Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
P
PySegCNN
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Deploy
Releases
Package registry
Container Registry
Model registry
Operate
Terraform modules
Monitor
Incidents
Analyze
Value stream analytics
Contributor 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
earth_observation_public
PySegCNN
Commits
862ef05b
Commit
862ef05b
authored
4 years ago
by
Frisinghelli Daniel
Browse files
Options
Downloads
Patches
Plain Diff
Removed cval argument: merged model_config and train_config
parent
a2814daf
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
pysegcnn/main/config.py
+4
-14
4 additions, 14 deletions
pysegcnn/main/config.py
with
4 additions
and
14 deletions
pysegcnn/main/config.py
+
4
−
14
View file @
862ef05b
...
...
@@ -66,9 +66,6 @@ dataset_config = {
# used if split_mode='random' and split_mode='scene'
'
seed
'
:
0
,
# the constant value to pad around the ground truth mask if pad=True
'
cval
'
:
99
,
# whether to sort the dataset in chronological order, useful for time
# series data
'
sort
'
:
False
,
...
...
@@ -206,15 +203,15 @@ model_config = {
# was trained on
# whether to use a pretrained model for transfer learning
'
pretrained
'
:
Fals
e
,
'
transfer
'
:
Tru
e
,
# name of the pretrained model to apply to a different dataset
'
pretrained_model
'
:
'
UNet_SparcsDataset_t125_b
128
_rgbn.pt
'
,
'
pretrained_model
'
:
'
UNet_SparcsDataset_t125_b
64
_rgbn.pt
'
,
# Training ----------------------------------------------------------------
# whether to resume training from an existing model checkpoint
'
checkpoint
'
:
Fals
e
,
'
checkpoint
'
:
Tru
e
,
# define the batch size
# determines how many samples of the dataset are processed until the
...
...
@@ -222,13 +219,7 @@ model_config = {
'
batch_size
'
:
64
,
# the seed for the random number generator intializing the network weights
'
torch_seed
'
:
0
}
# the training configuration dictionary
train_config
=
{
'
torch_seed
'
:
0
,
# ----------------------------- Training ---------------------------------
...
...
@@ -307,5 +298,4 @@ eval_config = {
config
=
{
**
dataset_config
,
**
split_config
,
**
model_config
,
**
train_config
,
**
eval_config
}
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