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

Fix to input_type node of CubaLIF neurons #107

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Fix to input_type node of CubaLIF neurons #107

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
031ca0b
Added "squeeze()" to update Rockpool RNN example
Apr 29, 2024
c826534
Merge branch 'main' of https://github.com/neuromorphs/NIR
Jun 10, 2024
30f46a7
Fixed issue where scalar neuron modules would have an incorrect `inpu…
Jun 10, 2024
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 nir/ir/neuron.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,8 +60,8 @@ def __post_init__(self):
), "All parameters must have the same shape"
# If w_in is a scalar, make it an array of same shape as v_threshold
self.w_in = np.ones_like(self.v_threshold) * self.w_in
self.input_type = {"input": np.array(self.v_threshold.shape)}
self.output_type = {"output": np.array(self.v_threshold.shape)}
self.input_type = {"input": np.array([np.size(self.v_threshold)])}
self.output_type = {"output": np.array([np.size(self.v_threshold)])}


@dataclass(eq=False)
Expand Down
10 changes: 5 additions & 5 deletions paper/03_rnn/rockpool_apply.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,21 +107,21 @@
},
{
"cell_type": "code",
"execution_count": 16,
"execution_count": 34,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"100%|██████████| 140/140 [00:13<00:00, 10.58it/s]"
"100%|██████████| 140/140 [00:13<00:00, 10.20it/s]"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"n_correct 100 out of 140 (71.42857142857143%)\n"
"n_correct 108 out of 140 (77.14285714285715%)\n"
]
},
{
Expand All @@ -143,7 +143,7 @@
" sample = single_sample[0].numpy()[0] # shape: (256, 12)\n",
"\n",
" output, rec_dict = net(torch.tensor(sample))\n",
" n_output_spikes = np.sum(output.detach().numpy(), axis=1)\n",
" n_output_spikes = np.sum(output.squeeze().detach().numpy(), axis=0)\n",
"\n",
" predicted_label = int(np.argmax(n_output_spikes))\n",
" actual_label = int(single_sample[1])\n",
Expand All @@ -160,7 +160,7 @@
},
{
"cell_type": "code",
"execution_count": 32,
"execution_count": 35,
"metadata": {},
"outputs": [
{
Expand Down
Loading