bamsumit
bamsumit
@chenjiefighting look st this repo: https://github.com/neuromorphs/tonic
Hi, I am happy to provide pointers. Before you start implementing, you may want to port Slayer 2.0 instead (https://github.com/lava-nc/lava-dl). It's newer, supports more features, and is actively maintained. If...
Hi did you successfully install the package?
Can you try adding `.contiguous()` in line 734 and 740 of `slayer.py` ` input.reshape(...)`**`.contiguous()`**
The networks trained with slayer auto export the network in hdf5 format that is compatible with lava-dl. For others, you will need to manually create the lava network to run...
The performance on TIDIGIT depends on the spike encoding. What is the spike encoding you are using? If you are using NTIDIGITS, the config and accuracy seems fine.
@qianhuiliu are you learning axonal delay as well?
@mathisrichter The [MNIST training tutorial](https://github.com/lava-nc/lava-dl/blob/main/tutorials/lava/lib/dl/bootstrap/mnist/train.ipynb) already shows how the training can be done without the `assistant`. It is the same steps as training a standard PyTorch network, so it would...
@rileywhite-noblis The input block typically consists of neuron only. The fix you suggested works in python but will not work on Loihi because a neuron can only get its input...
@danielbdr there seem to be linting errors as well.