Chouffe commented on a change in pull request #15340: [Clojure] Add fastText 
example
URL: https://github.com/apache/incubator-mxnet/pull/15340#discussion_r297296679
 
 

 ##########
 File path: contrib/clojure-package/examples/cnn-text-classification/README.md
 ##########
 @@ -49,6 +48,21 @@ and then run
 - `lein uberjar`
 - `java -Xms1024m -Xmx2048m -jar 
target/cnn-text-classification-0.1.0-SNAPSHOT-standalone.jar`
 
+## Usage with fastText
+
+Using fastText instead of glove is fairly straightforward, as the pretrained 
embedding format is very similar.
+
+Download the 'Simple English' pretrained wiki word vectors (text) from the 
fastText
+[site](https://fasttext.cc/docs/en/pretrained-vectors.html) and place them in 
the
+`data/fastText` directory.
+
+Then you can run training on a subset of examples through the repl using:
+```
+(train-convnet {:devs [(context/cpu 0)] :embedding-size 300 :batch-size 100 
:test-size 100 :num-epoch 10 :max-examples 1000 :pretrained-embedding 
:fastText})
 
 Review comment:
   Should we use `(context/default-context)` instead?

----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
 
For queries about this service, please contact Infrastructure at:
[email protected]


With regards,
Apache Git Services

Reply via email to