Tensorflow
moshanghuakai_pang
这个作者很懒,什么都没留下…
展开
-
Tensorflow中tensor维度的理解以及np.stack的理解
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...转载 2018-10-11 17:07:24 · 1248 阅读 · 0 评论 -
InvalidArgumentError: Matrix size-incompatible: In[0]: [32,4], In[1]: [32,4] [[{{node MatMul}} = M
错误:tensorflow.python.framework.errors_impl.InvalidArgumentError: Matrix size-incompatible: In[0]: [32,4], In[1]: [32,4] [[{{node MatMul}} = MatMul[T=DT_FLOAT, transpose_a=false, transpose_b=false...原创 2018-10-13 10:43:28 · 11761 阅读 · 1 评论 -
错误:InvalidArgumentError: Negative dimension size caused by subtracting 8 from 4 for 'conv2d_1/convol
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。原创 2018-10-10 11:13:35 · 5911 阅读 · 0 评论 -
UserWarning: Update your `Conv2D` call to the Keras 2 API
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 (...原创 2018-10-10 11:17:14 · 1454 阅读 · 0 评论 -
错误:AttributeError: module 'tensorflow' has no attribute 'scalar_summary'
解决方法:将tf.scalar_summary改为tf.summary.scalar原创 2018-10-10 11:26:25 · 4538 阅读 · 2 评论 -
initialize_all_variables (from tensorflow.python.ops.variables) is deprecated and will be removed af
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...原创 2018-10-10 14:20:41 · 6913 阅读 · 0 评论 -
UserWarning: The default mode, 'constant', will be changed to 'reflect' in skimage 0.15. warn("The
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...原创 2018-10-10 15:26:24 · 3079 阅读 · 1 评论 -
解决安装pandas后ImportError: No module named 'pandas'
使用安装命令:pip install --user pandas其他类似,出现上述问题是环境变量的问题,加上--user 完美解决。原创 2019-01-27 09:22:55 · 32157 阅读 · 1 评论