python - Stride with different height and width in Tensorflow -


i'm using tensorflow process 1d signals (shape being (?, 5000, 1, 12)) , perform stride operations. however, when try tf.nn.conv2d(input_variable, w, strides=[1, stride, 1, 1], padding='same'), valueerror:

/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/common_shapes.pyc in conv2d_shape(op)     207   if stride_r != stride_c:     208     # todo(shlens): add support this. --> 209     raise valueerror("current implementation supports equal length "     210                      "strides in row , column dimensions.")     211   valueerror: current implementation supports equal length strides in row , column dimensions. 

is there known workaround limits of current implementation, allow me have horizontal stride only?

we're working on supporting strides different lengths.


Comments

Popular posts from this blog

How to check data type in C++? -

javascript - Is getTimezoneOffset() stable during daylight saving transition? -

sql server - SQL Query returns one result, does not return 0 or NULL result -