AttributeError: модуль 'resnet' не имеет атрибута 'ResnetBuilder' - PullRequest
Новая
       17

AttributeError: модуль 'resnet' не имеет атрибута 'ResnetBuilder'

1 голос
/ 09 июля 2019

Привет, я попытался запустить следующую программу и неожиданно получаю ошибку ниже: 

AttributeError: module 'resnet' has no attribute 'ResnetBuilder'

во время работы ResNet из GitHub , но я не понимаю, почему это происходит в следующей части: 

 model = resnet.ResnetBuilder.build_resnet_18((img_channels, img_rows, img_cols), nb_classes)
 model.compile(loss='categorical_crossentropy',
                 optimizer='adam',

учитывая ResnetBuilder это уже определено здесь: 

class ResnetBuilder(object):
    @staticmethod
    def build(input_shape, num_outputs, block_fn, repetitions):
        """Builds a custom ResNet like architecture.
        Args:
            input_shape: The input shape in the form (nb_channels, nb_rows, nb_cols)
            num_outputs: The number of outputs at final softmax layer
            block_fn: The block function to use. This is either `basic_block` or `bottleneck`.
                The original paper used basic_block for layers < 50
            repetitions: Number of repetitions of various block units.
                At each block unit, the number of filters are doubled and the input size is halved
        Returns:
            The keras `Model`.
        """
        _handle_dim_ordering()
        if len(input_shape) != 3:
            raise Exception("Input shape should be a tuple (nb_channels, nb_rows, nb_cols)")

        # Permute dimension order if necessary
        if K.image_dim_ordering() == 'tf':
            input_shape = (input_shape[1], input_shape[2], input_shape[0])

        # Load function from str if needed.
        block_fn = _get_block(block_fn)

        input = Input(shape=input_shape)
        conv1 = _conv_bn_relu(filters=64, kernel_size=(7, 7), strides=(2, 2))(input)
        pool1 = MaxPooling2D(pool_size=(3, 3), strides=(2, 2), padding="same")(conv1)

        block = pool1
        filters = 64
        for i, r in enumerate(repetitions):
            block = _residual_block(block_fn, filters=filters, repetitions=r, is_first_layer=(i == 0))(block)
            filters *= 2

        # Last activation
        block = _bn_relu(block)

        # Classifier block
        block_shape = K.int_shape(block)
        pool2 = AveragePooling2D(pool_size=(block_shape[ROW_AXIS], block_shape[COL_AXIS]),
                                 strides=(1, 1))(block)
        flatten1 = Flatten()(pool2)
        dense = Dense(units=num_outputs, kernel_initializer="he_normal",
                      activation="softmax")(flatten1)

        model = Model(inputs=input, outputs=dense)
        return model

    @staticmethod
    def build_resnet_18(input_shape, num_outputs):
        return ResnetBuilder.build(input_shape, num_outputs, basic_block, [2, 2, 2, 2])

    @staticmethod
    def build_resnet_34(input_shape, num_outputs):
        return ResnetBuilder.build(input_shape, num_outputs, basic_block, [3, 4, 6, 3])

    @staticmethod
    def build_resnet_50(input_shape, num_outputs):
        return ResnetBuilder.build(input_shape, num_outputs, bottleneck, [3, 4, 6, 3])

    @staticmethod
    def build_resnet_101(input_shape, num_outputs):
        return ResnetBuilder.build(input_shape, num_outputs, bottleneck, [3, 4, 23, 3])

    @staticmethod
    def build_resnet_152(input_shape, num_outputs):
        return ResnetBuilder.build(input_shape, num_outputs, bottleneck, [3, 8, 36, 3])

Есть идеи, как это можно исправить?

1 Ответ

0 голосов
/ 09 июля 2019

Вы можете попробовать другой пакет:

Попробуйте это РЕПО 

!pip install image-classifiers

from classification_models import Classifiers
classifier, preprocess_input = Classifiers.get('resnet18')
model = classifier((224, 224, 3), weights='imagenet')
...