0

我正在 python 中实现 SEGNET 分段网络，但出现以下错误，

_Traceback（最近一次调用最后）：文件“/scratch/pkasar.dbatu/training/NEW_SEGNET_updated_on_16_11_20.py”，第 370 行，在 model=segnet(input_shape=(256,256,3),n_labels=1) 文件“/scratch/pkasar .dbatu/training/NEW_SEGNET_updated_on_16_11_20.py”，第 161 行，在 segnet conv_14 = Convolution2D(512, (kernel, kernel), padding="same")(unpool_1) 文件“/home/pkasar.dbatu/.conda/envs/ dl/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py”，第 897 行，调用 self._maybe_build(inputs) 文件“/home/pkasar.dbatu/.conda/envs/ dl/lib/python3.7/site-packages/tensorflow/python/keras/engine/base_layer.py"，第 2416 行，在 _maybe_build self.build(input_shapes) # pylint:disable=not-callable File "/home/pkasar .dbtu/.conda/envs/dl/lib/python3。7/site-packages/tensorflow/python/keras/layers/convolutional.py”，第 153 行，在 build input_channel = self._get_input_channel(input_shape) 文件“/home/pkasar.dbatu/.conda/envs/dl/lib/ python3.7/site-packages/tensorflow/python/keras/layers/convolutional.py"，第293行，在get_input_channel raise ValueError('The channel dimension of the inputs' ValueError: The channel dimension of the inputs should be defined. 发现没有任何。

TensorFlow图像是：- tensorflow 2.2.0 tensorflow-gpu 2.2.0 keras-base 2.4.3 keras-gpu 2.4.3 python 3.7.9 请帮帮我提前谢谢

代码片段如下：-

from keras.layers.convolutional import Convolution2D
from keras.layers.core import Activation, Reshape
from keras.layers.normalization import BatchNormalization
from keras.models import Model
from keras import backend as K
from keras.layers import Layer

class MaxPoolingWithArgmax2D(Layer):
def init(self, pool_size=(2, 2), strides=(2, 2), padding="same", **kwargs):
super(MaxPoolingWithArgmax2D, self).init(**kwargs)
self.padding = padding
self.pool_size = pool_size
self.strides = strides

def call(self, inputs, **kwargs):
    padding = self.padding
    pool_size = self.pool_size
    strides = self.strides
    if K.backend() == "tensorflow":
        ksize = [1, pool_size[0], pool_size[1], 1]
        padding = padding.upper()
        strides = [1, strides[0], strides[1], 1]
        output, argmax = K.tf.nn.max_pool_with_argmax(
            inputs, ksize=ksize, strides=strides, padding=padding
        )
    else:
        errmsg = "{} backend is not supported for layer {}".format(
            K.backend(), type(self).__name__
        )
        raise NotImplementedError(errmsg)
    argmax = K.cast(argmax, K.floatx())
    return [output, argmax]

def compute_output_shape(self, input_shape):
    ratio = (1, 2, 2, 1)
    output_shape = [
        dim // ratio[idx] if dim is not None else None
        for idx, dim in enumerate(input_shape)
    ]
    output_shape = tuple(output_shape)
    return [output_shape, output_shape]

def compute_mask(self, inputs, mask=None):
    return 2 * [None]
class MaxUnpooling2D(Layer):
def init(self, size=(2, 2), **kwargs):
super(MaxUnpooling2D, self).init(**kwargs)
self.size = size

def call(self, inputs, output_shape=None):
    updates, mask = inputs[0], inputs[1]
    with K.tf.variable_scope(self.name):
        mask = K.cast(mask, "int32")
        input_shape = K.tf.shape(updates, out_type="int32")
        #  calculation new shape
        if output_shape is None:
            output_shape = (
                input_shape[0],
                input_shape[1] * self.size[0],
                input_shape[2] * self.size[1],
                input_shape[3],
            )
        self.output_shape1 = output_shape

        # calculation indices for batch, height, width and feature maps
        one_like_mask = K.ones_like(mask, dtype="int32")
        batch_shape = K.concatenate([[input_shape[0]], [1], [1], [1]], axis=0)
        batch_range = K.reshape(
            K.tf.range(output_shape[0], dtype="int32"), shape=batch_shape
        )
        b = one_like_mask * batch_range
        y = mask // (output_shape[2] * output_shape[3])
        x = (mask // output_shape[3]) % output_shape[2]
        feature_range = K.tf.range(output_shape[3], dtype="int32")
        f = one_like_mask * feature_range

