cmudict-0.7b.test.ctf"
    path = os.path.join(os.path.dirname(os.path.abspath(__file__)), rel_path)

    test_mb_source = text_format_minibatch_source(
        path,
        [
            StreamConfiguration(feature_stream_name, input_vocab_dim, True, "S0"),
            StreamConfiguration(labels_stream_name, label_vocab_dim, True, "S1"),
        ],
        10000,
        False,
    )
    features_si = test_mb_source[feature_stream_name]
    labels_si = test_mb_source[labels_stream_name]

    # choose this to be big enough for the longest sentence
    train_minibatch_size = 1024

    # Get minibatches of sequences to test and perform testing
    i = 0
    total_error = 0.0
    while True:
        mb = test_mb_source.get_next_minibatch(train_minibatch_size)
        if len(mb) == 0:
            break

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

        total_error += mb_error

        if debug_output:
            print("Minibatch {}, Error {} ".format(i, mb_error))

        i += 1

    # Average of evaluation errors of all test minibatches
    return total_error / i

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def train_and_evaluate(create_train_reader, test_reader, network_name, max_epochs, create_dist_learner, scale_up=False):

    set_computation_network_trace_level(0)

    # Input variables denoting the features and label data
    input_var = input_variable((num_channels, image_height, image_width))
    label_var = input_variable((num_classes))

    # create model, and configure learning parameters 
    if network_name == 'resnet20': 
        z = create_cifar10_model(input_var, 3, num_classes)
        lr_per_mb = [1.0]*80+[0.1]*40+[0.01]
    elif network_name == 'resnet110': 
        z = create_cifar10_model(input_var, 18, num_classes)
        lr_per_mb = [0.1]*1+[1.0]*80+[0.1]*40+[0.01]
    else: 
        return RuntimeError("Unknown model name!")

    # loss and metric
    ce = cross_entropy_with_softmax(z, label_var)
    pe = classification_error(z, label_var)

    # shared training parameters 
    epoch_size = 50000                    # for now we manually specify epoch size
    
    # NOTE: scaling up minibatch_size increases sample throughput. In 8-GPU machine,
    # ResNet110 samples-per-second is ~7x of single GPU, comparing to ~3x without scaling
    # up. However, bigger minimatch size on the same number of samples means less updates, 
    # thus leads to higher training error. This is a trade-off of speed and accuracy
    minibatch_size = 128 * (distributed.Communicator.num_workers() if scale_up else 1)

    momentum_time_constant = -minibatch_size/np.log(0.9)
    l2_reg_weight = 0.0001

    # Set learning parameters
    lr_per_sample = [lr/minibatch_size for lr in lr_per_mb]
    lr_schedule = learning_rate_schedule(lr_per_sample, epoch_size=epoch_size, unit=UnitType.sample)
    mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)
    
    # trainer object
    learner     = create_dist_learner(momentum_sgd(z.parameters, lr_schedule, mm_schedule,
                                                   l2_regularization_weight = l2_reg_weight))
    trainer     = Trainer(z, ce, pe, learner)

    total_number_of_samples = max_epochs * epoch_size
    train_reader=create_train_reader(total_number_of_samples)

    # define mapping from reader streams to network inputs
    input_map = {
        input_var: train_reader.streams.features,
        label_var: train_reader.streams.labels
    }

    log_number_of_parameters(z) ; print()
    progress_printer = ProgressPrinter(tag='Training')

    # perform model training
    current_epoch=0
    updated=True
    while updated:
        data=train_reader.next_minibatch(minibatch_size, input_map=input_map) # fetch minibatch.
        updated=trainer.train_minibatch(data)                                 # update model with it
        progress_printer.update_with_trainer(trainer, with_metric=True)       # log progress
        epoch_index = int(trainer.total_number_of_samples_seen/epoch_size)
        if current_epoch != epoch_index:                                      # new epoch reached
            progress_printer.epoch_summary(with_metric=True)
            current_epoch=epoch_index
            trainer.save_checkpoint(os.path.join(model_path, network_name + "_{}.dnn".format(current_epoch)))

