JEdward7777's picture
update model card README.md
758f5f2
|
raw
history blame
4.2 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: delivery_truck_classification
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: train
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 1

delivery_truck_classification

This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2212
  • Accuracy: 1.0

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: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 40

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.67 1 1.7282 0.3
No log 1.67 2 1.6786 0.3
No log 2.67 3 1.5811 0.35
No log 3.67 4 1.4410 0.45
No log 4.67 5 1.2802 0.65
No log 5.67 6 1.1453 0.75
No log 6.67 7 1.0253 0.75
No log 7.67 8 0.9306 0.75
No log 8.67 9 0.8566 0.8
No log 9.67 10 0.8048 0.8
No log 10.67 11 0.7585 0.8
No log 11.67 12 0.7097 0.8
No log 12.67 13 0.6443 0.8
No log 13.67 14 0.5772 0.8
No log 14.67 15 0.5056 0.8
No log 15.67 16 0.4444 0.8
No log 16.67 17 0.3857 0.85
No log 17.67 18 0.3330 0.85
No log 18.67 19 0.2907 0.9
1.4985 19.67 20 0.2552 0.95
1.4985 20.67 21 0.2212 1.0
1.4985 21.67 22 0.1938 1.0
1.4985 22.67 23 0.1699 1.0
1.4985 23.67 24 0.1490 1.0
1.4985 24.67 25 0.1329 1.0
1.4985 25.67 26 0.1203 1.0
1.4985 26.67 27 0.1141 1.0
1.4985 27.67 28 0.1084 1.0
1.4985 28.67 29 0.1018 1.0
1.4985 29.67 30 0.0953 1.0
1.4985 30.67 31 0.0878 1.0
1.4985 31.67 32 0.0794 1.0
1.4985 32.67 33 0.0730 1.0
1.4985 33.67 34 0.0687 1.0
1.4985 34.67 35 0.0664 1.0
1.4985 35.67 36 0.0649 1.0
1.4985 36.67 37 0.0640 1.0
1.4985 37.67 38 0.0639 1.0
1.4985 38.67 39 0.0638 1.0
0.4842 39.67 40 0.0637 1.0

Framework versions

  • Transformers 4.21.2
  • Pytorch 1.12.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1