        # transpose indices & reshape update values to one dimension
        updates_size = K.tf.size(updates)
        indices = K.transpose(K.reshape(K.stack([b, y, x, f]), [4, updates_size]))
        values = K.reshape(updates, [updates_size])
        ret = K.tf.scatter_nd(indices, values, output_shape)
        return ret

def compute_output_shape(self, input_shape):
    mask_shape = input_shape[1]
    return (
        mask_shape[0],
        mask_shape[1] * self.size[0],
        mask_shape[2] * self.size[1],
        mask_shape[3],
    )
def segnet(input_shape, n_labels, kernel=3, pool_size=(2, 2), output_mode="softmax"):
# encoder
inputs = Input(shape=input_shape)

conv_1 = Convolution2D(64, (kernel, kernel), padding="same")(inputs)
conv_1 = BatchNormalization()(conv_1)
conv_1 = Activation("relu")(conv_1)
conv_2 = Convolution2D(64, (kernel, kernel), padding="same")(conv_1)
conv_2 = BatchNormalization()(conv_2)
conv_2 = Activation("relu")(conv_2)

pool_1, mask_1 = MaxPoolingWithArgmax2D(pool_size)(conv_2)

conv_3 = Convolution2D(128, (kernel, kernel), padding="same")(pool_1)
conv_3 = BatchNormalization()(conv_3)
conv_3 = Activation("relu")(conv_3)
conv_4 = Convolution2D(128, (kernel, kernel), padding="same")(conv_3)
conv_4 = BatchNormalization()(conv_4)
conv_4 = Activation("relu")(conv_4)

pool_2, mask_2 = MaxPoolingWithArgmax2D(pool_size)(conv_4)

conv_5 = Convolution2D(256, (kernel, kernel), padding="same")(pool_2)
conv_5 = BatchNormalization()(conv_5)
conv_5 = Activation("relu")(conv_5)
conv_6 = Convolution2D(256, (kernel, kernel), padding="same")(conv_5)
conv_6 = BatchNormalization()(conv_6)
conv_6 = Activation("relu")(conv_6)
conv_7 = Convolution2D(256, (kernel, kernel), padding="same")(conv_6)
conv_7 = BatchNormalization()(conv_7)
conv_7 = Activation("relu")(conv_7)

pool_3, mask_3 = MaxPoolingWithArgmax2D(pool_size)(conv_7)

conv_8 = Convolution2D(512, (kernel, kernel), padding="same")(pool_3)
conv_8 = BatchNormalization()(conv_8)
conv_8 = Activation("relu")(conv_8)
conv_9 = Convolution2D(512, (kernel, kernel), padding="same")(conv_8)
conv_9 = BatchNormalization()(conv_9)
conv_9 = Activation("relu")(conv_9)
conv_10 = Convolution2D(512, (kernel, kernel), padding="same")(conv_9)
conv_10 = BatchNormalization()(conv_10)
conv_10 = Activation("relu")(conv_10)

pool_4, mask_4 = MaxPoolingWithArgmax2D(pool_size)(conv_10)

conv_11 = Convolution2D(512, (kernel, kernel), padding="same")(pool_4)
conv_11 = BatchNormalization()(conv_11)
conv_11 = Activation("relu")(conv_11)
conv_12 = Convolution2D(512, (kernel, kernel), padding="same")(conv_11)
conv_12 = BatchNormalization()(conv_12)
conv_12 = Activation("relu")(conv_12)
conv_13 = Convolution2D(512, (kernel, kernel), padding="same")(conv_12)
conv_13 = BatchNormalization()(conv_13)
conv_13 = Activation("relu")(conv_13)

pool_5, mask_5 = MaxPoolingWithArgmax2D(pool_size)(conv_13)
print("Build enceder done..")

# decoder

unpool_1 = MaxUnpooling2D(pool_size)([pool_5, mask_5])

conv_14 = Convolution2D(512, (kernel, kernel), padding="same")(unpool_1)
conv_14 = BatchNormalization()(conv_14)
conv_14 = Activation("relu")(conv_14)
conv_15 = Convolution2D(512, (kernel, kernel), padding="same")(conv_14)
conv_15 = BatchNormalization()(conv_15)
conv_15 = Activation("relu")(conv_15)
conv_16 = Convolution2D(512, (kernel, kernel), padding="same")(conv_15)
conv_16 = BatchNormalization()(conv_16)
conv_16 = Activation("relu")(conv_16)

unpool_2 = MaxUnpooling2D(pool_size)([conv_16, mask_4])

