Unable to resume the training process

tobran / GALIP

[CVPR2023] A faster, smaller, and better text-to-image model for large-scale training

MIT License

225 stars 25 forks source link

Unable to resume the training process #23

Closed VinayHajare closed 6 months ago

VinayHajare commented 7 months ago

I am training the model on the CUB dataset using 1 GPU but due to some cause the training interrupted and when I configured it with state_epoch to the last epoch when the process is interrupted and I am confused that what should be the path of the pre-trained_path and log dir.

VinayHajare commented 6 months ago

Issue has been solved.