1d52eb75c5fcfb3f9465eb6614b7bb2b57dece4d,autokeras/layer_transformer.py,,deeper_conv_block,#Any#Any#Any#,10

Before Change

    Returns:
        The deeper convolution layer
    
    filter_shape = (kernel_size,) * (len(conv_layer.kernel_size))
    n_filters = conv_layer.filters
    weight = np.zeros(filter_shape + (n_filters, n_filters))
    center = tuple(map(lambda x: int((x - 1) / 2), filter_shape))
    for i in range(n_filters):
        filter_weight = np.zeros(filter_shape + (n_filters,))
        index = center + (i,)
        filter_weight[index] = 1
        weight[..., i] = filter_weight
    bias = np.zeros(n_filters)
    new_conv_layer = StubConv(n_filters, kernel_size=filter_shape, func=conv_layer.func)
    bn = StubBatchNormalization()

    if weighted:
        new_conv_layer.set_weights((add_noise(weight, np.array([0, 1])), add_noise(bias, np.array([0, 1]))))
        new_weights = [np.ones(n_filters, dtype=np.float32),
                       np.zeros(n_filters, dtype=np.float32),
                       np.zeros(n_filters, dtype=np.float32),
                       np.ones(n_filters, dtype=np.float32)]
        bn.set_weights(new_weights)

    return [bn,
            StubActivation("relu"),
            new_conv_layer,
            StubDropout(constant.CONV_DROPOUT_RATE)]


def dense_to_deeper_block(dense_layer, weighted=True):
    Get deeper layer for dense layer

After Change

    
    if not weighted:
        return StubConvBlock(conv_layer.filters, conv_layer.kernel_size)
    filter_shape = (kernel_size,) * (len(conv_layer.get_weights()[1][0].shape) - 2)
    n_filters = conv_layer.filters
    weight = np.zeros(filter_shape + (n_filters, n_filters))
    center = tuple(map(lambda x: int((x - 1) / 2), filter_shape))
    for i in range(n_filters):
        filter_weight = np.zeros(filter_shape + (n_filters,))
        index = center + (i,)
        filter_weight[index] = 1
        weight[..., i] = filter_weight
    bias = np.zeros(n_filters)
    conv_weights = (add_noise(weight, np.array([0, 1])), add_noise(bias, np.array([0, 1])))
    // conv_weights = (weight, bias)
    new_conv_layer = StubConvBlock(n_filters, kernel_size=filter_shape)

    bn_weights = [np.ones(n_filters, dtype=np.float32),
                   np.zeros(n_filters, dtype=np.float32),
                   np.zeros(n_filters, dtype=np.float32),
                   np.ones(n_filters, dtype=np.float32)]
    new_conv_layer.set_weights([bn_weights, conv_weights])

    return new_conv_layer


def dense_to_deeper_block(dense_layer, weighted=True):
    Get deeper layer for dense layer

Instances