Pytorch version of code completion with neural attention and pointer networks
- refactor preprocessing code
- add python to AST code
- config for preprocessing
- join training for type
- python3 >= 3.6
- torch >= 1.2, or tensorboadX for earlier versions
- pyyaml
- run
python3 preprocess.pyfor preprocessing - run
CUDA_VISIBLE_DEVICES=id python3 train.py --config=path/to/config.ymlfor training with specified config, list of available configscan be found at configs folder
| model | vocab_size 1k | vocab_size 10k | vocab_size 50k |
|---|---|---|---|
| simple_lstm | 66.33 | 65.7 | 61.68, 1 epoch |
| attn_lstm | 64.95 | 65.77 | 63.15, 1 epoch |
| pointer_mixture | 66.62 | 67.05 | 65.3, 3 epochs |
Here will be examples of code generation