Multiprocessing Issues in Docker

Apr 20, 2020

PyTorch Specific¶

Using num_workers > 0 for a DataLoader in Docker might causes issues ...

MULTIPROCESSING BEST PRACTICES

Runtime Error with DataLoader: exited unexpectedly #5301

https://forums.fast.ai/t/runtimeerror-dataloader-worker-pid-137-is-killed-by-signal-bus-error/27095

https://github.com/pytorch/pytorch/issues/2244

Get the Number of Cores in macOS

Apr 16, 2020

Using Shell Command¶

Delete a Layer in a Pretrained Model in PyTorch

Apr 16, 2020

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¶

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

Save and Load PyTorch Models

Apr 09, 2020

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

PyTorch uses pickle to serialize and deserialize objects.
The PyTorch convention is to use the file extension .pt or .pth for saving model (or its parameters) and use the file extension …