Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

README typo fixed in 03_rnn #113

Merged
merged 1 commit into from
Sep 6, 2024
Merged

README typo fixed in 03_rnn #113

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions paper/03_rnn/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ Please use as many graphs as your platform supports. The more data in the paper,
### Already available examples

The following examples can be used to get started with NIR export/import:
- `snntorch_apply.ipynb` to train a SRNN in snnTorch with optimized hyperparameters
- `Braille_training_snntorch.ipynb` to train a SRNN in snnTorch with optimized hyperparameters
- `lava_apply.py` to load a graph into Lava and perform inference
- `nengo_apply.ipynb` to load a graph into Nengo and perform inference
- `norse_apply.ipynb` to load a graph into Norse, make some analysis and perform inference
Expand All @@ -58,4 +58,4 @@ The following examples can be used to get started with NIR export/import:

## *Additional information for training*

To train the Braille reading model in snnTorch, use the above listed `braille_training_snntorch.ipynb` notebook. By setting the `reset_mechanism`, `reset_delay` and `parameters_filename` variables, the different models (and corresponding hyperparameters) can be selected. The variable `use_bias` allows to specify if bias can be used or not depending on the target platform. At the very beginning of the notebook, the `store_weights` variable can be set as True or False according to what is needed. A cell for GPU usage is also present.
To train the Braille reading model in snnTorch, use the above listed `Braille_training_snntorch.ipynb` notebook. By setting the `reset_mechanism`, `reset_delay` and `parameters_filename` variables, the different models (and corresponding hyperparameters) can be selected. The variable `use_bias` allows to specify if bias can be used or not depending on the target platform. At the very beginning of the notebook, the `store_weights` variable can be set as True or False according to what is needed. A cell for GPU usage is also present.
Loading