mirror of
https://github.com/wassname/Castor.git
synced 2026-09-13 12:11:12 +08:00
Achyudh Ram
cc275f6bde
* Add ReutersTrainer, ReutersEvaluator options in Factory classes * Add Reuters to Kim-CNN command line arguments * Fix SST dataset path according to changes in Kim-CNN args The dataset path in args.py was made to point at the dataset folder rather than dataset/SST folder. Hence SST folder was added to paths in the SST dataset class * Add Reuters dataset class, and support in __main__ * Add Reuters dataset trainers and evaluators * Remove debug print statement in reuters_evaluator * Fix rounding bug in reuters_trainer and reuters_evaluator * Add LSTM for baseline text classification measurements * Add eval metrics for lstm_baseline * Set batch_first param in lstm_baseline * Remove onnx args from lstm_baseline * Pack padded sequences in LSTM_baseline * Add TensorBoardX support for Reuters trainer * Add Arxiv Academic Paper Dataset (AAPD) * Add Hidden Bottleneck Layer to BiLSTM * Fix packing of padded tensors in Reuters * Add cmdline args for Hidden Bottleneck Layer for BiLSTM * Include pre-padding lengths in AAPD dataset * Remove duplication of preprocessing code in AAPD * Remove batch_size condition in ReutersTrainer * Add ignore_lengths option to ReutersTrainer and ReutersEvaluator * Add AAPDCharQuantized and ReutersCharQuantized * Rename Reuters_hierarchical to ReutersHierarchical * Add CharacterCNN for document classification * Update README.md for CharacterCNN * Fix table in README.md for CharacterCNN * Add AAPDHierarchical for HAN * Update HAN for changes in Reuters dataset endpoints * Fix bug in CharCNN when running on CPU
54 lines
1.4 KiB
Markdown
54 lines
1.4 KiB
Markdown
## Character-level Convolutional Network
|
||
|
||
Implementation of Char-CNN from Character-level Convolutional Networks for Text Classification (http://papers.nips.cc/paper/5782-character-level-convolutional-networks-for-text-classification.pdf)
|
||
|
||
## Quick Start
|
||
|
||
To run the model on Reuters dataset, just run the following from the Castor working directory:
|
||
|
||
```
|
||
python -m char_cnn --dataset Reuters --gpu 1 --batch_size 128 --lr 0.001
|
||
```
|
||
|
||
To test the model, you can use the following command.
|
||
|
||
```
|
||
python -m char_cnn --trained_model kim_cnn/saves/Reuters/best_model.pt
|
||
```
|
||
|
||
## Dataset
|
||
|
||
We experiment the model on the following datasets.
|
||
|
||
- Reuters Newswire (RCV-1)
|
||
- Arxiv Academic Paper Dataset (AAPD)
|
||
|
||
## Settings
|
||
|
||
Adam is used for training.
|
||
|
||
## Dataset Results
|
||
|
||
### RCV-1
|
||
```
|
||
python -m char_cnn --dataset Reuters --gpu 1 --batch_size 128 --lr 0.001
|
||
```
|
||
| Accuracy | Avg. Precision | Avg. Recall | Avg. F1
|
||
-- | -- | -- | -- | --
|
||
Char-CNN (Dev) | 0.585 | 0.702 | 0.569 | 0.628
|
||
Char-CNN (Test) | 0.589 | 0.691 | 0.552 | 0.614
|
||
|
||
### AAPD
|
||
```
|
||
python -m char_cnn --dataset AAPD --gpu 1 --batch_size 128 --lr 0.001
|
||
```
|
||
| Accuracy | Avg. Precision | Avg. Recall | Avg. F1
|
||
-- | -- | -- | -- | --
|
||
Char-CNN (Dev) | 0.305 | 0.681 | 0.537 | 0.600
|
||
Char-CNN (Test) | 0.294 | 0.681 | 0.526 | 0.593
|
||
|
||
## TODO
|
||
- Support ONNX export. Currently throws a ONNX export failed (Couldn't export Python operator forward_flattened_wrapper) exception.
|
||
- Parameters tuning
|
||
|