    # Evaluation parameters
    epoch_size     = 10000
    minibatch_size = 16

    # process minibatches and evaluate the model
    metric_numer    = 0
    metric_denom    = 0
    sample_count    = 0
    minibatch_index = 0

    while True:
        data = test_reader.next_minibatch(minibatch_size, input_map=input_map)
        if not data: break;

        local_mb_samples=data[label_var].num_samples
        metric_numer += trainer.test_minibatch(data) * local_mb_samples
        metric_denom += local_mb_samples
        minibatch_index += 1

    print("")
    print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
    print("")

    return metric_numer/metric_denom

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def train_and_evaluate(reader_train, reader_test, network_name, epoch_size, max_epochs, profiler_dir=None,
                       model_dir=None, log_dir=None, tensorboard_logdir=None, gen_heartbeat=False):

    set_computation_network_trace_level(0)

    # Input variables denoting the features and label data
    input_var = C.input_variable((num_channels, image_height, image_width), name='features')
    label_var = C.input_variable((num_classes))

    # create model, and configure learning parameters
    if network_name == 'resnet20':
        z = create_cifar10_model(input_var, 3, num_classes)
        lr_per_mb = [1.0]*80+[0.1]*40+[0.01]
    elif network_name == 'resnet110':
        z = create_cifar10_model(input_var, 18, num_classes)
        lr_per_mb = [0.1]*1+[1.0]*80+[0.1]*40+[0.01]
    else:
        raise RuntimeError("Unknown model name!")

    # loss and metric
    ce = cross_entropy_with_softmax(z, label_var)
    pe = classification_error(z, label_var)

    # shared training parameters
    minibatch_size = 128
    momentum_time_constant = -minibatch_size/np.log(0.9)
    l2_reg_weight = 0.0001

    # Set learning parameters
    lr_per_sample = [lr/minibatch_size for lr in lr_per_mb]
    lr_schedule = learning_rate_schedule(lr_per_sample, epoch_size=epoch_size, unit=UnitType.sample)
    mm_schedule = momentum_as_time_constant_schedule(momentum_time_constant)

    # progress writers
    progress_writers = [ProgressPrinter(tag='Training', log_to_file=log_dir, num_epochs=max_epochs, gen_heartbeat=gen_heartbeat)]
    tensorboard_writer = None
    if tensorboard_logdir is not None:
        tensorboard_writer = TensorBoardProgressWriter(freq=10, log_dir=tensorboard_logdir, model=z)
        progress_writers.append(tensorboard_writer)

    # trainer object
    learner = momentum_sgd(z.parameters, lr_schedule, mm_schedule,
                           l2_regularization_weight = l2_reg_weight)
    trainer = Trainer(z, (ce, pe), learner, progress_writers)

    # define mapping from reader streams to network inputs
    input_map = {
        input_var: reader_train.streams.features,
        label_var: reader_train.streams.labels
    }

    log_number_of_parameters(z) ; print()

    # perform model training
    if profiler_dir:
        start_profiler(profiler_dir, True)

    for epoch in range(max_epochs):       # loop over epochs
        sample_count = 0
        while sample_count < epoch_size:  # loop over minibatches in the epoch
            data = reader_train.next_minibatch(min(minibatch_size, epoch_size-sample_count), input_map=input_map) # fetch minibatch.
            trainer.train_minibatch(data)                                   # update model with it
            sample_count += trainer.previous_minibatch_sample_count         # count samples processed so far

        trainer.summarize_training_progress()

        # Log mean of each parameter tensor, so that we can confirm that the parameters change indeed.
        if tensorboard_writer:
            for parameter in z.parameters:
                tensorboard_writer.write_value(parameter.uid + "/mean", reduce_mean(parameter).eval(), epoch)

        if model_dir:
            z.save(os.path.join(model_dir, network_name + "_{}.dnn".format(epoch)))
        enable_profiler() # begin to collect profiler data after first epoch

    if profiler_dir:
        stop_profiler()

    # Evaluation parameters
    test_epoch_size     = 10000
    minibatch_size = 16

    # process minibatches and evaluate the model
    metric_numer    = 0
    metric_denom    = 0
    sample_count    = 0

    while sample_count < test_epoch_size:
        current_minibatch = min(minibatch_size, test_epoch_size - sample_count)
        # Fetch next test min batch.
        data = reader_test.next_minibatch(current_minibatch, input_map=input_map)
        # minibatch data to be trained with
        metric_numer += trainer.test_minibatch(data) * current_minibatch
        metric_denom += current_minibatch
        # Keep track of the number of samples processed so far.
        sample_count += data[label_var].num_samples

    print("")
    trainer.summarize_test_progress()
    print("")
#.........这里部分代码省略.........

