Python keras_resnet.models方法代码示例

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def download_imagenet(self):
        """ Downloads ImageNet weights and returns path to weights file.
        """
        resnet_filename = 'ResNet-{}-model.keras.h5'
        resnet_resource = 'https://github.com/fizyr/keras-models/releases/download/v0.0.1/{}'.format(resnet_filename)
        depth = int(self.backbone.replace('resnet', ''))

        filename = resnet_filename.format(depth)
        resource = resnet_resource.format(depth)
        if depth == 50:
            checksum = '3e9f4e4f77bbe2c9bec13b53ee1c2319'
        elif depth == 101:
            checksum = '05dc86924389e5b401a9ea0348a3213c'
        elif depth == 152:
            checksum = '6ee11ef2b135592f8031058820bb9e71'

        return get_file(
            filename,
            resource,
            cache_subdir='models',
            md5_hash=checksum
        ) 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def resnet_maskrcnn(num_classes, backbone='resnet50', inputs=None, modifier=None, mask_dtype=keras.backend.floatx(), **kwargs):
    # choose default input
    if inputs is None:
        inputs = keras.layers.Input(shape=(None, None, 3), name='image')

    # create the resnet backbone
    if backbone == 'resnet50':
        resnet = keras_resnet.models.ResNet50(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet101':
        resnet = keras_resnet.models.ResNet101(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet152':
        resnet = keras_resnet.models.ResNet152(inputs, include_top=False, freeze_bn=True)

    # invoke modifier if given
    if modifier:
        resnet = modifier(resnet)

    # create the full model
    model = retinanet.retinanet_mask(inputs=inputs, num_classes=num_classes, backbone_layers=resnet.outputs[1:], mask_dtype=mask_dtype, **kwargs)

    return model 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def download_imagenet(backbone):
    validate_backbone(backbone)

    backbone = int(backbone.replace('resnet', ''))

    filename = resnet_filename.format(backbone)
    resource = resnet_resource.format(backbone)
    if backbone == 50:
        checksum = '3e9f4e4f77bbe2c9bec13b53ee1c2319'
    elif backbone == 101:
        checksum = '05dc86924389e5b401a9ea0348a3213c'
    elif backbone == 152:
        checksum = '6ee11ef2b135592f8031058820bb9e71'

    return keras.applications.imagenet_utils.get_file(
        filename,
        resource,
        cache_subdir='models',
        md5_hash=checksum
    ) 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def resnet_retinanet(num_classes, backbone='resnet50', inputs=None, modifier=None, **kwargs):
    validate_backbone(backbone)

    # choose default input
    if inputs is None:
        inputs = keras.layers.Input(shape=(None, None, 3))

    if backbone == 'resnet50':
        resnet = keras_resnet.models.ResNet50(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet101':
        resnet = keras_resnet.models.ResNet101(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet152':
        resnet = keras_resnet.models.ResNet152(inputs, include_top=False, freeze_bn=True)

    # invoke modifier if given
    if modifier:
        resnet = modifier(resnet)

    # create the full model
    model = retinanet.retinanet_bbox(inputs=inputs, num_classes=num_classes, backbone=resnet, **kwargs)

    return model 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def resnet_retinanet(num_classes, backbone='resnet50', inputs=None, modifier=None, **kwargs):
    """ Constructs a retinanet model using a resnet backbone.

    Args
        num_classes: Number of classes to predict.
        backbone: Which backbone to use (one of ('resnet50', 'resnet101', 'resnet152')).
        inputs: The inputs to the network (defaults to a Tensor of shape (None, None, 3)).
        modifier: A function handler which can modify the backbone before using it in retinanet (this can be used to freeze backbone layers for example).

