Destroyed How to train a model? (markdown)

master
Coet 6 years ago
parent
commit
ba43d7e6b0
1 changed files with 0 additions and 11 deletions
  1. +0
    -11
      How-to-train-a-model?.md

+ 0
- 11
How-to-train-a-model?.md

@@ -1,11 +0,0 @@
1. Define a model, which is initialized with `args`.
[example](https://github.com/fastnlp/fastNLP/blob/743a6d75474fa393bc849c0392317c2c6bd868e4/fastNLP/models/sequence_modeling.py#L12)

2. Set model parameters in the config file. The parameters you set will be packed as `args` and used in model initialization.
[example](https://github.com/fastnlp/fastNLP/blob/743a6d75474fa393bc849c0392317c2c6bd868e4/reproduction/chinese_word_seg/cws.cfg#L1)

3. Write a script to use Trainer.
[example](https://github.com/fastnlp/fastNLP/blob/743a6d75474fa393bc849c0392317c2c6bd868e4/reproduction/chinese_word_seg/cws_train.py#L51)

#### Chinese Word Segmentation (CWS)
CWS data can be downloaded from [here](http://sighan.cs.uchicago.edu/bakeoff2005/).

Loading…
Cancel
Save