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: 0.9692307692307692

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: 0.2293
Accuracy: 0.9692

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: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.84	4	1.9335	0.1846
No log	1.84	8	1.8364	0.2615
No log	2.84	12	1.7054	0.3846
No log	3.84	16	1.5629	0.4154
2.0106	4.84	20	1.3907	0.4769
2.0106	5.84	24	1.1984	0.5692
2.0106	6.84	28	0.9519	0.6615
2.0106	7.84	32	0.7510	0.7846
2.0106	8.84	36	0.5749	0.8615
1.1009	9.84	40	0.4244	0.9385
1.1009	10.84	44	0.3652	0.8923
1.1009	11.84	48	0.2735	0.9538
1.1009	12.84	52	0.2909	0.8923
1.1009	13.84	56	0.2293	0.9692
0.6329	14.84	60	0.2563	0.9077
0.6329	15.84	64	0.2218	0.9231
0.6329	16.84	68	0.2102	0.9538
0.6329	17.84	72	0.1829	0.9231
0.6329	18.84	76	0.1992	0.9231
0.497	19.84	80	0.1814	0.9231
0.497	20.84	84	0.1807	0.9385
0.497	21.84	88	0.1765	0.9538
0.497	22.84	92	0.1868	0.9231
0.497	23.84	96	0.2089	0.9385
0.4198	24.84	100	0.1898	0.9385
0.4198	25.84	104	0.2065	0.9231
0.4198	26.84	108	0.1845	0.9231
0.4198	27.84	112	0.1724	0.9231
0.4198	28.84	116	0.1612	0.9385
0.368	29.84	120	0.1538	0.9538
0.368	30.84	124	0.1568	0.9538
0.368	31.84	128	0.1475	0.9692
0.368	32.84	132	0.1453	0.9538
0.368	33.84	136	0.1576	0.9692
0.3709	34.84	140	0.1430	0.9692
0.3709	35.84	144	0.1384	0.9692
0.3709	36.84	148	0.1432	0.9692
0.3709	37.84	152	0.1347	0.9692
0.3709	38.84	156	0.1359	0.9538
0.3373	39.84	160	0.1597	0.9538
0.3373	40.84	164	0.1522	0.9692
0.3373	41.84	168	0.1477	0.9538
0.3373	42.84	172	0.1480	0.9692
0.3373	43.84	176	0.1472	0.9692
0.3342	44.84	180	0.1473	0.9692
0.3342	45.84	184	0.1458	0.9692
0.3342	46.84	188	0.1529	0.9692
0.3342	47.84	192	0.1550	0.9692
0.3342	48.84	196	0.1494	0.9692
0.2914	49.84	200	0.1470	0.9692
0.2914	50.84	204	0.1460	0.9692
0.2914	51.84	208	0.1478	0.9692
0.2914	52.84	212	0.1481	0.9692
0.2914	53.84	216	0.1461	0.9692
0.2736	54.84	220	0.1458	0.9692
0.2736	55.84	224	0.1438	0.9692
0.2736	56.84	228	0.1427	0.9692
0.2736	57.84	232	0.1418	0.9692
0.2736	58.84	236	0.1401	0.9692
0.2589	59.84	240	0.1399	0.9692

Framework versions

Transformers 4.25.1
Pytorch 1.13.0+cu116
Datasets 2.8.0
Tokenizers 0.13.2