Question

当我尝试将它附加到InceptionV3时，我无法使GlobalAveragePooling2D工作。有谁看到我做错了什么？我可以让GlobalMaxPooling2D工作。

inceptModel = InceptionV3(include_top=False, input_shape= (162,243, 3))
x = inceptModel.outputs
x = GlobalAveragePooling2D()(x)

结果

Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/opt/anaconda/anaconda3/lib/python3.5/site-packages/keras/engine/topology.py", line 617, in __call__
    output = self.call(inputs, **kwargs)
  File "/opt/anaconda/anaconda3/lib/python3.5/site-packages/keras/layers/pooling.py", line 540, in call
    return K.mean(inputs, axis=[1, 2])
  File "/opt/anaconda/anaconda3/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py", line 1362, in mean
    if x.dtype.base_dtype == tf.bool:
AttributeError: 'list' object has no attribute 'dtype'

但是

GlobalMaxPooling2D()(x)

工作正常。有没有人有想法？

版本：

import keras; print(keras.__version__)
2.1.3

import tensorflow as tf; print(tf.__version__)
1.2.1

GlobalAveragePooling2D（） - AttributeError：＆＃39; list＆＃39;对象没有属性＆＃39; dtype＆＃39;

0 个答案: