Skip to content

GitLab

Commit 6aa8eb46 authored by Neal Wu's avatar Neal Wu Committed by GitHub
Browse files

Merge pull request #1565 from derekjchow/master 

Reduce batchsize from 32->24 for SSD configs.
parents df05d720 4b31d8fe
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
object_detection/samples/configs/ssd_inception_v2_pets.config
View file @ 6aa8eb46
...@@ -134,7 +134,7 @@ model { ...@@ -134,7 +134,7 @@ model {
} }
train_config: { train_config: {
batch_size: 32 batch_size: 24
optimizer { optimizer {
rms_prop_optimizer: { rms_prop_optimizer: {
learning_rate: { learning_rate: {
......
object_detection/samples/configs/ssd_mobilenet_v1_pets.config
View file @ 6aa8eb46
...@@ -140,7 +140,7 @@ model { ...@@ -140,7 +140,7 @@ model {
} }
train_config: { train_config: {
batch_size: 32 batch_size: 24
optimizer { optimizer {
rms_prop_optimizer: { rms_prop_optimizer: {
learning_rate: { learning_rate: {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment