could not broadcast input array from shape (1000,1,1) into shape (1,1000)

[gauticse2015]

When i run the visualize.py code, i got the above error as follows:-

Traceback (most recent call last): File "visualize.py", line 69, in bw = net.backward(**{net.outputs[0]: caffeLabel}) File "../python/caffe/pycaffe.py", line 167, in _Net_backward self.blobs[top].diff[...] = diff ValueError: could not broadcast input array from shape (1000,1,1) into shape (1,1000)

and when i change the net.backward line as: bw = net.backward(), it runs perfectly. please tell me what is the problem??

[artvandelay]

It might have to do with the caffe version. Which version are you using?

On 05-Aug-2016 4:28 PM, "gauticse2015" notifications@github.com wrote:

When i run the visualize.py code, i got the above error as follows:-

Traceback (most recent call last): File "visualize.py", line 69, in bw = net.backward(**{net.outputs[0]: caffeLabel}) File "../python/caffe/pycaffe.py", line 167, in _Net_backward self.blobs[top].diff[...] = diff ValueError: could not broadcast input array from shape (1000,1,1) into shape (1,1000)

and when i change the net.backward line as: bw = net.backward(), it runs perfectly. please tell me what is the problem??

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/artvandelay/Deep_Inside_Convolutional_Networks/issues/1, or mute the thread https://github.com/notifications/unsubscribe-auth/ABMc5O0qsbI891B0qRTqMzRLZwthSnzJks5qcxc7gaJpZM4Jdk7O .

[gauticse2015]

My current version of caffe is "1.0.0-rc3".

[gauticse2015]

i have modified two lines of code in visualize.py as:

caffeLabel = np.zeros((1,1000)) caffeLabel[0,label_index] = 1;

now its gives desired result.

Thanks...

[artvandelay]

I'll make the changes to the code. I wonder if only the rc version has this issue.

[artvandelay]

Closing it

[bgth]

Hi @artvandelay .. Is it possible to update the code with this change? This works for latest caffe. Thanks.