segformer-b5-finetuned-human-parsing

模型介绍

This model is a fine-tuned version of nvidia/mit-b5 on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.2292 - Mean Iou: 0.6258 - Mean Accuracy: 0.7547 - Overall Accuracy: 0.8256 - Accuracy Background: nan - Accuracy Hat: 0.8561 - Accuracy Hair: 0.8974 - Accuracy Sunglasses: 0.7540 - Accuracy Upper-clothes: 0.8553 - Accuracy Skirt: 0.7026 - Accuracy Pants: 0.8913 - Accuracy Dress: 0.7525 - Accuracy Belt: 0.4251 - Accuracy Left-shoe: 0.6014 - Accuracy Right-shoe: 0.6374 - Accuracy Face: 0.9094 - Accuracy Left-leg: 0.8452 - Accuracy Right-leg: 0.8343 - Accuracy Left-arm: 0.8506 - Accuracy Right-arm: 0.8287 - Accuracy Bag: 0.8232 - Accuracy Scarf: 0.3662 - Iou Background: 0.0 - Iou Hat: 0.7625 - Iou Hair: 0.8171 - Iou Sunglasses: 0.6400 - Iou Upper-clothes: 0.7700 - Iou Skirt: 0.6211 - Iou Pants: 0.7788 - Iou Dress: 0.5512 - Iou Belt: 0.3564 - Iou Left-shoe: 0.5032 - Iou Right-shoe: 0.5381 - Iou Face: 0.8294 - Iou Left-leg: 0.7412 - Iou Right-leg: 0.7591 - Iou Left-arm: 0.7579 - Iou Right-arm: 0.7705 - Iou Bag: 0.7729 - Iou Scarf: 0.2956 The following hyperparameters were used during training: - learning_rate: 6e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 15

主要特点

特点摘要待依据来源补齐，不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价，不将渠道价格视为厂商官方统一价格。

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

常见问题

资料来源与可追溯记录

许可证：other。模型介绍与第三方评测均以原来源的具体版本和方法为准。