osmanh/RMBG-human_parsing-finetuned

<!-- 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. -->

RMBG-human_parsing-finetuned

This model is a fine-tuned version of briaai/RMBG-1.4 on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 0.7383
• —Mean Iou: 0.0018
• —Mean Accuracy: 0.0020
• —Overall Accuracy: 0.0085
• —Accuracy Background: nan
• —Accuracy Hat: 0.0
• —Accuracy Hair: 0.0000
• —Accuracy Sunglasses: 0.0
• —Accuracy Upper-clothes: 0.0310
• —Accuracy Skirt: 0.0
• —Accuracy Pants: 0.0035
• —Accuracy Dress: 0.0
• —Accuracy Belt: 0.0
• —Accuracy Left-shoe: 0.0
• —Accuracy Right-shoe: 0.0
• —Accuracy Face: 0.0
• —Accuracy Left-leg: 0.0
• —Accuracy Right-leg: 0.0
• —Accuracy Left-arm: 0.0
• —Accuracy Right-arm: 0.0
• —Accuracy Bag: 0.0
• —Accuracy Scarf: 0.0
• —Iou Background: 0.0
• —Iou Hat: 0.0
• —Iou Hair: 0.0000
• —Iou Sunglasses: 0.0
• —Iou Upper-clothes: 0.0296
• —Iou Skirt: 0.0
• —Iou Pants: 0.0035
• —Iou Dress: 0.0
• —Iou Belt: 0.0
• —Iou Left-shoe: 0.0
• —Iou Right-shoe: 0.0
• —Iou Face: 0.0
• —Iou Left-leg: 0.0
• —Iou Right-leg: 0.0
• —Iou Left-arm: 0.0
• —Iou Right-arm: 0.0
• —Iou Bag: 0.0
• —Iou Scarf: 0.0

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: 8
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —num_epochs: 20

Training results

Framework versions

• —Transformers 4.46.3
• —Pytorch 2.5.1+cu121
• —Datasets 3.2.0
• —Tokenizers 0.20.3