Python tensorpack.dataflow.FakeData() Examples

The following are 5 code examples of tensorpack.dataflow.FakeData(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module tensorpack.dataflow , or try the search function .
Example #1
Source File: imagenet.py    From LQ-Nets with MIT License 5 votes vote down vote up 
def get_config(model, fake=False, data_aug=True):
    nr_tower = max(get_nr_gpu(), 1)
    batch = TOTAL_BATCH_SIZE // nr_tower

    if fake:
        logger.info("For benchmark, batch size is fixed to 64 per tower.")
        dataset_train = FakeData(
            [[64, 224, 224, 3], [64]], 1000, random=False, dtype='uint8')
        callbacks = []
    else:
        logger.info("Running on {} towers. Batch size per tower: {}".format(nr_tower, batch))
        dataset_train = get_data('train', batch, data_aug)
        dataset_val = get_data('val', batch, data_aug)
        callbacks = [
            ModelSaver(),
        ]
        if data_aug:
            callbacks.append(ScheduledHyperParamSetter('learning_rate',
                                                       [(30, 1e-2), (60, 1e-3), (85, 1e-4), (95, 1e-5), (105, 1e-6)]))
        callbacks.append(HumanHyperParamSetter('learning_rate'))
        infs = [ClassificationError('wrong-top1', 'val-error-top1'),
                ClassificationError('wrong-top5', 'val-error-top5')]
        if nr_tower == 1:
            # single-GPU inference with queue prefetch
            callbacks.append(InferenceRunner(QueueInput(dataset_val), infs))
        else:
            # multi-GPU inference (with mandatory queue prefetch)
            callbacks.append(DataParallelInferenceRunner(
                dataset_val, infs, list(range(nr_tower))))

    return AutoResumeTrainConfig(
        model=model,
        dataflow=dataset_train,
        callbacks=callbacks,
        steps_per_epoch=5000 if TOTAL_BATCH_SIZE == 256 else 10000,
        max_epoch=110 if data_aug else 64,
        nr_tower=nr_tower
    )
Example #2
Source File: imagenet-resnet.py    From webvision-2.0-benchmarks with Apache License 2.0 4 votes vote down vote up 
def get_config(model, fake=False):
    nr_tower = max(get_nr_gpu(), 1)
    assert args.batch % nr_tower == 0
    batch = args.batch // nr_tower

    if fake:
        logger.info("For benchmark, batch size is fixed to 64 per tower.")
        dataset_train = FakeData(
            [[64, 224, 224, 3], [64]], 1000, random=False, dtype='uint8')
        callbacks = []
    else:
        logger.info("Running on {} towers. Batch size per tower: {}".format(nr_tower, batch))
        dataset_train = get_data('train', batch)
        dataset_val = get_data('val', batch)

        BASE_LR = 0.1 * (args.batch / 256.0)
        callbacks = [
            ModelSaver(),
            ScheduledHyperParamSetter(
                'learning_rate', [(0, BASE_LR), (30, BASE_LR * 1e-1), (60, BASE_LR * 1e-2),
                                  (90, BASE_LR * 1e-3)]),
        ]
        if BASE_LR > 0.1:
            callbacks.append(
                ScheduledHyperParamSetter(
                    'learning_rate', [(0, 0.1), (3, BASE_LR)], interp='linear'))

        infs = [ClassificationError('wrong-top1', 'val-error-top1'),
                ClassificationError('wrong-top5', 'val-error-top5')]
        if nr_tower == 1:
            # single-GPU inference with queue prefetch
            callbacks.append(InferenceRunner(QueueInput(dataset_val), infs))
        else:
            # multi-GPU inference (with mandatory queue prefetch)
            callbacks.append(DataParallelInferenceRunner(
                dataset_val, infs, list(range(nr_tower))))

    return TrainConfig(
        model=model,
        dataflow=dataset_train,
        callbacks=callbacks,
        steps_per_epoch=100 if args.fake else 1280000 // args.batch,
        max_epoch=110,
    )
Example #3
Source File: imagenet-resnet-gn.py    From GroupNorm-reproduce with Apache License 2.0 4 votes vote down vote up 
def get_config(model, fake=False):
    nr_tower = max(get_num_gpu(), 1)
    assert args.batch % nr_tower == 0
    batch = args.batch // nr_tower

    if fake:
        logger.info("For benchmark, batch size is fixed to 64 per tower.")
        dataset_train = FakeData(
            [[64, 224, 224, 3], [64]], 1000, random=False, dtype='uint8')
        callbacks = []
        steps_per_epoch = 100
    else:
        logger.info("Running on {} towers. Batch size per tower: {}".format(nr_tower, batch))

        dataset_train = get_imagenet_dataflow(args.data, 'train', batch)
        dataset_val = get_imagenet_dataflow(args.data, 'val', min(64, batch))
        steps_per_epoch = 1281167 // args.batch

