Sa3ed99/detr_finetuned_cppe5
011
<!-- 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. -->
detrfinetunedcppe5
This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3407
- Map: 0.2599
- Map 50: 0.5107
- Map 75: 0.2411
- Map Small: 0.1265
- Map Medium: 0.2152
- Map Large: 0.4809
- Mar 1: 0.2669
- Mar 10: 0.4141
- Mar 100: 0.4315
- Mar Small: 0.2471
- Mar Medium: 0.4009
- Mar Large: 0.7004
- Map Coverall: 0.5407
- Mar 100 Coverall: 0.6477
- Map Face Shield: 0.1688
- Mar 100 Face Shield: 0.4532
- Map Gloves: 0.1974
- Mar 100 Gloves: 0.3344
- Map Goggles: 0.1266
- Mar 100 Goggles: 0.3415
- Map Mask: 0.266
- Mar 100 Mask: 0.3804
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: 5e-05
- trainbatchsize: 8
- evalbatchsize: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: cosine
- num_epochs: 30
Training results
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
