datamonster/ms-cond-detr-res-50-vehicles

<!-- 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. -->

ms-cond-detr-res-50-vehicles

This model is a fine-tuned version of datamonster/ms-cond-detr-res-50-vehicles on the None dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.8407
• —eval_map: 0.5078
• —evalmap50: 0.8475
• —evalmap75: 0.543
• —evalmapsmall: 0.1375
• —evalmapmedium: 0.5038
• —evalmaplarge: 0.7143
• —evalmar1: 0.2612
• —evalmar10: 0.5658
• —evalmar100: 0.6127
• —evalmarsmall: 0.3327
• —evalmarmedium: 0.6156
• —evalmarlarge: 0.7981
• —evalmapmotorbike: 0.3689
• —evalmar100_motorbike: 0.4835
• —evalmapcar: 0.5308
• —evalmar100_car: 0.6198
• —evalmapbus: 0.5808
• —evalmar100_bus: 0.6911
• —evalmapcontainer: 0.5506
• —evalmar100_container: 0.6566
• —eval_runtime: 144.8577
• —evalsamplesper_second: 15.898
• —evalstepsper_second: 1.988
• —epoch: 36.0
• —step: 82980

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: 0.0001
• —trainbatchsize: 4
• —evalbatchsize: 8
• —seed: 42
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosinewithrestarts
• —num_epochs: 60
• —mixedprecisiontraining: Native AMP

Framework versions

• —Transformers 4.45.1
• —Pytorch 2.4.0
• —Datasets 3.0.1
• —Tokenizers 0.20.0