Richard Wong
6072e4408c
- added frozen encoder/decoder variants |
||
|---|---|---|
| .. | ||
| classification_bert_complete_desc | ||
| classification_bert_complete_desc_unit | ||
| classification_bert_complete_desc_unit_name | ||
| classification_bert_pattern_desc | ||
| classification_bert_pattern_desc_unit | ||
| classification_t5_complete | ||
| classification_t5_complete_with_constrastive | ||
| classification_t5_mdm_with_contrastive | ||
| frozen_t5_decoder | ||
| frozen_t5_encoder | ||
| hybrid_t5_complete_desc_unit | ||
| hybrid_t5_pattern_desc_unit | ||
| mapping_baseline | ||
| mapping_t5_complete_desc | ||
| mapping_t5_complete_desc_unit | ||
| mapping_t5_complete_desc_unit_name | ||
| mapping_t5_final_delivery_model | ||
| mapping_t5_pattern_desc_unit | ||
| modified_t5_decoder_1_layers | ||
| modified_t5_decoder_2_layers | ||
| modified_t5_decoder_3_layers | ||
| modified_t5_decoder_4_layers | ||
| modified_t5_decoder_8_layers | ||
| modified_t5_decoder_9_layers | ||
| modified_t5_decoder_12_layers | ||
| random_t5_encoder | ||
| README.md | ||
| predict.bash | ||
| train.bash | ||
README.md
Train
What is this folder
Here contains the code for training and mapping evaluation.
Each folder contains a training variation.
After training, each folder contains the checkpoint files for each fold.
The folders are named with the following convention:
<method_type>_<model_type>_<prediction_type>_<included_fields>
e.g.
"classification_bert_complete_desc_unit",
which means: folder to perform classification using the bert model, predicting for the complete thing+property output using description and unit
To train, just run python train.py
The inference code is within a folder classification_prediction or
mapping_prediction.
Note: the classification_t5 folders are depracated in favor of the BERT-based classification models.