mirror of https://github.com/wassname/Castor.git synced 2026-09-09 11:13:20 +08:00

Files

T

Achyudh Ram ed4f01852e Baseline LSTM implementation (#150 )

* 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

2018-10-11 03:04:23 -04:00

1.1 KiB

Raw Permalink Blame History

lstm_baseline

Implementation of a standard LSTM using PyTorch and Torchtext for text classification baseline measurements.

Model Type

rand: All words are randomly initialized and then modified during training.
static: A model with pre-trained vectors from word2vec. All words -- including the unknown ones that are initialized with zero -- are kept static and only the other parameters of the model are learned.
non-static: Same as above but the pretrained vectors are fine-tuned for each task.

Quick Start

To run the model on Reuters dataset on static, just run the following from the Castor working directory.

python -m lstm_baseline --mode static

Dataset

We experiment the model on the following datasets.

Reuters dataset - ModApte splits

Settings

Adadelta is used for training.

TODO

Support ONNX export. Currently throws a ONNX export failed (Couldn't export Python operator forward_flattened_wrapper) exception.
Add dataset results with different hyperparameters
Parameters tuning

1.1 KiB Raw Permalink Blame History