Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
A
accelerated_deeplearning_training
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
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
Code review analytics
Issue 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
Accelerated_training
accelerated_deeplearning_training
Merge requests
!11
Subsampler and qr
Code
Review changes
Check out branch
Download
Patches
Plain diff
Merged
Subsampler and qr
subsampler_and_QR
into
master
Overview
0
Commits
6
Pipelines
0
Changes
1
Merged
Lupo Pasini, Massimiliano
requested to merge
subsampler_and_QR
into
master
4 years ago
Overview
0
Commits
6
Pipelines
0
Changes
1
Expand
0
0
Merge request reports
Viewing commit
21a88c0b
Prev
Next
Show latest version
1 file
+
2
−
2
Inline
Compare changes
Side-by-side
Inline
Show whitespace changes
Show one file at a time
21a88c0b
LogSoftMax activation function used
· 21a88c0b
Massimiliano Lupo Pasini
authored
4 years ago
modules/NN_models.py
+
2
−
2
Options
@@ -146,7 +146,7 @@ class MLP(NeuralNetwork, ABC):
# Activation function for classification problem
if
classification
:
self
.
layers
+=
[
torch
.
nn
.
Softmax
()]
self
.
layers
+=
[
torch
.
nn
.
Log
Softmax
()]
# Multilayer perceptron
self
.
model
=
torch
.
nn
.
Sequential
(
*
self
.
layers
)
@@ -224,7 +224,7 @@ class CNN2D(NeuralNetwork, ABC):
bias
=
self
.
use_bias
)]
# Activation function for classification problem
self
.
layers
+=
[
torch
.
nn
.
Softmax
()]
self
.
layers
+=
[
torch
.
nn
.
Log
Softmax
()]
# Convolutional neural network
self
.
model
=
torch
.
nn
.
Sequential
(
*
self
.
layers
)
Loading