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-sealv1
    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: 0.9793103448275862

swin-tiny-patch4-window7-224-finetuned-sealv1

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: 0.0650
Accuracy: 0.9793

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: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.95	5	1.2920	0.4966
1.1379	1.9	10	1.0177	0.4966
1.1379	2.86	15	0.7626	0.8759
0.6784	4.0	21	0.5388	0.9310
0.6784	4.95	26	0.4191	0.9103
0.3269	5.9	31	0.3990	0.8897
0.3269	6.86	36	0.2090	0.9517
0.2068	8.0	42	0.1819	0.9586
0.2068	8.95	47	0.1192	0.9655
0.1104	9.9	52	0.0682	0.9724
0.1104	10.86	57	0.0854	0.9724
0.0571	12.0	63	0.0816	0.9655
0.0571	12.95	68	0.0535	0.9793
0.0382	13.9	73	0.0491	0.9793
0.0382	14.86	78	0.0534	0.9793
0.0158	16.0	84	0.0369	0.9793
0.0158	16.95	89	0.1111	0.9724
0.0082	17.9	94	0.0515	0.9862
0.0082	18.86	99	0.0713	0.9793
0.0105	20.0	105	0.0598	0.9793
0.009	20.95	110	0.0759	0.9724
0.009	21.9	115	0.0769	0.9793
0.0134	22.86	120	0.0702	0.9793
0.0134	24.0	126	0.0605	0.9793
0.0042	24.95	131	0.0621	0.9793
0.0042	25.9	136	0.0654	0.9793
0.0027	26.86	141	0.0666	0.9724
0.0027	28.0	147	0.0665	0.9793
0.0065	28.57	150	0.0650	0.9793

Framework versions

Transformers 4.38.2
Pytorch 1.10.2+cu113
Datasets 2.18.0
Tokenizers 0.15.2