Hi, I have a question about the procedure for [fine-tuning a pre-trained object 
detection 
model](https://cv.gluon.ai/build/examples_detection/finetune_detection.html).

Does the described procedure modify all the weight values in the model?
With tensorflow, you have the option to "freeze" some of the weights, so that 
for example you can only fine-tune the fully connected layers at the end of the 
network, while keeping the first part of the model untouched.
Is there any way to do the same?





---
[Visit 
Topic](https://discuss.mxnet.apache.org/t/object-detection-fine-tuning-select-which-layers-are-modified/6726/1)
 or reply to this email to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click 
here](https://discuss.mxnet.apache.org/email/unsubscribe/55448bf9e584acc992a79f03357ffa92a3a21a957532fce6fd59c56a15ac8eb0).

Reply via email to