NetX Dimension Seems Lost

[lava-nc]

NetX Dimension Seems Lost

[bamsumit]

@ahmetakman your network, as you defined in self.blocks, has two hidden layers and one output layer of dimensions 512, 512, and 10 respectively. So it does make sense to get the dimension of the network as 512, 512, and 10 when you load the network, isn't it?

[ahmetakman]

I thought the dimension should be
Dense : Process_1 , shape : (34342,512)
Dense : Process_4 , shape : (512,512)
Dense : Process_7 , shape : (512,10)
As were in the NetX examples.

[bamsumit]

Look at the dense block definition in PilotNet SDNN training

and the shapes in PilotNet SDNN inference with NetX

[ahmetakman]

I have mistaken the error about the dimensions I got when was connecting the processes. I will try again soon ,and write back. Thanks for the reply.

[ahmetakman]

Let me come back to here,

First of all, I am not sure my environment is fully utilized but at some point I have a system with barely passing unit tests with hanging code block issue #55 .

Here my interpretation about NetX dimensions is still because of the current error I am getting. Let me summarize my goal then give the error.

I would like to run trained NMNIST model with lava core by using NetX network exchange. The result of the conversion is given above.

When I try to connect processes with the code block:

gt_logger = io.sink.RingBuffer(shape=(1,), buffer=num_steps)
output_logger = io.sink.RingBuffer(shape=net.out_layer.shape, buffer=num_steps)
dataloader.ground_truth.connect(gt_logger.a_in)
dataloader.s_out.connect(net.in_layer.neuron.a_in) ***** issue line ********
net.out_layer.out.connect(output_logger.a_in)

I get the error

AssertionError: Shapes torch.Size([2312]) and (512,) are incompatible.]()

First, my interpretation was the dimension was lost since it is 512 not 2312

[bamsumit]

Aren't you supposed to connect the dataloader.s_out to net.in_layer.synapse.s_in ? It seems you are bypassing the syanpse of the first layer!

dataloader.s_out.connect(net.in_layer.syanpse.s_in)

[ahmetakman]

Yeah that was it, now I have connected processes the run config is running right now.

Thank you very much for the explanation. I sincerely thank for your patience.

I am actively learning the lava-ecosystem, SNNs ,and the new computers I am running them on.
Until I completely got the structure, I think it is natural to misunderstand some concepts.

I am closing the issue,
All the best,
Ahmet.

[bamsumit]

No problem @ahmetakman, happy to clarify any confusion.