    Returns
        RetinaNet model with a ResNet backbone.
    """
    # choose default input
    if inputs is None:
        if keras.backend.image_data_format() == 'channels_first':
            inputs = keras.layers.Input(shape=(3, None, None))
        else:
            inputs = keras.layers.Input(shape=(None, None, 3))

    # create the resnet backbone
    if backbone == 'resnet50':
        resnet = keras_resnet.models.ResNet50(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet101':
        resnet = keras_resnet.models.ResNet101(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet152':
        resnet = keras_resnet.models.ResNet152(inputs, include_top=False, freeze_bn=True)
    else:
        raise ValueError('Backbone (\'{}\') is invalid.'.format(backbone))

    # invoke modifier if given
    if modifier:
        resnet = modifier(resnet)

    # create the full model
    return retinanet.retinanet(inputs=inputs, num_classes=num_classes, backbone_layers=resnet.outputs[1:], **kwargs) 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def get_custom_objects(architecture):
    """ Provides a dictionary with custom objects required for loading a certain model architecture using `keras.models.load_model`. """
    
    if architecture in ('resnet-32', 'resnet-110', 'resnet-110-fc', 'resnet-110-wfc', 'pyramidnet-272-200', 'pyramidnet-110-270'):
        return { 'ChannelPadding' : cifar_resnet.ChannelPadding }
    else:
        return {} 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def resnet_retinanet(num_classes, backbone='resnet50', inputs=None, modifier=None, cfg=None, **kwargs):
    """ Constructs a retinanet model using a resnet backbone.

    Args
        num_classes: Number of classes to predict.
        backbone: Which backbone to use (one of ('resnet50', 'resnet101', 'resnet152')).
        inputs: The inputs to the network (defaults to a Tensor of shape (None, None, 3)).
        modifier: A function handler which can modify the backbone before using it in retinanet (this can be used to freeze backbone layers for example).

    Returns
        RetinaNet model with a ResNet backbone.
    """
    # choose default input
    if inputs is None:
        if keras.backend.image_data_format() == 'channels_first':
            inputs = keras.layers.Input(shape=(3, None, None))
        else:
            inputs = keras.layers.Input(shape=(None, None, 3))
    elif isinstance(inputs, tuple):
        inputs = keras.layers.Input(inputs)
        
    # create the resnet backbone
    if backbone == 'resnet50':
        resnet = keras_resnet.models.ResNet50(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet101':
        resnet = keras_resnet.models.ResNet101(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet152':
        resnet = keras_resnet.models.ResNet152(inputs, include_top=False, freeze_bn=True)
    else:
        raise ValueError('Backbone (\'{}\') is invalid.'.format(backbone))

    # invoke modifier if given
    if modifier:
        resnet = modifier(resnet)

    # create the full model
    return retinanet.retinanet(inputs=inputs, num_classes=num_classes, backbone_layers=resnet.outputs[1:], **kwargs) 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def resnet_retinanet(num_classes, backbone='resnet50', inputs=None, modifier=None, **kwargs):
    """ Constructs a retinanet model using a resnet backbone.

    Args
        num_classes: Number of classes to predict.
        backbone: Which backbone to use (one of ('resnet50', 'resnet101', 'resnet152')).
        inputs: The inputs to the network (defaults to a Tensor of shape (None, None, 3)).
        modifier: A function handler which can modify the backbone before using it in retinanet (this can be used to
        freeze backbone layers for example).

    Returns
        RetinaNet model with a ResNet backbone.
    """
    # choose default input
    if inputs is None:
        inputs = keras.layers.Input(shape=(None, None, 3))

    # create the resnet backbone
    if backbone == 'resnet50':
        resnet = keras_resnet.models.ResNet50(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet101':
        resnet = keras_resnet.models.ResNet101(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet152':
        resnet = keras_resnet.models.ResNet152(inputs, include_top=False, freeze_bn=True)
    else:
        raise ValueError('Backbone (\'{}\') is invalid.'.format(backbone))

    # invoke modifier if given
    if modifier:
        resnet = modifier(resnet)

    # create the full model
    return retinanet.retinanet(inputs=inputs, num_classes=num_classes, backbone_layers=resnet.outputs[1:], **kwargs) 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def resnet_m2det(num_classes, backbone='resnet50', inputs=None, modifier=None, **kwargs):
    """ Constructs a m2det model using a resnet backbone.

