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

Align HPO search space to new default hyper parameter #1240

Merged
merged 1 commit into from
Sep 5, 2022
Merged

Align HPO search space to new default hyper parameter #1240

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
8 changes: 4 additions & 4 deletions ...del-preparation-algorithm/configs/classification/efficientnet_b0_cls_incr/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@ hp_space:
learning_parameters.learning_rate:
param_type: qloguniform
range:
- 0.0003
- 0.1
- 0.0014
JihwanEom marked this conversation as resolved.
Show resolved Hide resolved
- 0.035
- 0.0001
learning_parameters.batch_size:
param_type: qloguniform
range:
- 64
- 256
- 42
JihwanEom marked this conversation as resolved.
Show resolved Hide resolved
- 96
- 2
8 changes: 4 additions & 4 deletions ...l-preparation-algorithm/configs/classification/efficientnet_v2_s_cls_incr/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@ hp_space:
learning_parameters.learning_rate:
param_type: qloguniform
range:
- 0.0014
- 0.035
- 0.0007
- 0.07
- 0.0001
learning_parameters.batch_size:
param_type: qloguniform
range:
- 40
- 96
- 32
- 128
- 2
8 changes: 4 additions & 4 deletions ...reparation-algorithm/configs/classification/mobilenet_v3_large_1_cls_incr/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@ hp_space:
learning_parameters.learning_rate:
param_type: qloguniform
range:
- 0.0032
- 0.08
- 0.0008
- 0.1
- 0.0001
learning_parameters.batch_size:
param_type: qloguniform
range:
- 40
- 96
- 64
JihwanEom marked this conversation as resolved.
Show resolved Hide resolved
- 256
- 2
6 changes: 3 additions & 3 deletions ...l/model-preparation-algorithm/configs/detection/cspdarknet_yolox_cls_incr/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,12 +5,12 @@ hp_space:
learning_parameters.learning_rate:
param_type: qloguniform
range:
- 0.00004
- 0.001
- 0.00002
- 0.002
- 0.00001
learning_parameters.batch_size:
param_type: qloguniform
range:
- 4
- 32
- 16
- 2
2 changes: 1 addition & 1 deletion ...l/model-preparation-algorithm/configs/detection/mobilenetv2_atss_cls_incr/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,5 +12,5 @@ hp_space:
param_type: qloguniform
range:
- 4
- 32
- 16
- 2
8 changes: 4 additions & 4 deletions ...al/model-preparation-algorithm/configs/detection/mobilenetv2_ssd_cls_incr/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,12 +5,12 @@ hp_space:
learning_parameters.learning_rate:
param_type: qloguniform
range:
- 0.001
- 0.1
- 0.002
- 0.05
- 0.001
learning_parameters.batch_size:
param_type: qloguniform
range:
- 4
- 32
- 6
- 12
- 2
12 changes: 6 additions & 6 deletions ...l/model-preparation-algorithm/configs/segmentation/ocr-lite-hrnet-18-mod2/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,14 +2,14 @@ metric: mDice
search_algorithm: asha
hp_space:
learning_parameters.learning_rate:
param_type: quniform
param_type: qloguniform
range:
- 0.001
- 0.1
- 0.001
- 0.0002
- 0.005
- 0.0001
learning_parameters.batch_size:
param_type: qloguniform
range:
- 4
- 16
- 6
- 12
- 2
13 changes: 6 additions & 7 deletions ...al/model-preparation-algorithm/configs/segmentation/ocr-lite-hrnet-s-mod2/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,16 +1,15 @@
metric: mDice
search_algorithm: asha
# max_iterations: 30
hp_space:
learning_parameters.learning_rate:
param_type: quniform
param_type: qloguniform
range:
- 0.001
- 0.1
- 0.001
- 0.0002
- 0.005
- 0.0001
learning_parameters.batch_size:
param_type: qloguniform
range:
- 4
- 16
- 6
- 12
- 2
9 changes: 4 additions & 5 deletions ...al/model-preparation-algorithm/configs/segmentation/ocr-lite-hrnet-x-mod3/hpo_config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,13 +1,12 @@
metric: mDice
search_algorithm: asha
# max_iterations: 30
hp_space:
learning_parameters.learning_rate:
param_type: quniform
param_type: qloguniform
range:
- 0.001
- 0.1
- 0.001
- 0.0001
- 0.01
- 0.0001
learning_parameters.batch_size:
param_type: qloguniform
range:
Expand Down