metadata
license: apache-2.0
base_model: facebook/detr-resnet-50
tags:
- object-detection
- vision
- generated_from_trainer
model-index:
- name: detr-resnet-50-base-coco
results: []
detr-resnet-50-base-coco
This model is a fine-tuned version of facebook/detr-resnet-50 on the detection-datasets/coco dataset. It achieves the following results on the evaluation set:
- Loss: 6395.8599
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 4 | 6398.5435 |
| No log | 2.0 | 8 | 6397.9766 |
| 6175.8828 | 3.0 | 12 | 6397.4253 |
| 6175.8828 | 4.0 | 16 | 6396.9629 |
| 6292.3258 | 5.0 | 20 | 6396.5718 |
| 6292.3258 | 6.0 | 24 | 6396.2788 |
| 6292.3258 | 7.0 | 28 | 6396.0767 |
| 6230.4844 | 8.0 | 32 | 6395.9600 |
| 6230.4844 | 9.0 | 36 | 6395.8672 |
| 6089.8695 | 10.0 | 40 | 6395.8599 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.0+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3