metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- generated_from_trainer
model-index:
- name: detr-resnet-50_finetuned_cppe5
results: []
detr-resnet-50_finetuned_cppe5
This model is a fine-tuned version of facebook/detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9955
- Map: 0.0411
- Map 50: 0.0772
- Map 75: 0.039
- Map Small: 0.0115
- Map Medium: 0.0697
- Map Large: 0.0393
- Mar 1: 0.1019
- Mar 10: 0.1856
- Mar 100: 0.2512
- Mar Small: 0.1753
- Mar Medium: 0.198
- Mar Large: 0.2287
- Map Coverall: 0.1697
- Mar 100 Coverall: 0.7308
- Map Face Shield: 0.0
- Mar 100 Face Shield: 0.0
- Map Gloves: 0.0142
- Mar 100 Gloves: 0.2446
- Map Goggles: 0.0
- Mar 100 Goggles: 0.0
- Map Mask: 0.0219
- Mar 100 Mask: 0.2805
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
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Map | Map 50 | Map 75 | Map Small | Map Medium | Map Large | Mar 1 | Mar 10 | Mar 100 | Mar Small | Mar Medium | Mar Large | Map Coverall | Mar 100 Coverall | Map Face Shield | Mar 100 Face Shield | Map Gloves | Mar 100 Gloves | Map Goggles | Mar 100 Goggles | Map Mask | Mar 100 Mask |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.5336 | 1.0 | 113 | 2.0865 | 0.0339 | 0.0619 | 0.0331 | 0.0065 | 0.0165 | 0.037 | 0.0787 | 0.1585 | 0.2087 | 0.0948 | 0.1537 | 0.2152 | 0.1504 | 0.6957 | 0.0 | 0.0 | 0.0028 | 0.1125 | 0.0 | 0.0 | 0.0165 | 0.2352 |
| 2.1741 | 2.0 | 226 | 1.9955 | 0.0411 | 0.0772 | 0.039 | 0.0115 | 0.0697 | 0.0393 | 0.1019 | 0.1856 | 0.2512 | 0.1753 | 0.198 | 0.2287 | 0.1697 | 0.7308 | 0.0 | 0.0 | 0.0142 | 0.2446 | 0.0 | 0.0 | 0.0219 | 0.2805 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1