conv_17 = Convolution2D(512, (kernel, kernel), padding="same")(unpool_2)
conv_17 = BatchNormalization()(conv_17)
conv_17 = Activation("relu")(conv_17)
conv_18 = Convolution2D(512, (kernel, kernel), padding="same")(conv_17)
conv_18 = BatchNormalization()(conv_18)
conv_18 = Activation("relu")(conv_18)
conv_19 = Convolution2D(256, (kernel, kernel), padding="same")(conv_18)
conv_19 = BatchNormalization()(conv_19)
conv_19 = Activation("relu")(conv_19)

unpool_3 = MaxUnpooling2D(pool_size)([conv_19, mask_3])

conv_20 = Convolution2D(256, (kernel, kernel), padding="same")(unpool_3)
conv_20 = BatchNormalization()(conv_20)
conv_20 = Activation("relu")(conv_20)
conv_21 = Convolution2D(256, (kernel, kernel), padding="same")(conv_20)
conv_21 = BatchNormalization()(conv_21)
conv_21 = Activation("relu")(conv_21)
conv_22 = Convolution2D(128, (kernel, kernel), padding="same")(conv_21)
conv_22 = BatchNormalization()(conv_22)
conv_22 = Activation("relu")(conv_22)

unpool_4 = MaxUnpooling2D(pool_size)([conv_22, mask_2])

conv_23 = Convolution2D(128, (kernel, kernel), padding="same")(unpool_4)
conv_23 = BatchNormalization()(conv_23)
conv_23 = Activation("relu")(conv_23)
conv_24 = Convolution2D(64, (kernel, kernel), padding="same")(conv_23)
conv_24 = BatchNormalization()(conv_24)
conv_24 = Activation("relu")(conv_24)

unpool_5 = MaxUnpooling2D(pool_size)([conv_24, mask_1])

conv_25 = Convolution2D(64, (kernel, kernel), padding="same")(unpool_5)
conv_25 = BatchNormalization()(conv_25)
conv_25 = Activation("relu")(conv_25)

conv_26 = Convolution2D(n_labels, (1, 1), padding="valid")(conv_25)
conv_26 = BatchNormalization()(conv_26)
conv_26 = Reshape(
    (input_shape[0] * input_shape[1], n_labels),
    input_shape=(input_shape[0], input_shape[1], n_labels),
)(conv_26)

outputs = Activation(output_mode)(conv_26)
print("Build decoder done..")

model = Model(inputs=inputs, outputs=outputs, name="SegNet")

return model```
4

3 回答 3

0

你有input_shape=(256,256,3).

你必须有(number_of_samples, nb_channels, rows, cols)

于 2020-11-17T09:05:39.157 回答
0

MaxUnpooling2D 类定义中需要进行以下更改：-

class MaxUnpooling2D(Layer):
def __init__(self, size=(2, 2), **kwargs):
    super(MaxUnpooling2D, self).__init__(**kwargs)
    self.size = size

def call(self, inputs, output_shape=None):
    updates, mask = inputs[0], inputs[1]
    with tf.compat.v1.variable_scope(self.name):
        mask = K.cast(mask, 'int32')
        input_shape = tf.shape(updates, out_type='int32')
        #print(updates.shape)
        #print(mask.shape)
        if output_shape is None:
            output_shape = (
                input_shape[0],
                input_shape[1] * self.size[0],
                input_shape[2] * self.size[1],
                input_shape[3])

        ret = tf.scatter_nd(K.expand_dims(K.flatten(mask)),
                              K.flatten(updates),
                              [K.prod(output_shape)])

        input_shape = updates.shape
        out_shape = [-1,
                     input_shape[1] * self.size[0],
                     input_shape[2] * self.size[1],
                     input_shape[3]]
    return K.reshape(ret, out_shape)

def get_config(self):
    config = super().get_config().copy()
    config.update({
        'size': self.size
    })
    return config

def compute_output_shape(self, input_shape):
    mask_shape = input_shape[1]
    return (
            mask_shape[0],
            mask_shape[1]*self.size[0],
            mask_shape[2]*self.size[1],
            mask_shape[3]
            )
于 2020-11-18T08:26:35.410 回答
0

只是对答案的补充，由于 get_config 方法，我收到了 json 序列化警告。因此，我无法保存模型，如果有人遇到类似问题，请使用以下方法修复它：

def get_config(self):
    config = super(MaxUnpooling2D, self).get_config()
    config.update({'size': self.size})
    return config
于 2020-12-29T18:46:42.987 回答