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: 1.9677
- Map: 0.0546
- Map 50: 0.103
- Map 75: 0.0504
- Map Small: 0.0092
- Map Medium: 0.0513
- Map Large: 0.053
- Mar 1: 0.099
- Mar 10: 0.2024
- Mar 100: 0.2506
- Mar Small: 0.1343
- Mar Medium: 0.1925
- Mar Large: 0.2414
- Map Coverall: 0.233
- Mar 100 Coverall: 0.7017
- Map Face Shield: 0.0
- Mar 100 Face Shield: 0.0
- Map Gloves: 0.0047
- Mar 100 Gloves: 0.2792
- Map Goggles: 0.0
- Mar 100 Goggles: 0.0
- Map Mask: 0.0352
- Mar 100 Mask: 0.272
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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 107 | 2.0994 | 0.0445 | 0.0869 | 0.04 | 0.0045 | 0.0347 | 0.0464 | 0.0794 | 0.1672 | 0.2137 | 0.0881 | 0.1491 | 0.221 | 0.199 | 0.6589 | 0.0 | 0.0 | 0.0019 | 0.2107 | 0.0 | 0.0 | 0.0217 | 0.1989 |
| No log | 2.0 | 214 | 1.9677 | 0.0546 | 0.103 | 0.0504 | 0.0092 | 0.0513 | 0.053 | 0.099 | 0.2024 | 0.2506 | 0.1343 | 0.1925 | 0.2414 | 0.233 | 0.7017 | 0.0 | 0.0 | 0.0047 | 0.2792 | 0.0 | 0.0 | 0.0352 | 0.272 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1