metadata

license: apache-2.0
base_model: microsoft/swin-base-patch4-window7-224
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: swin-base-patch4-window7-224-MM_Classification_base
    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: 0.8681177976952625

swin-base-patch4-window7-224-MM_Classification_base

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:

Loss: 0.3364
Accuracy: 0.8681

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: 128
eval_batch_size: 128
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 512
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.9771	1.0	19	0.5489	0.7913
0.4913	2.0	38	0.3562	0.8553
0.3633	3.0	57	0.3353	0.8668
0.3343	4.0	76	0.3177	0.8656
0.3096	5.0	95	0.3072	0.8758
0.2822	6.0	114	0.3213	0.8630
0.2749	7.0	133	0.3173	0.8643
0.2526	8.0	152	0.3110	0.8758
0.2405	9.0	171	0.3263	0.8758
0.2152	10.0	190	0.3268	0.8656
0.2226	11.0	209	0.3209	0.8732
0.2067	12.0	228	0.3289	0.8771
0.2019	13.0	247	0.3316	0.8745
0.195	14.0	266	0.3398	0.8732
0.1862	15.0	285	0.3364	0.8681

Framework versions

Transformers 4.43.3
Pytorch 1.13.1+cu117
Datasets 2.20.0
Tokenizers 0.19.1