All Projects → luopeixiang → Im2latex

luopeixiang / Im2latex

Licence: mit
Pytorch implemention of Deep CNN Encoder + LSTM Decoder with Attention for Image to Latex

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Im2latex

Deeplearningmugenknock
でぃーぷらーにんぐを無限にやってディープラーニングでDeepLearningするための実装CheatSheet
Stars: ✭ 684 (+714.29%)
Mutual labels:  seq2seq
Hip Hop Seq2seq
DeeCamp 2018,AI有嘻哈 自动写歌词
Stars: ✭ 44 (-47.62%)
Mutual labels:  seq2seq
English2cypher
A model to transform english into Cypher queries, based off the CLEVR-graph dataset
Stars: ✭ 54 (-35.71%)
Mutual labels:  seq2seq
Neuralconvo
Neural conversational model in Torch
Stars: ✭ 773 (+820.24%)
Mutual labels:  seq2seq
Augmented seq2seq
enhance seq2seq model for open ended dialog generation
Stars: ✭ 29 (-65.48%)
Mutual labels:  seq2seq
Machine Translation
Stars: ✭ 51 (-39.29%)
Mutual labels:  seq2seq
Practical seq2seq
A simple, minimal wrapper for tensorflow's seq2seq module, for experimenting with datasets rapidly
Stars: ✭ 563 (+570.24%)
Mutual labels:  seq2seq
Xmunmt
An implementation of RNNsearch using TensorFlow
Stars: ✭ 69 (-17.86%)
Mutual labels:  seq2seq
Sockeye
Sequence-to-sequence framework with a focus on Neural Machine Translation based on Apache MXNet
Stars: ✭ 990 (+1078.57%)
Mutual labels:  seq2seq
Asr
Stars: ✭ 54 (-35.71%)
Mutual labels:  seq2seq
Seq2seq Signal Prediction
Signal forecasting with a Sequence-to-Sequence (seq2seq) Recurrent Neural Network (RNN) model in TensorFlow - Guillaume Chevalier
Stars: ✭ 890 (+959.52%)
Mutual labels:  seq2seq
Keras Question And Answering Web Api
Question answering system developed using seq2seq and memory network model in Keras
Stars: ✭ 21 (-75%)
Mutual labels:  seq2seq
Mxnet Seq2seq
Sequence to sequence learning with MXNET
Stars: ✭ 51 (-39.29%)
Mutual labels:  seq2seq
Cluener2020
CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition
Stars: ✭ 689 (+720.24%)
Mutual labels:  seq2seq
Sequence To Sequence 101
a series of tutorials on sequence to sequence learning, implemented with PyTorch.
Stars: ✭ 62 (-26.19%)
Mutual labels:  seq2seq
Seq2seq Pytorch
Sequence to Sequence Models with PyTorch
Stars: ✭ 678 (+707.14%)
Mutual labels:  seq2seq
Tensorflow Seq2seq Dialogs
Build conversation Seq2Seq models with TensorFlow
Stars: ✭ 43 (-48.81%)
Mutual labels:  seq2seq
Tensorflow seq2seq chatbot
Stars: ✭ 81 (-3.57%)
Mutual labels:  seq2seq
Ai Writer data2doc
PyTorch Implementation of NBA game summary generator.
Stars: ✭ 69 (-17.86%)
Mutual labels:  seq2seq
Pointer Networks Experiments
Sorting numbers with pointer networks
Stars: ✭ 53 (-36.9%)
Mutual labels:  seq2seq

Im2Latex

License

Deep CNN Encoder + LSTM Decoder with Attention for Image to Latex, the pytorch implemention of the model architecture used by the Seq2Seq for LaTeX generation

Sample results from this implemention

sample_result

Experimental results on the IM2LATEX-100K test dataset

BLUE-4 Edit Distance Exact Match
40.80 44.23 0.27

Getting Started

Install dependency:

pip install -r requirement.txt

Download the dataset for training:

cd data
wget http://lstm.seas.harvard.edu/latex/data/im2latex_validate_filter.lst
wget http://lstm.seas.harvard.edu/latex/data/im2latex_train_filter.lst
wget http://lstm.seas.harvard.edu/latex/data/im2latex_test_filter.lst
wget http://lstm.seas.harvard.edu/latex/data/formula_images_processed.tar.gz
wget http://lstm.seas.harvard.edu/latex/data/im2latex_formulas.norm.lst
tar -zxvf formula_images_processed.tar.gz

Preprocess:

python preprocess.py

Build vocab

python build_vocab.py

Train:

 python train.py \
      --data_path=[data dir] \
      --save_dir=[the dir for saving ckpts] \
      --dropout=0.2 --add_position_features \
      --epoches=25 --max_len=150

Evaluate:

python evaluate.py --split=test \
     --model_path=[the path to model] \
     --data_path=[data dir] \
     --batch_size=32 \
     --ref_path=[the file to store reference] \
     --result_path=[the file to store decoding result]

Features

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].