Check the availability of pruning for DINO, SegFormer and Classification of pyt

[hoin.na]

Please provide the following information when requesting support.

• Hardware (T4/V100/Xavier/Nano/etc)
• Network Type (Detectnet_v2/Faster_rcnn/Yolo_v4/LPRnet/Mask_rcnn/Classification/etc)
• TLT Version (Please run “tlt info --verbose” and share “docker_tag” here)
• Training spec file(If have, please share here)
• How to reproduce the issue ? (This is for errors. Please share the command line and the detailed log here.)

For the above base models, I have tried to prune trained model, but there is no option to prune. I want to make sure whether TAO 5.0 supports prune for Vision Transformer models or not.
Thanks.

[Morganh]

These networks(DINO, SegFormer and Classification of pyt) do not support pruning yet.

[hoin.na]

Thank you for your reply.
Since I want to prune PyTorch model for optimization after training, could you let me know the expected released schedule for supporting pruning of PyTorch Model on TAO?

[Morganh]

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

Actually some networks in pytorch docker can support pruning. For example, ocrnet. But DINO, SegFormer and Classification of pyt do not support yet. For these models, will sync with internal team about the feature.