julia-wenkmann/segformer-b1-finetuned-tennisdata

<!-- 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. -->

segformer-b1-finetuned-tennisdata

This model is a fine-tuned version of nvidia/mit-b0 on the julia-wenkmann/TennisSegmentation dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.0158
• —evalmeaniou: 0.4994
• —evalmeanaccuracy: 0.6483
• —evaloverallaccuracy: 0.9915
• —evalaccuracyundefined: nan
• —evalaccuracyobject: nan
• —evalaccuracyball: 0.0
• —evalaccuracyplayerTop: 0.7071
• —evalaccuracyplayerBottom: 0.8904
• —evalaccuracycourt: 0.9956
• —evaliouundefined: 0.0
• —evaliouobject: nan
• —evaliouball: 0.0
• —evaliouplayerTop: 0.7071
• —evaliouplayerBottom: 0.7968
• —evalioucourt: 0.9931
• —eval_runtime: 8.2745
• —evalsamplesper_second: 2.175
• —evalstepsper_second: 1.088
• —epoch: 29.41
• —step: 1000

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: 6e-05
• —trainbatchsize: 2
• —evalbatchsize: 2
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —num_epochs: 100

Framework versions

• —Transformers 4.35.2
• —Pytorch 2.1.0+cu121
• —Datasets 2.17.1
• —Tokenizers 0.15.2