[GitHub] shuokay opened a new issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file?

[GitBox <gi...@apache.org>]

shuokay opened a new issue #8623: How to set different learning rate to different layers with pretained model which only have symbols json file and params file?
URL: https://github.com/apache/incubator-mxnet/issues/8623
 
 
   Model downloaded from model zoo only have symbol json file and model params file. I know one way of setting different learning rate in python file for example:
   ```python
   c1 = mx.sym.Convolution(data, kernel=(3,3), num_filter=16, name="c1", attr={"lr_mult": "0.01"})
   ```
   However, the pretrained model dont have symbol  python file, so how can I set `lr_muli` attribute to it.
   I think `net.get_internals()` may help, but it doesn't get the `c1` symbol but `c1_weights` and `c1_vias`

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


With regards,
Apache Git Services