    Args
        num_classes: Number of classes to predict.
        backbone: Which backbone to use (one of ('resnet50', 'resnet101', 'resnet152')).
        inputs: The inputs to the network (defaults to a Tensor of shape (640, 640, 3)).
        modifier: A function handler which can modify the backbone before using it in m2det (this can be used to freeze backbone layers for example).

    Returns
        m2det model with a ResNet backbone.
    """
    # choose default input
    if inputs is None:
        if keras.backend.image_data_format() == 'channels_first':
            inputs = keras.layers.Input(shape=(3, 640, 640))
        else:
            inputs = keras.layers.Input(shape=(640, 640, 3))

    # create the resnet backbone
    if backbone == 'resnet50':
        resnet = keras_resnet.models.ResNet50(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet101':
        resnet = keras_resnet.models.ResNet101(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet152':
        resnet = keras_resnet.models.ResNet152(inputs, include_top=False, freeze_bn=True)
    else:
        raise ValueError('Backbone (\'{}\') is invalid.'.format(backbone))

    # invoke modifier if given
    if modifier:
        resnet = modifier(resnet)

    # create the full model
    return m2det.m2det(inputs=inputs, num_classes=num_classes, backbone_layers=resnet.outputs[1:], **kwargs) 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def create_models(backbone_retinanet, backbone, num_classes, weights, multi_gpu=0, freeze_backbone=False):
    modifier = freeze_model if freeze_backbone else None

    # Keras recommends initialising a multi-gpu model on the CPU to ease weight sharing, and to prevent OOM errors.
    # optionally wrap in a parallel model
    if multi_gpu > 1:
        with tf.device('/cpu:0'):
            model = model_with_weights(backbone_retinanet(num_classes, backbone=backbone, nms=False, modifier=modifier), weights=weights, skip_mismatch=True)
        training_model = multi_gpu_model(model, gpus=multi_gpu)

        # append NMS for prediction only
        classification   = model.outputs[1]
        detections       = model.outputs[2]
        boxes            = keras.layers.Lambda(lambda x: x[:, :, :4])(detections)
        detections       = layers.NonMaximumSuppression(name='nms')([boxes, classification, detections])
        prediction_model = keras.models.Model(inputs=model.inputs, outputs=model.outputs[:2] + [detections])
    else:
        model            = model_with_weights(backbone_retinanet(num_classes, backbone=backbone, nms=True, modifier=modifier), weights=weights, skip_mismatch=True)
        training_model   = model
        prediction_model = model

    # compile model
    training_model.compile(
        loss={
            'regression'    : losses.smooth_l1(),
            'classification': losses.focal()
        },
        optimizer=keras.optimizers.adam(lr=1e-5, clipnorm=0.001)
    )

    return model, training_model, prediction_model 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def resnet_retinanet(num_classes, backbone='resnet50', inputs=None, modifier=None, **kwargs):
    """ Constructs a retinanet model using a resnet backbone.

    Args
        num_classes: Number of classes to predict.
        backbone: Which backbone to use (one of ('resnet50', 'resnet101', 'resnet152')).
        inputs: The inputs to the network (defaults to a Tensor of shape (None, None, 3)).
        modifier: A function handler which can modify the backbone before using it in retinanet (this can be used to freeze backbone layers for example).

    Returns
        RetinaNet model with a ResNet backbone.
    """
    # choose default input
    if inputs is None:
        if keras.backend.image_data_format() == 'channels_first':
            inputs = keras.layers.Input(shape=(3, None, None))
        else:
            inputs = keras.layers.Input(shape=(None, None, 3))

    # create the resnet backbone
    if backbone == 'resnet50':
        resnet = keras_resnet.models.ResNet50(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet101':
        resnet = keras_resnet.models.ResNet101(inputs, include_top=False, freeze_bn=True)
    elif backbone == 'resnet152':
        resnet = keras_resnet.models.ResNet152(inputs, include_top=False, freeze_bn=True)
    else:
        raise ValueError('Backbone (\'{}\') is invalid.'.format(backbone))

