indhub opened a new issue #7814: Pooling operator expects kernel size even when 
'global_pool' is set to True
URL: https://github.com/apache/incubator-mxnet/issues/7814
 
 
   Pooling operator expects kernel size even when 'global_pool' is set to True. 
If 'global_pool' is true, kernel should automatically be set to (height, 
width). User shouldn't have to provide kernel size.
   
   ## Environment info
   Operating System: Ubuntu
   
   Compiler: gcc
   
   Package used (Python/R/Scala/Julia): Python
   
   MXNet version: 0.10
   
   Or if installed from source:
   
   MXNet commit hash (`git rev-parse HEAD`):
   
   If you are using python package, please provide
   
   Python version and distribution:
   Python 2.7.12
   
   If you are using R package, please provide
   
   R `sessionInfo()`:
   
   ## Error Message:
   ```
   Traceback (most recent call last):
     File "resnet50.py", line 965, in <module>
       name='pool5')
     File 
"/usr/local/lib/python2.7/dist-packages/mxnet-0.10.0-py2.7.egg/mxnet/_ctypes/symbol.py",
 line 181, in creator
       ctypes.byref(sym_handle)))
     File 
"/usr/local/lib/python2.7/dist-packages/mxnet-0.10.0-py2.7.egg/mxnet/base.py", 
line 84, in check_call
       raise MXNetError(py_str(_LIB.MXGetLastError()))
   mxnet.base.MXNetError: Required parameter kernel of Shape(tuple) is not 
presented, in operator Pooling(name="", global_pool="True", pool_type="avg")
   ```
   
   ## Minimum reproducible example
   ```
   pool5 = mx.symbol.Pooling(data=data,
       pool_type='avg',
       global_pool=True,
       #kernel=(1,1),
       name='pool')
   ```
   
   ## Steps to reproduce
   or if you are running standard examples, please provide the commands you 
have run that lead to the error.
   
   1. Create a pooling layer with 'global_pool' set to True and kernel size not 
set (like shown above)
   2. Run the code.
   
   
 
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to