Skip to content

GitLab

Unverified Commit 1275111f authored by andyjpaddle's avatar andyjpaddle Committed by GitHub
Browse files

fix rec attn oom (#4872)

parent ffa21931
Show whitespace changes
Inline Side-by-side
Showing with 5 additions and 5 deletions
test_tipc/configs/rec_mtb_nrtr/train_infer_python.txt
View file @ 1275111f
...@@ -6,7 +6,7 @@ Global.use_gpu:True|True ...@@ -6,7 +6,7 @@ Global.use_gpu:True|True
Global.auto_cast:null Global.auto_cast:null
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300 Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
Global.save_model_dir:./output/ Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128 Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=64
Global.pretrained_model:null Global.pretrained_model:null
train_model_name:latest train_model_name:latest
train_infer_img_dir:./inference/rec_inference train_infer_img_dir:./inference/rec_inference
......
test_tipc/configs/rec_mv3_tps_bilstm_att_v2.0/train_infer_python.txt
View file @ 1275111f
...@@ -6,7 +6,7 @@ Global.use_gpu:True|True ...@@ -6,7 +6,7 @@ Global.use_gpu:True|True
Global.auto_cast:null Global.auto_cast:null
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300 Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
Global.save_model_dir:./output/ Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128 Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=64
Global.pretrained_model:null Global.pretrained_model:null
train_model_name:latest train_model_name:latest
train_infer_img_dir:./inference/rec_inference train_infer_img_dir:./inference/rec_inference
......
test_tipc/configs/rec_r31_sar/train_infer_python.txt
View file @ 1275111f
...@@ -6,7 +6,7 @@ Global.use_gpu:True|True ...@@ -6,7 +6,7 @@ Global.use_gpu:True|True
Global.auto_cast:null Global.auto_cast:null
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300 Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
Global.save_model_dir:./output/ Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128 Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=64
Global.pretrained_model:null Global.pretrained_model:null
train_model_name:latest train_model_name:latest
train_infer_img_dir:./inference/rec_inference train_infer_img_dir:./inference/rec_inference
......
test_tipc/configs/rec_r34_vd_tps_bilstm_att_v2.0/train_infer_python.txt
View file @ 1275111f
...@@ -6,7 +6,7 @@ Global.use_gpu:True|True ...@@ -6,7 +6,7 @@ Global.use_gpu:True|True
Global.auto_cast:null Global.auto_cast:null
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300 Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
Global.save_model_dir:./output/ Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128 Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=64
Global.pretrained_model:null Global.pretrained_model:null
train_model_name:latest train_model_name:latest
train_infer_img_dir:./inference/rec_inference train_infer_img_dir:./inference/rec_inference
......
test_tipc/configs/rec_r50_fpn_vd_none_srn/train_infer_python.txt
View file @ 1275111f
...@@ -6,7 +6,7 @@ Global.use_gpu:True|True ...@@ -6,7 +6,7 @@ Global.use_gpu:True|True
Global.auto_cast:null Global.auto_cast:null
Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300 Global.epoch_num:lite_train_lite_infer=2|whole_train_whole_infer=300
Global.save_model_dir:./output/ Global.save_model_dir:./output/
Train.loader.batch_size_per_card:lite_train_lite_infer=128|whole_train_whole_infer=128 Train.loader.batch_size_per_card:lite_train_lite_infer=16|whole_train_whole_infer=64
Global.pretrained_model:null Global.pretrained_model:null
train_model_name:latest train_model_name:latest
train_infer_img_dir:./inference/rec_inference train_infer_img_dir:./inference/rec_inference
......
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