usamaaleem99tech's picture
update model card README.md
5b0319a
|
raw
history blame
No virus
2.91 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: segformer-class-classWeights-augmentation
    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

segformer-class-classWeights-augmentation

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: 0.0018
  • 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: 10
  • eval_batch_size: 10
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 40
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 0.89 6 0.9811 0.5862
1.0899 1.93 13 0.9601 0.5862
0.7599 2.96 20 0.8930 0.6897
0.7599 4.0 27 0.5230 0.7931
0.3436 4.89 33 0.1652 0.9310
0.1853 5.93 40 0.0544 1.0
0.1853 6.96 47 0.0937 0.9655
0.1839 8.0 54 0.0566 0.9655
0.1772 8.89 60 0.0084 1.0
0.1772 9.93 67 0.0114 1.0
0.1016 10.96 74 0.0039 1.0
0.1534 12.0 81 0.0038 1.0
0.1534 12.89 87 0.0187 0.9655
0.1256 13.93 94 0.0023 1.0
0.1234 14.96 101 0.0016 1.0
0.1234 16.0 108 0.0019 1.0
0.1129 16.89 114 0.0018 1.0
0.17 17.78 120 0.0018 1.0

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.13.3