metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: delivery_truck_classification
    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: 0.9814814814814815

delivery_truck_classification

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: 0.1169
Accuracy: 0.9815

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	0.8	3	1.7556	0.2037
No log	1.8	6	1.5833	0.3704
No log	2.8	9	1.3483	0.5926
No log	3.8	12	1.1101	0.6667
No log	4.8	15	0.9116	0.7222
No log	5.8	18	0.7632	0.7407
1.7322	6.8	21	0.6118	0.7963
1.7322	7.8	24	0.5017	0.8519
1.7322	8.8	27	0.4241	0.8889
1.7322	9.8	30	0.3522	0.8704
1.7322	10.8	33	0.2918	0.9259
1.7322	11.8	36	0.2659	0.9259
1.7322	12.8	39	0.2587	0.9444
0.7462	13.8	42	0.2063	0.9259
0.7462	14.8	45	0.1870	0.9259
0.7462	15.8	48	0.1739	0.9630
0.7462	16.8	51	0.2043	0.9259
0.7462	17.8	54	0.1897	0.9259
0.7462	18.8	57	0.1764	0.9444
0.4232	19.8	60	0.1587	0.9444
0.4232	20.8	63	0.1556	0.9630
0.4232	21.8	66	0.1516	0.9630
0.4232	22.8	69	0.1264	0.9630
0.4232	23.8	72	0.1180	0.9630
0.4232	24.8	75	0.1110	0.9630
0.4232	25.8	78	0.1232	0.9630
0.3571	26.8	81	0.1169	0.9815
0.3571	27.8	84	0.1051	0.9815
0.3571	28.8	87	0.0986	0.9630
0.3571	29.8	90	0.0937	0.9630
0.3571	30.8	93	0.0931	0.9630
0.3571	31.8	96	0.0932	0.9630
0.3571	32.8	99	0.0941	0.9630
0.3239	33.8	102	0.0920	0.9630
0.3239	34.8	105	0.0851	0.9630
0.3239	35.8	108	0.0828	0.9630
0.3239	36.8	111	0.0810	0.9630
0.3239	37.8	114	0.0801	0.9630
0.3239	38.8	117	0.0804	0.9630
0.3111	39.8	120	0.0807	0.9630

Framework versions

Transformers 4.24.0
Pytorch 1.12.1+cu113
Datasets 2.7.1
Tokenizers 0.13.2