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
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

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
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

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
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

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
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

#.........这里部分代码省略.........

# 需要导入模块: from cntk import Trainer [as 别名]
# 或者: from cntk.Trainer import test_minibatch [as 别名]
def convnet_cifar10_dataaug(reader_train, reader_test, max_epochs = 80):
    set_computation_network_trace_level(0)

    # Input variables denoting the features and label data
    input_var = input_variable((num_channels, image_height, image_width))
    label_var = input_variable((num_classes))

    # apply model to input
    scaled_input = element_times(constant(0.00390625), input_var)
    with default_options (activation=relu, pad=True): 
        z = Sequential([
            LayerStack(2, lambda : [
                Convolution((3,3), 64), 
                Convolution((3,3), 64), 
                MaxPooling((3,3), (2,2))
            ]), 
            LayerStack(2, lambda i: [
                Dense([256,128][i]), 
                Dropout(0.5)
            ]), 
            Dense(num_classes, activation=None)
        ])(scaled_input)

    # loss and metric
    ce = cross_entropy_with_softmax(z, label_var)
    pe = classification_error(z, label_var)

    # training config
    epoch_size = 50000                    # for now we manually specify epoch size
    minibatch_size = 64

    # Set learning parameters
    lr_per_sample          = [0.0015625]*20+[0.00046875]*20+[0.00015625]*20+[0.000046875]*10+[0.000015625]
    lr_schedule            = learning_rate_schedule(lr_per_sample, unit=UnitType.sample, epoch_size=epoch_size)
    mm_time_constant       = [0]*20+[600]*20+[1200]
    mm_schedule            = momentum_as_time_constant_schedule(mm_time_constant, epoch_size=epoch_size)
    l2_reg_weight          = 0.002
    
    # trainer object
    learner     = momentum_sgd(z.parameters, lr_schedule, mm_schedule,
                               l2_regularization_weight = l2_reg_weight)
    trainer     = Trainer(z, ce, pe, learner)

    # define mapping from reader streams to network inputs
    input_map = {
        input_var: reader_train.streams.features,
        label_var: reader_train.streams.labels
    }

    log_number_of_parameters(z) ; print()
    progress_printer = ProgressPrinter(tag='Training')

    # perform model training
    for epoch in range(max_epochs):       # loop over epochs
        sample_count = 0
        while sample_count < epoch_size:  # loop over minibatches in the epoch
            data = reader_train.next_minibatch(min(minibatch_size, epoch_size-sample_count), input_map=input_map) # fetch minibatch.
            trainer.train_minibatch(data)                                   # update model with it
            sample_count += trainer.previous_minibatch_sample_count         # count samples processed so far
            progress_printer.update_with_trainer(trainer, with_metric=True) # log progress
        progress_printer.epoch_summary(with_metric=True)
        persist.save_model(z, os.path.join(model_path, "ConvNet_CIFAR10_DataAug_{}.dnn".format(epoch)))
    
    ### Evaluation action
    epoch_size     = 10000
    minibatch_size = 16

    # process minibatches and evaluate the model
    metric_numer    = 0
    metric_denom    = 0
    sample_count    = 0
    minibatch_index = 0

    while sample_count < epoch_size:
        current_minibatch = min(minibatch_size, epoch_size - sample_count)
        # Fetch next test min batch.
        data = reader_test.next_minibatch(current_minibatch, input_map=input_map)
        # minibatch data to be trained with
        metric_numer += trainer.test_minibatch(data) * current_minibatch
        metric_denom += current_minibatch
        # Keep track of the number of samples processed so far.
        sample_count += data[label_var].num_samples
        minibatch_index += 1

    print("")
    print("Final Results: Minibatch[1-{}]: errs = {:0.2f}% * {}".format(minibatch_index+1, (metric_numer*100.0)/metric_denom, metric_denom))
    print("")

    return metric_numer/metric_denom