Ben Chuanlong Du's Blog

It is never too late to learn.

Delete a Layer in a Pretrained Model in PyTorch

It is common to customize a pretrained model by delete the output layer or replace it to the output layer that suits your use case. There are several ways to achieve this in PyTorch.

Replace the Fully Connected Layer with an Identity Layer

  1. Define an identity layer.

  2. Replace the fully connected layer with an Identity Layer (using ResNet18 as an example).

Save and Load PyTorch Models

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

  1. PyTorch uses pickle to serialize and deserialize objects.

  2. The PyTorch convention is to use the file extension .pt or .pth for saving model (or its parameters) and use the file extension …

Tips on Deep Graph Learning

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

https://github.com/dmlc/dgl

Tips on Speechlogger

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

  1. You can configure the source of voice of SpeechLogger.

    SpeechLogger