amnraw/finetune-instance-segmentation-posture

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

finetune-instance-segmentation-posture

This model is a fine-tuned version of facebook/mask2former-swin-tiny-coco-instance on the qubvel-hf/ade20k-mini dataset. It achieves the following results on the evaluation set:

• —Loss: 30.5625
• —Map: 0.2089
• —Map 50: 0.4081
• —Map 75: 0.1963
• —Map Small: 0.1412
• —Map Medium: 0.6277
• —Map Large: 0.8115
• —Mar 1: 0.0944
• —Mar 10: 0.25
• —Mar 100: 0.2879
• —Mar Small: 0.2137
• —Mar Medium: 0.7147
• —Mar Large: 0.8531
• —Map Person: 0.1381
• —Mar 100 Person: 0.2036
• —Map Car: 0.2797
• —Mar 100 Car: 0.3722

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 1e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 16
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: constant
• —num_epochs: 2.0
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.47.0.dev0
• —Pytorch 2.3.1+cu121
• —Datasets 3.0.2
• —Tokenizers 0.20.1