Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
P
Progressive Layer-based Compression for Convolutional Spiking Neural Network
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Build
Pipelines
Jobs
Pipeline schedules
Artifacts
Deploy
Releases
Package registry
Model registry
Operate
Environments
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Hammouda Elbez
Progressive Layer-based Compression for Convolutional Spiking Neural Network
Commits
12a0e64a
Commit
12a0e64a
authored
2 years ago
by
Mazdak Fatahi
Browse files
Options
Downloads
Patches
Plain Diff
Upload New File
parent
8c089d97
No related branches found
No related tags found
No related merge requests found
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
SpiNNaker/ExractTheWeights.ipynb
+132
-0
132 additions, 0 deletions
SpiNNaker/ExractTheWeights.ipynb
with
132 additions
and
0 deletions
SpiNNaker/ExractTheWeights.ipynb
0 → 100644
+
132
−
0
View file @
12a0e64a
{
"cells": [
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Input file shape = (313600,)\n",
"784 400\n",
"Input file shape = (313600,)\n",
"784 400\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 720x720 with 8 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 720x720 with 8 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"import SpiNNakerHelpers as mySpiNNaker\n",
"\n",
"input_files_name=['weights_fc1_0_0_25_0.7', 'weights_fc1_1_1_25_0.7']\n",
"output_files_name=['weights_fc1_0_0_25_0.7_not_transposed.txt', 'weights_fc1_1_1_25_0.7_not_transposed.txt']\n",
"a=mySpiNNaker.Extract_ConnectionFiles(input_files_name, output_files_name, Input_size=784, Output_size=400, n_samples_to_plot=4, Transpoed=True, Inpute_shape={'x':28, 'y':28} )\n"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Input file shape = (640000,)\n",
"Input file shape = (640000,)\n"
]
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 720x720 with 18 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 720x720 with 18 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"\n",
"\n",
"input_files_name=[ 'weights_fc2_0_0_25_0.7', 'weights_fc2_1_1_25_0.7']\n",
"output_files_name=['weights_fc2_0_0_25_0.7_not_transposed.txt', 'weights_fc2_1_1_25_0.7_not_transposed.txt']\n",
"a=mySpiNNaker.Extract_ConnectionFiles(input_files_name, output_files_name, Input_size=400, Output_size=1600, n_samples_to_plot=9, Transpoed=False, Inpute_shape={'x':20, 'y':20} )\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "snntorch",
"language": "python",
"name": "snntorch"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.10"
},
"orig_nbformat": 4,
"vscode": {
"interpreter": {
"hash": "20a24a3a4007955ef5ee2dc9fb7716c1a03a2c0fc0e1cbee0d7177cafa6993b3"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
%% Cell type:code id: tags:
```
python
import
SpiNNakerHelpers
as
mySpiNNaker
input_files_name
=
[
'
weights_fc1_0_0_25_0.7
'
,
'
weights_fc1_1_1_25_0.7
'
]
output_files_name
=
[
'
weights_fc1_0_0_25_0.7_not_transposed.txt
'
,
'
weights_fc1_1_1_25_0.7_not_transposed.txt
'
]
a
=
mySpiNNaker
.
Extract_ConnectionFiles
(
input_files_name
,
output_files_name
,
Input_size
=
784
,
Output_size
=
400
,
n_samples_to_plot
=
4
,
Transpoed
=
True
,
Inpute_shape
=
{
'
x
'
:
28
,
'
y
'
:
28
}
)
```
%% Output
Input file shape = (313600,)
784 400
Input file shape = (313600,)
784 400
%% Cell type:code id: tags:
```
python
input_files_name
=
[
'
weights_fc2_0_0_25_0.7
'
,
'
weights_fc2_1_1_25_0.7
'
]
output_files_name
=
[
'
weights_fc2_0_0_25_0.7_not_transposed.txt
'
,
'
weights_fc2_1_1_25_0.7_not_transposed.txt
'
]
a
=
mySpiNNaker
.
Extract_ConnectionFiles
(
input_files_name
,
output_files_name
,
Input_size
=
400
,
Output_size
=
1600
,
n_samples_to_plot
=
9
,
Transpoed
=
False
,
Inpute_shape
=
{
'
x
'
:
20
,
'
y
'
:
20
}
)
```
%% Output
Input file shape = (640000,)
Input file shape = (640000,)
%% Cell type:code id: tags:
```
python
```
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment