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

edit num_workers and change MPA repo as a latest #1314

Merged
merged 1 commit into from
Oct 28, 2022
Merged

edit num_workers and change MPA repo as a latest #1314

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 1 addition & 1 deletion external/model-preparation-algorithm/configs/classification/configuration.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,7 +83,7 @@ learning_parameters:
warning: null
num_workers:
affects_outcome_of: NONE
default_value: 0
default_value: 2
description:
Increasing this value might improve training speed however it might
cause out of memory errors. If the number of workers is set to zero, data loading
Expand Down
2 changes: 0 additions & 2 deletions ...model-preparation-algorithm/configs/classification/efficientnet_b0_cls_incr/template.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,6 @@ hyper_parameters:
batch_size:
default_value: 64
auto_hpo_state: POSSIBLE
num_workers:
default_value: 0
learning_rate:
default_value: 0.0049
auto_hpo_state: POSSIBLE
Expand Down
2 changes: 0 additions & 2 deletions ...del-preparation-algorithm/configs/classification/efficientnet_v2_s_cls_incr/template.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,6 @@ hyper_parameters:
batch_size:
default_value: 64
auto_hpo_state: POSSIBLE
num_workers:
default_value: 0
learning_rate:
default_value: 0.0071
auto_hpo_state: POSSIBLE
Expand Down
2 changes: 0 additions & 2 deletions ...algorithm/configs/classification/mobilenet_v3_large_075_cls_incr/template_experiment.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,6 @@ hyper_parameters:
batch_size:
default_value: 32
auto_hpo_state: POSSIBLE
num_workers:
default_value: 4
learning_rate:
default_value: 0.016
auto_hpo_state: POSSIBLE
Expand Down
2 changes: 0 additions & 2 deletions ...-preparation-algorithm/configs/classification/mobilenet_v3_large_1_cls_incr/template.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,6 @@ hyper_parameters:
batch_size:
default_value: 64
auto_hpo_state: POSSIBLE
num_workers:
default_value: 0
learning_rate:
default_value: 0.0058
auto_hpo_state: POSSIBLE
Expand Down
2 changes: 0 additions & 2 deletions ...ion-algorithm/configs/classification/mobilenet_v3_small_cls_incr/template_experiment.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,6 @@ hyper_parameters:
batch_size:
default_value: 32
auto_hpo_state: POSSIBLE
num_workers:
default_value: 4
learning_rate:
default_value: 0.016
auto_hpo_state: POSSIBLE
Expand Down
2 changes: 1 addition & 1 deletion external/model-preparation-algorithm/configs/detection/configuration.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,7 +101,7 @@ learning_parameters:
warning: null
num_workers:
affects_outcome_of: NONE
default_value: 0
default_value: 2
description:
Increasing this value might improve training speed however it might
cause out of memory errors. If the number of workers is set to zero, data loading
Expand Down
2 changes: 1 addition & 1 deletion external/model-preparation-algorithm/submodule
Open in desktop
Submodule submodule updated 4 files
+7 −0 mpa/det/trainer.py
+4 −0 recipes/stages/_base_/runners/cls_runner.py
+5 −4 recipes/stages/classification/train.yaml
+1 −1 recipes/stages/classification/train_multilabel.yaml