mrdbourke's picture
upload trashify object detection model with data augmentation
8b7b946 verified
|
raw
history blame
2.71 kB
metadata
library_name: transformers
license: apache-2.0
base_model: microsoft/conditional-detr-resnet-50
tags:
  - generated_from_trainer
model-index:
  - name: detr_finetuned_trashify_box_detector_with_data_aug
    results: []

detr_finetuned_trashify_box_detector_with_data_aug

This model is a fine-tuned version of microsoft/conditional-detr-resnet-50 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.0749

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 25
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
36.0329 1.0 50 3.4510
2.8564 2.0 100 2.2827
2.3323 3.0 150 2.1028
2.1202 4.0 200 1.8915
1.9452 5.0 250 1.6696
1.7582 6.0 300 1.5181
1.6291 7.0 350 1.4310
1.5394 8.0 400 1.3669
1.4751 9.0 450 1.3164
1.3906 10.0 500 1.2860
1.394 11.0 550 1.2915
1.338 12.0 600 1.2461
1.3071 13.0 650 1.2300
1.2772 14.0 700 1.2059
1.2363 15.0 750 1.1639
1.2213 16.0 800 1.1547
1.1372 17.0 850 1.1213
1.1423 18.0 900 1.1322
1.0991 19.0 950 1.1069
1.1041 20.0 1000 1.1001
1.0921 21.0 1050 1.0869
1.063 22.0 1100 1.0760
1.0561 23.0 1150 1.0775
1.0373 24.0 1200 1.0799
1.0325 25.0 1250 1.0749

Framework versions

  • Transformers 4.45.0.dev0
  • Pytorch 2.4.0+cu124
  • Datasets 2.21.0
  • Tokenizers 0.19.1