Skip to content

Commit

Permalink
Update README.MD
Browse files Browse the repository at this point in the history
  • Loading branch information
yangheng95 authored Jan 16, 2022
1 parent f34234c commit 193e8ae
Showing 1 changed file with 8 additions and 3 deletions.
11 changes: 8 additions & 3 deletions README.MD
Original file line number Diff line number Diff line change
Expand Up @@ -10,12 +10,17 @@ We hope you can share your custom dataset or a available public dataset. If you

### Important: Rename your dataset filename before use it in PyABSA

- APC dataset name should be: {id}.dataset name}.{type}.dat , e.g., 996.restaurant.train.dat, 996.restaurant.test.dat, 996.restaurant.valid.dat
- ATEPC dataset name should be: {id}.{dataset name}.{type}.dat.atepc , e.g., 996.restaurant.train.dat.atepc, 996.restaurant.test.dat.atepc, 996.restaurant.valid.dat.atepc
- APC dataset name should be: {id}.dataset name}.{type}.dat , e.g., `996.restaurant.train.dat`, `996.restaurant.test.dat`, `996.restaurant.valid.dat`
- ATEPC dataset name should be: {id}.{dataset name}.{type}.dat.atepc , `e.g., 996.restaurant.train.dat.atepc`, `996.restaurant.test.dat.atepc`, `996.restaurant.valid.dat.atepc`

Then, use the id to loacte your dataset, e.g.,

```python3
Trainer(config=_config,
from pyabsa.functional import APCConfigManager

config = APCConfigManager.get_apc_config_english() # APC task

Trainer(config=config,
dataset='996.restaurant', # train set and test set will be automatically detected
checkpoint_save_mode=1,
auto_device=device # automatic choose CUDA or CPU
Expand Down

0 comments on commit 193e8ae

Please sign in to comment.