This model consists of an SMP-UNet trained on the LSDB dataset in December 2023 for GelGenie. It should only be used for low-resolution images.
The model was trained on both the training and validation set for 600 epochs and the final checkpoint extracted (total of 59 images).
Its performance is slightly worse than the other low resolution model available despite the extended dataset it was trained on.
For more details on the configuration used for training, please visit https://huggingface.co/mattaq/GelGenie-LowRes-Extended-Dec-2023 and check the config.toml file. Our codebase is fully open-sourced and is available here: https://github.com/mattaq31/GelGenie.
Inference API (serverless) does not yet support pytorch models for this pipeline type.