amyeroberts's picture
amyeroberts HF staff
update model card README.md
477e70b
|
raw
history blame
2.34 kB
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: 6387.9546

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: 0.0002
  • 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: 20.0

Training results

Training Loss Epoch Step Validation Loss
No log 1.0 4 6394.3193
No log 2.0 8 6393.3564
6173.6062 3.0 12 6390.9482
6173.6062 4.0 16 6389.5869
6287.2859 5.0 20 6388.7280
6287.2859 6.0 24 6388.6221
6287.2859 7.0 28 6388.4399
6224.3344 8.0 32 6388.2119
6224.3344 9.0 36 6388.5449
6083.1363 10.0 40 6388.3262
6083.1363 11.0 44 6390.2056
6083.1363 12.0 48 6388.6606
6260.7426 13.0 52 6388.1484
6260.7426 14.0 56 6388.0479
6377.543 15.0 60 6388.0303
6377.543 16.0 64 6388.1338
6377.543 17.0 68 6388.0596
6318.3168 18.0 72 6388.0195
6318.3168 19.0 76 6387.9639
6258.2133 20.0 80 6387.9546

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.0+cu117
  • Datasets 2.13.1
  • Tokenizers 0.13.3