osmanh/nvidia-mit-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. -->

nvidia-mit-human_parsing-finetuned

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

• —Loss: 0.4281
• —Mean Iou: 0.1550
• —Mean Accuracy: 0.1965
• —Overall Accuracy: 0.4227
• —Accuracy Background: nan
• —Accuracy Hat: 0.0
• —Accuracy Hair: 0.3297
• —Accuracy Sunglasses: 0.0
• —Accuracy Upper-clothes: 0.7034
• —Accuracy Skirt: 0.5732
• —Accuracy Pants: 0.5945
• —Accuracy Dress: 0.5303
• —Accuracy Belt: 0.0
• —Accuracy Left-shoe: 0.0
• —Accuracy Right-shoe: 0.0
• —Accuracy Face: 0.3038
• —Accuracy Left-leg: 0.0925
• —Accuracy Right-leg: 0.1645
• —Accuracy Left-arm: 0.0025
• —Accuracy Right-arm: 0.0403
• —Accuracy Bag: 0.0054
• —Accuracy Scarf: 0.0
• —Iou Background: 0.0
• —Iou Hat: 0.0
• —Iou Hair: 0.2795
• —Iou Sunglasses: 0.0
• —Iou Upper-clothes: 0.5617
• —Iou Skirt: 0.4270
• —Iou Pants: 0.5179
• —Iou Dress: 0.4082
• —Iou Belt: 0.0
• —Iou Left-shoe: 0.0
• —Iou Right-shoe: 0.0
• —Iou Face: 0.2943
• —Iou Left-leg: 0.0917
• —Iou Right-leg: 0.1613
• —Iou Left-arm: 0.0025
• —Iou Right-arm: 0.0402
• —Iou Bag: 0.0053
• —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