CodePlay2016 commented on issue #11794: fail to quantize custom symbols 
exported from hybrid block
URL: 
https://github.com/apache/incubator-mxnet/issues/11794#issuecomment-406517323
 
 
   @reminisce In fact that quantized symbol file is for another issue, sorry 
for the trouble. I have uploaded the related file to [Baidu 
Drive](https://pan.baidu.com/s/1hjJd3w1ehOB3ZSrWRDS7cQ)(the access key is 
`881o`) in the `symbol.rar` file. The original symbol and param files named 
`model_symbol-symbol.json` and `model_symbol-0000.params`, and the quantized 
symbol and param files named `model_symbol_quantized.json` and 
`model_symbol_quantized.param`. What's more, the gluon hybrid block model file 
is named `model`, whose architecture is defined in the script named `models.py` 
in my [repo](https://github.com/CodePlay2016/prune_mx_face). Thank you.

----------------------------------------------------------------
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:
[email protected]


With regards,
Apache Git Services

Reply via email to