未验证 提交 05b7d526 编写于 作者: u010070587's avatar u010070587 提交者: GitHub

Merge pull request #6957 from Topdu/dygraph

add ABINet pretrained model & fix vitstr yml bug
...@@ -8,7 +8,7 @@ Global: ...@@ -8,7 +8,7 @@ Global:
# evaluation is run every 2000 iterations # evaluation is run every 2000 iterations
eval_batch_step: [0, 2000] eval_batch_step: [0, 2000]
cal_metric_during_train: True cal_metric_during_train: True
pretrained_model: pretrained_model: ./pretrain_models/abinet_vl_pretrained
checkpoints: checkpoints:
save_inference_dir: save_inference_dir:
use_visualdl: False use_visualdl: False
......
...@@ -81,7 +81,7 @@ Train: ...@@ -81,7 +81,7 @@ Train:
Eval: Eval:
dataset: dataset:
name: LMDBDataSet name: LMDBDataSet
data_dir: ./train_data/data_lmdb_release/evaluaiton/ data_dir: ./train_data/data_lmdb_release/evaluation/
transforms: transforms:
- DecodeImage: # load image - DecodeImage: # load image
img_mode: BGR img_mode: BGR
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册