sars973/detr_finetuned_cppe5
029
<!-- 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 facebook/detr-resnet-101 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3489
- Map: 0.2197
- Map 50: 0.4408
- Map 75: 0.1896
- Map Small: 0.0734
- Map Medium: 0.1903
- Map Large: 0.3159
- Mar 1: 0.2516
- Mar 10: 0.4459
- Mar 100: 0.4733
- Mar Small: 0.191
- Mar Medium: 0.4214
- Mar Large: 0.6208
- Map Coverall: 0.4922
- Mar 100 Coverall: 0.6752
- Map Face Shield: 0.1239
- Mar 100 Face Shield: 0.4392
- Map Gloves: 0.1397
- Mar 100 Gloves: 0.4259
- Map Goggles: 0.0782
- Mar 100 Goggles: 0.42
- Map Mask: 0.2645
- Mar 100 Mask: 0.4062
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: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
- lrschedulertype: cosine
- num_epochs: 30
Training results
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0