    # invoke modifier if given
    if modifier:
        resnet = modifier(resnet)

    # create the full model
    # resnet.outputs contains 4 layers
    backbone_layers = {
        'C2': resnet.outputs[0],
        'C3': resnet.outputs[1],
        'C4': resnet.outputs[2],
        'C5': resnet.outputs[3]
    }

    return retinanet.retinanet(inputs=inputs, num_classes=num_classes, backbone_layers=backbone_layers, **kwargs) 

# 需要导入模块: import keras_resnet [as 别名]
# 或者: from keras_resnet import models [as 别名]
def parse_args(args):
    parser     = argparse.ArgumentParser(description='Simple training script for training a RetinaNet network.')
    subparsers = parser.add_subparsers(help='Arguments for specific dataset types.', dest='dataset_type')
    subparsers.required = True

    coco_parser = subparsers.add_parser('coco')
    coco_parser.add_argument('coco_path', help='Path to dataset directory (ie. /tmp/COCO).')

    pascal_parser = subparsers.add_parser('pascal')
    pascal_parser.add_argument('pascal_path', help='Path to dataset directory (ie. /tmp/VOCdevkit).')

    kitti_parser = subparsers.add_parser('kitti')
    kitti_parser.add_argument('kitti_path', help='Path to dataset directory (ie. /tmp/kitti).')

    def csv_list(string):
        return string.split(',')

    oid_parser = subparsers.add_parser('oid')
    oid_parser.add_argument('main_dir', help='Path to dataset directory.')
    oid_parser.add_argument('--version',  help='The current dataset version is V3.', default='2017_11')
    oid_parser.add_argument('--labels-filter',  help='A list of labels to filter.', type=csv_list, default=None)
    oid_parser.add_argument('--annotation-cache-dir', help='Path to store annotation cache.', default='.')
    oid_parser.add_argument('--fixed-labels', help='Use the exact specified labels.', default=False)

    csv_parser = subparsers.add_parser('csv')
    csv_parser.add_argument('annotations', help='Path to CSV file containing annotations for training.')
    csv_parser.add_argument('classes', help='Path to a CSV file containing class label mapping.')
    csv_parser.add_argument('--val-annotations', help='Path to CSV file containing annotations for validation (optional).')

    group = parser.add_mutually_exclusive_group()
    group.add_argument('--snapshot',          help='Resume training from a snapshot.')
    group.add_argument('--imagenet-weights',  help='Initialize the model with pretrained imagenet weights. This is the default behaviour.', action='store_const', const=True, default=True)
    group.add_argument('--weights',           help='Initialize the model with weights from a file.')
    group.add_argument('--no-weights',        help='Don\'t initialize the model with any weights.', dest='imagenet_weights', action='store_const', const=False)

    parser.add_argument('--backbone',        help='Backbone model used by retinanet.', default='resnet50', type=str)
    parser.add_argument('--batch-size',      help='Size of the batches.', default=1, type=int)
    parser.add_argument('--gpu',             help='Id of the GPU to use (as reported by nvidia-smi).')
    parser.add_argument('--multi-gpu',       help='Number of GPUs to use for parallel processing.', type=int, default=0)
    parser.add_argument('--multi-gpu-force', help='Extra flag needed to enable (experimental) multi-gpu support.', action='store_true')
    parser.add_argument('--epochs',          help='Number of epochs to train.', type=int, default=30)
    parser.add_argument('--steps',           help='Number of steps per epoch.', type=int, default=10000)
    parser.add_argument('--snapshot-path',   help='Path to store snapshots of models during training (defaults to \'./snapshots\')', default='./snapshots')
    parser.add_argument('--tensorboard-dir', help='Log directory for Tensorboard output', default='./logs')
    parser.add_argument('--no-snapshots',    help='Disable saving snapshots.', dest='snapshots', action='store_false')
    parser.add_argument('--no-evaluation',   help='Disable per epoch evaluation.', dest='evaluation', action='store_false')
    parser.add_argument('--freeze-backbone', help='Freeze training of backbone layers.', action='store_true')

    return check_args(parser.parse_args(args))