Skip to content
GitLab
Explore
Sign in
Register
Primary navigation
Search or go to…
Project
F
Foss_SWTT
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
Container 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
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Hyunjun Go
Foss_SWTT
Commits
1e8b3320
Commit
1e8b3320
authored
2 years ago
by
Hyunjun Go
Browse files
Options
Downloads
Patches
Plain Diff
Update README.md
parent
8a2124e2
No related branches found
No related tags found
No related merge requests found
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
README.md
+28
-0
28 additions, 0 deletions
README.md
with
28 additions
and
0 deletions
README.md
+
28
−
0
View file @
1e8b3320
...
...
@@ -22,3 +22,31 @@ Deep learning에 사용되는 프레임워크인 PyTorch를 통해
#### tutorial code
[
ipynb 파일 참조
](
timm_tutorial.ipynb
)
#### timm construct model
*
GPU 사용의 경우
```.cuda()```
혹은
```.to(divice)```
필요
```
python
model
=
timm
.
create_model
(
'
모델명
'
,
pretrained
=
True
,
num_classes
=
num_classes
)
```
#### timm 구현된 model list 출력
```
python
import
timm
from
pprint
import
pprint
model_names
=
timm
.
list_models
(
pretrained
=
True
)
pprint
(
model_names
)
```
#### timm construct optimizer
*
GPU 사용의 경우
```.cuda()```
혹은
```.to(divice)```
필요
```
python
optimizer
=
timm
.
optim
.
create_optimizer_v2
(
model
,
'
옵티마이저 명
'
,
lr
=
learning_rate
)
```
default = SGD(stochastic gradient descent) optimizer
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