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: 1.9388
- Map: 0.0646
- Map 50: 0.115
- Map 75: 0.0653
- Map Small: 0.0067
- Map Medium: 0.0637
- Map Large: 0.0632
- Mar 1: 0.0913
- Mar 10: 0.2065
- Mar 100: 0.2581
- Mar Small: 0.1571
- Mar Medium: 0.2236
- Mar Large: 0.2439
- Map Coverall: 0.2825
- Mar 100 Coverall: 0.6822
- Map Face Shield: 0.0069
- Mar 100 Face Shield: 0.0113
- Map Gloves: 0.0224
- Mar 100 Gloves: 0.2854
- Map Goggles: 0.0
- Mar 100 Goggles: 0.0
- Map Mask: 0.011
- Mar 100 Mask: 0.3116
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2.6043 | 1.0 | 107 | 2.0664 | 0.0555 | 0.0964 | 0.0513 | 0.0042 | 0.0444 | 0.0583 | 0.0737 | 0.1675 | 0.235 | 0.1427 | 0.199 | 0.2195 | 0.261 | 0.6383 | 0.0007 | 0.0097 | 0.0101 | 0.2382 | 0.0 | 0.0 | 0.0059 | 0.2889 |
| 2.077 | 2.0 | 214 | 1.9388 | 0.0646 | 0.115 | 0.0653 | 0.0067 | 0.0637 | 0.0632 | 0.0913 | 0.2065 | 0.2581 | 0.1571 | 0.2236 | 0.2439 | 0.2825 | 0.6822 | 0.0069 | 0.0113 | 0.0224 | 0.2854 | 0.0 | 0.0 | 0.011 | 0.3116 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1