When using slayer.block.cuba.Pool, input-output dimensions are not as expected.

lava-nc / lava-dl

Deep Learning library for Lava

https://lava-nc.org

BSD 3-Clause "New" or "Revised" License

149 stars 71 forks source link

When using slayer.block.cuba.Pool, input-output dimensions are not as expected. #293

Open LjubicaCimesa opened 5 months ago

LjubicaCimesa commented 5 months ago

Steps to reproduce the behavior:

When I run this code

import torch
input = torch.randn(1,8,6,7,160)
CL= slayer.block.cuba.Pool(neuron_params, kernel_size =(2,2) , stride = 2, padding =0)
output = CL(input)
output.shape

I get output of shape [1, 8, 3, 4, 160]

Expected behavior

After pooling, I expected to get the shape [1,8,3,3,160]

Environment (please complete the following information):

Device: Laptop MAC
OS: MAC Sonoma 14.3.1 (23D60)
Lava version [e.g. 0.5.0]

PhilippPlank commented 4 months ago

Thank you for you question. @bamsumit Could you take a look at it?