happy8825/siglip_classification_result_bestcheckpoint_20251217_003311
收藏数据链接:
官方服务:
资源简介:
# SigLIP Classification Eval - Model: /hub_data3/seohyun/outputs/siglip_ecva/best - Test repo: happy8825/siglip_test (split: train) - Samples visualized: 50 of 924 ## Metrics - accuracy: 0.6732 - f1: 0.7051 - total: 924, correct: 622 ## Confusion Matrix 
# SigLIP分类评估(SigLIP Classification Eval) - 模型:/hub_data3/seohyun/outputs/siglip_ecva/best - 测试仓库:happy8825/siglip_test(拆分集:训练集) - 可视化样本:924个样本中的50个 ## 评估指标 - 准确率(Accuracy):0.6732 - F1值(F1):0.7051 - 总样本数:924,分类正确样本数:622 ## 混淆矩阵 
提供机构:
happy8825