        BASE_LR = 0.1 * args.batch / 256.0
        logger.info("BASELR: {}".format(BASE_LR))
        callbacks = [
            ModelSaver(),
            EstimatedTimeLeft(),
            GPUUtilizationTracker(),
            ScheduledHyperParamSetter(
                'learning_rate', [(0, BASE_LR), (30, BASE_LR * 1e-1), (60, BASE_LR * 1e-2),
                                  (90, BASE_LR * 1e-3)]),
        ]
        if BASE_LR > 0.1:
            callbacks.append(
                ScheduledHyperParamSetter(
                    'learning_rate', [(0, 0.1), (5 * steps_per_epoch, BASE_LR)],
                    interp='linear', step_based=True))

        infs = [ClassificationError('wrong-top1', 'val-error-top1'),
                ClassificationError('wrong-top5', 'val-error-top5')]
        if nr_tower == 1:
            # single-GPU inference with queue prefetch
            callbacks.append(InferenceRunner(QueueInput(dataset_val), infs))
        else:
            # multi-GPU inference (with mandatory queue prefetch)
            callbacks.append(DataParallelInferenceRunner(
                dataset_val, infs, list(range(nr_tower))))

    return TrainConfig(
        model=model,
        dataflow=dataset_train,
        callbacks=callbacks,
        steps_per_epoch=steps_per_epoch,
        max_epoch=100,
    )
Example #4
Source File: adanet-resnet.py    From adanet with MIT License 4 votes vote down vote up 
def get_config(model, fake=False):
    nr_tower = max(get_num_gpu(), 1)
    assert args.batch % nr_tower == 0
    batch = args.batch // nr_tower

    logger.info("Running on {} towers. Batch size per tower: {}".format(nr_tower, batch))
    if batch < 32 or batch > 64:
        logger.warn("Batch size per tower not in [32, 64]. This probably will lead to worse accuracy than reported.")
    if fake:
        data = QueueInput(FakeData(
            [[batch, 224, 224, 3], [batch],[batch, 224, 224, 3], [batch]], 1000, random=False, dtype='uint8'))
        callbacks = []
    else:
        data = QueueInput(get_data('train', batch))

        START_LR = 0.1
        BASE_LR = START_LR * (args.batch / 256.0)
        callbacks = [
            ModelSaver(),
            EstimatedTimeLeft(),
            ScheduledHyperParamSetter(
                'learning_rate', [
                    (0, min(START_LR, BASE_LR)), (30, BASE_LR * 1e-1), (45, BASE_LR * 1e-2),
                    (55, BASE_LR * 1e-3)]),
        ]
        if BASE_LR > START_LR:
            callbacks.append(
                ScheduledHyperParamSetter(
                    'learning_rate', [(0, START_LR), (5, BASE_LR)], interp='linear'))

        infs = [ClassificationError('wrong-top1', 'val-error-top1'),
                ClassificationError('wrong-top5', 'val-error-top5')]
        dataset_val = get_data('val', batch)
        if nr_tower == 1:
            # single-GPU inference with queue prefetch
            callbacks.append(InferenceRunner(QueueInput(dataset_val), infs))
        else:
            # multi-GPU inference (with mandatory queue prefetch)
            callbacks.append(DataParallelInferenceRunner(
                dataset_val, infs, list(range(nr_tower))))

    return AutoResumeTrainConfig(
        model=model,
        data=data,
        callbacks=callbacks,
        steps_per_epoch=100 if args.fake else 1280000 // args.batch,
        max_epoch=60,
    )
Example #5
Source File: imagenet-resnet.py    From tensorpack with Apache License 2.0 4 votes vote down vote up 
def get_config(model):
    nr_tower = max(get_num_gpu(), 1)
    assert args.batch % nr_tower == 0
    batch = args.batch // nr_tower

    logger.info("Running on {} towers. Batch size per tower: {}".format(nr_tower, batch))
    if batch < 32 or batch > 64:
        logger.warn("Batch size per tower not in [32, 64]. This probably will lead to worse accuracy than reported.")
    if args.fake:
        data = QueueInput(FakeData(
            [[batch, 224, 224, 3], [batch]], 1000, random=False, dtype='uint8'))
        callbacks = []
    else:
        if args.symbolic:
            data = TFDatasetInput(get_imagenet_tfdata(args.data, 'train', batch))
        else:
            data = QueueInput(get_imagenet_dataflow(args.data, 'train', batch))

        START_LR = 0.1
        BASE_LR = START_LR * (args.batch / 256.0)
        callbacks = [
            ModelSaver(),
            EstimatedTimeLeft(),
            ScheduledHyperParamSetter(
                'learning_rate', [
                    (0, min(START_LR, BASE_LR)), (30, BASE_LR * 1e-1), (60, BASE_LR * 1e-2),
                    (90, BASE_LR * 1e-3), (100, BASE_LR * 1e-4)]),
        ]
        if BASE_LR > START_LR:
            callbacks.append(
                ScheduledHyperParamSetter(
                    'learning_rate', [(0, START_LR), (5, BASE_LR)], interp='linear'))

        infs = [ClassificationError('wrong-top1', 'val-error-top1'),
                ClassificationError('wrong-top5', 'val-error-top5')]
        dataset_val = get_imagenet_dataflow(args.data, 'val', batch)
        if nr_tower == 1:
            # single-GPU inference with queue prefetch
            callbacks.append(InferenceRunner(QueueInput(dataset_val), infs))
        else:
            # multi-GPU inference (with mandatory queue prefetch)
            callbacks.append(DataParallelInferenceRunner(
                dataset_val, infs, list(range(nr_tower))))

    if get_num_gpu() > 0:
        callbacks.append(GPUUtilizationTracker())

    return TrainConfig(
        model=model,
        data=data,
        callbacks=callbacks,
        steps_per_epoch=100 if args.fake else 1281167 // args.batch,
        max_epoch=105,
    )