moshanghuakai_pang的博客

tensor维度可以通过下面这个博客来理解:一维堆成二维import numpy as npa=[[1,2,3],   [4,5,6]]print("列表a如下：")print(a)print("增加一维，新维度的下标为0")c=np.stack(a,axis=0)print(c)print("增加一维，新维度的下标为1")c=np.stack(a,axis=1)p...

出现这个问题原因是Conv2D输入输入的顺序问题，正确的顺序是：input_shape= (width,height,channels),根据顺序调整即可。

错误如下：UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), strides=(1, 1), activation="relu")`  model.add(Conv2D(64, (3, 3), subsample=(1, 1), activation='relu'))Traceback (...

解决方法：将tf.scalar_summary改为tf.summary.scalar

Tensorflow :initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed after 2017-03-02.方法：将tf.initialize_all_variables改为tf.global_variables_initializer...

Tensorflow错误： UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15.  warn("The default mode, 'constant', will be changed to 'reflect' in " Traceback (most recent ca...