metadata

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-DMAE-ex
    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: 0.45652173913043476

swinv2-tiny-patch4-window8-256-DMAE-ex

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: 1.2080
Accuracy: 0.4565

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: 0.02
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.86	3	26.2016	0.1739
No log	2.0	7	1.3785	0.4565
12.975	2.86	10	2.2855	0.4565
12.975	4.0	14	1.5437	0.4565
12.975	4.86	17	1.5017	0.3261
2.1282	6.0	21	1.5409	0.1087
2.1282	6.86	24	1.4040	0.4565
2.1282	8.0	28	1.2780	0.4565
1.554	8.86	31	1.2300	0.3261
1.554	10.0	35	1.3228	0.3261
1.554	10.86	38	1.2745	0.4565
1.3748	12.0	42	1.3724	0.3261
1.3748	12.86	45	1.3726	0.4565
1.3748	14.0	49	1.2891	0.3261
1.5315	14.86	52	1.2979	0.4565
1.5315	16.0	56	1.2272	0.4565
1.5315	16.86	59	1.2749	0.3261
1.351	18.0	63	1.2219	0.4565
1.351	18.86	66	1.2200	0.4565
1.2678	20.0	70	1.2278	0.3261
1.2678	20.86	73	1.2318	0.4565
1.2678	22.0	77	1.2102	0.4565
1.244	22.86	80	1.2466	0.3261
1.244	24.0	84	1.2103	0.4565
1.244	24.86	87	1.2067	0.4565
1.2585	26.0	91	1.2129	0.4565
1.2585	26.86	94	1.2110	0.4565
1.2585	28.0	98	1.2131	0.4565
1.2405	28.86	101	1.2072	0.4565
1.2405	30.0	105	1.2099	0.4565
1.2405	30.86	108	1.2115	0.4565
1.2134	32.0	112	1.2138	0.4565
1.2134	32.86	115	1.2095	0.4565
1.2134	34.0	119	1.2081	0.4565
1.1982	34.29	120	1.2080	0.4565

Framework versions

Transformers 4.36.2
Pytorch 2.1.2+cu118
Datasets 2.16.1
Tokenizers 0.15.0