phunc20's picture
update model card README.md
53d340c
|
raw
history blame
4.9 kB
metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-tiny-patch4-window7-224-finetuned-wuhan
    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

swin-tiny-patch4-window7-224-finetuned-wuhan

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: 0.0203
  • 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: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 50

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 3 0.6245 0.7778
No log 2.0 6 0.5321 0.7778
No log 3.0 9 0.5123 0.7778
0.6482 4.0 12 0.4956 0.7778
0.6482 5.0 15 0.4585 0.7778
0.6482 6.0 18 0.3743 0.8611
0.5574 7.0 21 0.2842 0.9167
0.5574 8.0 24 0.2125 0.9167
0.5574 9.0 27 0.2683 0.9167
0.4882 10.0 30 0.1316 0.9444
0.4882 11.0 33 0.1366 0.9444
0.4882 12.0 36 0.0745 0.9722
0.4882 13.0 39 0.1065 0.9444
0.0907 14.0 42 0.0477 0.9722
0.0907 15.0 45 0.0460 0.9444
0.0907 16.0 48 0.0438 0.9722
0.0481 17.0 51 0.0203 1.0
0.0481 18.0 54 0.0093 1.0
0.0481 19.0 57 0.0082 1.0
0.013 20.0 60 0.0017 1.0
0.013 21.0 63 0.0008 1.0
0.013 22.0 66 0.0002 1.0
0.013 23.0 69 0.0001 1.0
0.0101 24.0 72 0.0938 0.9722
0.0101 25.0 75 0.1019 0.9722
0.0101 26.0 78 0.0005 1.0
0.0085 27.0 81 0.0000 1.0
0.0085 28.0 84 0.0000 1.0
0.0085 29.0 87 0.0001 1.0
0.0196 30.0 90 0.0001 1.0
0.0196 31.0 93 0.0001 1.0
0.0196 32.0 96 0.0000 1.0
0.0196 33.0 99 0.0000 1.0
0.0027 34.0 102 0.0000 1.0
0.0027 35.0 105 0.0000 1.0
0.0027 36.0 108 0.0000 1.0
0.0016 37.0 111 0.0000 1.0
0.0016 38.0 114 0.0000 1.0
0.0016 39.0 117 0.0000 1.0
0.0021 40.0 120 0.0000 1.0
0.0021 41.0 123 0.0000 1.0
0.0021 42.0 126 0.0000 1.0
0.0021 43.0 129 0.0000 1.0
0.0024 44.0 132 0.0000 1.0
0.0024 45.0 135 0.0000 1.0
0.0024 46.0 138 0.0000 1.0
0.0009 47.0 141 0.0000 1.0
0.0009 48.0 144 0.0000 1.0
0.0009 49.0 147 0.0000 1.0
0.0006 50.0 150 0.0000 1.0

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.1
  • Tokenizers 0.13.3