Commit 3365a5e8 authored by Shaoshuai Shi's avatar Shaoshuai Shi
Browse files

update default training batch for PartA2 and training epochs for centerpoint

parent 82987c4d
......@@ -170,7 +170,7 @@ MODEL:
OPTIMIZATION:
BATCH_SIZE_PER_GPU: 3
BATCH_SIZE_PER_GPU: 2
NUM_EPOCHS: 30
OPTIMIZER: adam_onecycle
......
......@@ -76,7 +76,7 @@ MODEL:
OPTIMIZATION:
BATCH_SIZE_PER_GPU: 4
NUM_EPOCHS: 36
NUM_EPOCHS: 30
OPTIMIZER: adam_onecycle
LR: 0.003
......
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