Training LPRNet on custom dataset with 'O' character

• Hardware Platform: GPU
• DeepStream Version: 6.3
• TensorRT Version: 5.1
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type: questions

I would like to train LPRNet on a custom dataset, since the version available online doesn’t have letter ‘O’
Is it possible to reuse available weights to train the network on new dataset or will I have to start from scratch?

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

You can use the pretrained model from ngc.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.