Pytorch model not learning

Autonomous Machines Jetson & Embedded Systems Jetson TX2
1

Hello,
I am running a model using transfer learning with pytorch in jupyter notebook on jetson tx2. However, the model is not learning at all keeping the accuracy same all the time. When I transferred the same code in google colab, it is working and learning as expected. Please help.
Thank you.

2

Hi,

It sounds that the transfer learning source may not support pyTorch model.
May I know which sample do you use first?

Thanks.

3

I am using densenet121 available in the torchvision models.

4

Hi,

densenet121 is a heavy model. TX2 may not have enough computing power for re-training the model.

Please noticed that Jetson platform is designed for fast inferencing.
It’s NOT suitable for training due the memory and bandwidth limitation.

Thanks.