metadata

library_name: transformers
license: apache-2.0
base_model: microsoft/swinv2-tiny-patch4-window8-256
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swinv2-tiny-patch4-window8-256-Ocular-Toxoplasmosis
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.8387096774193549

swinv2-tiny-patch4-window8-256-Ocular-Toxoplasmosis

This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window8-256 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.5167
Accuracy: 0.8387

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	0.7273	2	1.4057	0.2419
No log	1.8182	5	1.2100	0.4677
No log	2.9091	8	1.1808	0.4516
1.3062	4.0	11	1.0975	0.5968
1.3062	4.7273	13	1.0542	0.6613
1.3062	5.8182	16	0.9857	0.6613
1.3062	6.9091	19	0.9176	0.6774
1.0003	8.0	22	0.8761	0.6774
1.0003	8.7273	24	0.8540	0.6774
1.0003	9.8182	27	0.7777	0.6613
0.8096	10.9091	30	0.7498	0.6613
0.8096	12.0	33	0.7569	0.6613
0.8096	12.7273	35	0.7422	0.6774
0.8096	13.8182	38	0.7278	0.7097
0.6556	14.9091	41	0.6877	0.7258
0.6556	16.0	44	0.6433	0.7258
0.6556	16.7273	46	0.6324	0.7419
0.6556	17.8182	49	0.6390	0.7419
0.5725	18.9091	52	0.6504	0.7742
0.5725	20.0	55	0.6145	0.7581
0.5725	20.7273	57	0.5824	0.7903
0.5057	21.8182	60	0.5476	0.8226
0.5057	22.9091	63	0.5413	0.8226
0.5057	24.0	66	0.5335	0.8226
0.5057	24.7273	68	0.5302	0.8226
0.4945	25.8182	71	0.5231	0.8226
0.4945	26.9091	74	0.5167	0.8387
0.4945	28.0	77	0.5132	0.8387
0.4945	28.7273	79	0.5131	0.8387
0.4883	29.0909	80	0.5131	0.8387

Framework versions

Transformers 4.44.2
Pytorch 2.4.1+cu121
Datasets 3.0.1
Tokenizers 0.19.1