ValueError: Broadcasting failed

[dotaa]

hey,
I am using my own dataset and getting the following error,
Traceback (most recent call last):
File "train_mnist.py", line 177, in
main()
File "train_mnist.py", line 173, in main
trainer.run()
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/training/trainer.py", line 313, in run
six.reraise(*sys.exc_info())
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/training/trainer.py", line 299, in run
update()
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/training/updater.py", line 223, in update
self.update_core()
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/training/updater.py", line 234, in update_core
optimizer.update(loss_func, *in_arrays)
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/optimizer.py", line 536, in update
loss = lossfun(*args, **kwds)
File "/home/ram/sanaa/workspace/style_occasion/sanaa/train_conv/train_conv_multi/chainer-center-loss-master/model.py", line 49, in call
center_loss = self.center_loss_function(h, t)
File "/home/ram/sanaa/workspace/style_occasion/sanaa/train_conv/train_conv_multi/chainer-center-loss-master/center_loss.py", line 78, in call
return CenterLossFunction(self.alpha, self.num_classes)(x, t, self.centers)
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/function.py", line 235, in call
ret = node.apply(inputs)
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/function_node.py", line 245, in apply
outputs = self.forward(in_data)
File "/home/ram/sanaa/local/lib/python2.7/site-packages/chainer/function.py", line 135, in forward
return self._function.forward(inputs)
File "/home/ram/sanaa/workspace/style_occasion/sanaa/train_conv/train_conv_multi/chainer-center-loss-master/center_loss.py", line 39, in forward
y = xp.sum(xp.square(features - centers_batch)) / batch_size / 2
File "cupy/core/core.pyx", line 1185, in cupy.core.core.ndarray.sub
File "cupy/core/elementwise.pxi", line 798, in cupy.core.core.ufunc.call
File "cupy/core/core.pyx", line 2308, in cupy.core.core.broadcast.init
ValueError: Broadcasting failed
help would be appreciated!
thanks!

[shunk031]

File "/home/ram/sanaa/workspace/style_occasion/sanaa/train_conv/train_conv_multi/chainer-center-loss-master/center_loss.py", line 39, in forward
y = xp.sum(xp.square(features - centers_batch)) / batch_size / 2

Please check the dimension of features and centers_batch. If the dimension mismatched, above error is raised.
This code is written in Python 3.5.1, so I recommend that you use Python3.5 or higher.

[dotaa]

hello! yes, i solved that error.
its running but my cost values are exploding to NaN when i use center loss. when i disable it, the values are fine.
also, there is an issue with the script when passing
center_loss = self.center_loss_function(h, t, self.alpha_ratio)
it gives the error, Can take only 3 arguments, 4 given. so i removed self.alpha_ratio. is that why my values are going to Nan?
Can anybody help me with this?
Thanks!

[dotaa]

I tried debugging. but i am not able to understand...i printed out the centers, and after sometime, the center values are really very high and they go to Nan. is this a bug in the code. I print out the centers and they look like,

Can you help pls?

update:
i am using SGD momentum instead of adam. the cost values of just center loss is as high as 700.0 , now it isnt going to Nan.