You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mxnet.apache.org by jx...@apache.org on 2017/11/02 23:44:15 UTC

[incubator-mxnet] branch master updated: Correct Initialization Description in Finetune Tutorial. (#8517)

This is an automated email from the ASF dual-hosted git repository.

jxie pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-mxnet.git


The following commit(s) were added to refs/heads/master by this push:
     new 396943e  Correct Initialization Description in Finetune Tutorial. (#8517)
396943e is described below

commit 396943e22661f03867d103d134416541e7e4f2bb
Author: lou-k <lo...@curalate.com>
AuthorDate: Thu Nov 2 19:44:12 2017 -0400

    Correct Initialization Description in Finetune Tutorial. (#8517)
---
 docs/faq/finetune.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/docs/faq/finetune.md b/docs/faq/finetune.md
index 6c49656..533c3ca 100644
--- a/docs/faq/finetune.md
+++ b/docs/faq/finetune.md
@@ -145,8 +145,8 @@ def get_fine_tune_model(symbol, arg_params, num_classes, layer_name='flatten0'):
     return (net, new_args)
 ```
 
-Now we create a module. We first call `init_params` to randomly initialize parameters, next use `set_params` to replace all parameters except for the last fully-connected layer with pretrained model.
-
+Now we create a module. Note we pass the existing parameters from the loaded model via the `arg_params` argument.
+The parameters of the last fully-connected layer will be randomly initialized by the `initializer`.
 
 ```python
 import logging

-- 
To stop receiving notification emails like this one, please contact
['"commits@mxnet.apache.org" <co...@mxnet.apache.org>'].