Skip to content

Commit

Permalink
add option table
Browse files Browse the repository at this point in the history
  • Loading branch information
lfuelling committed Aug 22, 2016
1 parent fef13dd commit 26ade08
Showing 1 changed file with 7 additions and 2 deletions.
9 changes: 7 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -101,10 +101,15 @@ _(Disclaimer: nonsensical responses have been removed.)_
th train.lua [-h / options]
```

Use the `--dataset NUMBER` option to control the size of the dataset. Training on the full dataset takes about 5h for a single epoch.

The model will be saved to `data/model.t7` after each epoch if it has improved (error decreased).

### Options (some, not all)
- `--opencl` use opencl for computation (requires [torch-cl](https://github.com/hughperkins/distro-cl))
- `--cuda` use cuda for computation
- `--gpu [index]` use the nth GPU for computation (eg. on a 2015 MacBook `--gpu 0` results in the Intel GPU being used while `--gpu 1` uses the far more powerful AMD GPU)
- `-- dataset [size]` control the size of the dataset
- `--maxEpoch [amount]` specify the number of epochs to run

## Testing

To load the model and have a conversation:
Expand Down

0 comments on commit 26ade08

Please sign in to comment.