Hi all, I am using mxnet to train landmark detectionusing my custom network (mx.gluon.nn.HybridSequential()). I trained it on widerface dataset that has 5 outputs. Now, I want to use the same network but different number of output likes 68 outputs (last FC layer) to finetune on my dataset. Is it possible ? How can I do it. Just using lenet arch as example
Related Topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Updating mxnet from 1.0.0, networks give different outputs | 4 | 499 | March 13, 2019 | |
Finetuning in MXNet for ConvNet blocks | 3 | 1770 | March 26, 2019 | |
Mxnet-tensorrt result different | 5 | 737 | November 6, 2018 | |
Mxnet model to train multiple different classes in a single annotated image
|
0 | 247 | December 14, 2020 | |
Running inference with varying input size
|
3 | 1124 | October 20, 2019 |