Add the models and process of conv_in_time in src/lava/proc/conv_in_time

zeyuliu1037 commented 5 months ago

Issue Number:

Objective of pull request: Add the models and process of conv_in_time

Pull request checklist

Your PR fulfills the following requirements:

[ ] Issue created that explains the change and why it's needed
[x] Tests are part of the PR (for bug fixes / features)
[x] Docs reviewed and added / updated if needed (for bug fixes / features)
[x] PR conforms to Coding Conventions
[ ] PR applys BSD 3-clause or LGPL2.1+ Licenses to all code files
[ ] Lint (flakeheaven lint src/lava tests/) and (bandit -r src/lava/.) pass locally
[ ] Build tests (pytest) passes locally

Pull request type

Please check your PR type:

[ ] Bugfix
[x] Feature
[ ] Code style update (formatting, renaming)
[ ] Refactoring (no functional changes, no api changes)
[ ] Build related changes
[ ] Documentation changes
[ ] Other (please describe):

What is the current behavior?

None

What is the new behavior?

Conv in time can apply the Conv1d in the time dimension instead of the position dimension applied by the original convolution layer. The kernel size determines the delay time of the module. Specifically, for a kernel size of K, the delay time is K-1, i.e., after K-1 time steps, the module will output the correct result sequentially.

Does this introduce a breaking change?

[ ] Yes
[x] No

Supplemental information

The test code is located in the bottom comment of the /src/lava/proc/conv_in_time/process.py file.

bamsumit commented 4 months ago

@zeyuliu1037 seems there are some linting errors regarding code quality. Link here. Can you fix them?

zeyuliu1037 commented 4 months ago

Thanks for pointing that out, I have fixed them.

Best, Zeyu

On Thu, Feb 22, 2024 at 5:42 PM bamsumit @.***> wrote:

@zeyuliu1037 https://urldefense.com/v3/__https://github.com/zeyuliu1037__;!!LIr3w8kk_Xxm!rAFvGvpo5tcA4RBX8hXoRdOAj0ULpSSqcuSVaQmJ0q-cYbOspHvTYimL9rBxXrB6klhoTPEuxTwgHQh8ILv9dxTu$ seems there are some linting errors regarding code quality. Link here https://urldefense.com/v3/__https://github.com/lava-nc/lava/actions/runs/7999700382/job/21890696613?pr=833__;!!LIr3w8kk_Xxm!rAFvGvpo5tcA4RBX8hXoRdOAj0ULpSSqcuSVaQmJ0q-cYbOspHvTYimL9rBxXrB6klhoTPEuxTwgHQh8ILEcqje2$. Can you fix them?

— Reply to this email directly, view it on GitHub https://urldefense.com/v3/__https://github.com/lava-nc/lava/pull/833*issuecomment-1960621322__;Iw!!LIr3w8kk_Xxm!rAFvGvpo5tcA4RBX8hXoRdOAj0ULpSSqcuSVaQmJ0q-cYbOspHvTYimL9rBxXrB6klhoTPEuxTwgHQh8IPIquLTc$, or unsubscribe https://urldefense.com/v3/__https://github.com/notifications/unsubscribe-auth/AFUFEDOJYRFVEDWDS4GQR2LYU7XXLAVCNFSM6AAAAABCTR3X5SVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSNRQGYZDCMZSGI__;!!LIr3w8kk_Xxm!rAFvGvpo5tcA4RBX8hXoRdOAj0ULpSSqcuSVaQmJ0q-cYbOspHvTYimL9rBxXrB6klhoTPEuxTwgHQh8ILLGn-CU$ . You are receiving this because you were mentioned.Message ID: @.***>

bamsumit commented 4 months ago

@zeyuliu1037 we still have a few linting errors:

tests/lava/proc/conv_in_time/test_process.py
    38:  25 E128 continuation line under-indented for visual indent [pycodestyle]
  n_flat_output_neurons, n_flat_input_neurons]) - 128
  ^
    41:  25 E128 continuation line under-indented for visual indent [pycodestyle]
  "ground_truth/spike_input.npy"))
  ^
    43:  25 E128 continuation line under-indented for visual indent [pycodestyle]
  "ground_truth/quantized_weights_k_out_in.npy"))
  ^
    74:  25 E128 continuation line under-indented for visual indent [pycodestyle]
  "ground_truth/torch_output.npy"))
  ^

lava-nc / lava