I have installed the newest mxnet version 1.0.0 from pip. When I print the Layer's weight, it assert a KeyError: "Shape". I'm new in mxnet and everything I have followed with the mxnet official tutorial.
import mxnet
from mxnet import nd,gluon,autograd
net=gluon.nn.Dense(10,in_units=30)
print (net.weight)
The error is:
Traceback (most recent call last):
File "/home/user/docs/mxnet/mtcnn/tmp/learn_mxnet.py", line 5, in <module>
print (net.weight)
File "/usr/local/lib/python2.7/dist-packages/mxnet/gluon/parameter.py", line 120, in __repr__
return s.format(**self.__dict__)
KeyError: 'shape'
I think it may be the problem of the version 1.0.0.
To check the weights, you first need to initialize them as follows:
net.collect_params().initialize(mx.init.Xavier(), ctx=mx.cpu())
In your case, because you didn't specify input size to layers in Net's constructor, the shape of parameters cannot be determined at this point. So, if you access net.weight.data() now, an exception will be raised:
Traceback (most recent call last):
File "<stdin>", line 1, in <module>
File "/usr/local/lib/python2.7/dist-packages/mxnet-0.12.1-py2.7.egg/mxnet/gluon/parameter.py", line 389, in data
return self._check_and_get(self._data, ctx)
File "/usr/local/lib/python2.7/dist-packages/mxnet-0.12.1-py2.7.egg/mxnet/gluon/parameter.py", line 189, in _check_and_get
"nested child Blocks"%(self.name))
RuntimeError: Parameter dense0_weight has not been initialized. Note that you should initialize parameters and create Trainer with Block.collect_params() instead of Block.params because the later does not include Parameters of nested child Blocks
You can initialize the weights as follows:
net.collect_params().initialize(mxnet.init.Xavier(), ctx=mxnet.cpu())
print (net.weight.data())