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: 0.9846153846153847

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: 0.1296
Accuracy: 0.9846

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	1.8199	0.3231
No log	1.84	8	1.7275	0.4154
No log	2.84	12	1.6281	0.4615
No log	3.84	16	1.5272	0.4615
1.9537	4.84	20	1.3668	0.5077
1.9537	5.84	24	1.0964	0.6
1.9537	6.84	28	0.7691	0.7846
1.9537	7.84	32	0.6370	0.8308
1.9537	8.84	36	0.4329	0.9077
1.0682	9.84	40	0.3518	0.9077
1.0682	10.84	44	0.3229	0.8923
1.0682	11.84	48	0.2324	0.9385
1.0682	12.84	52	0.2369	0.9385
1.0682	13.84	56	0.2119	0.9385
0.6335	14.84	60	0.1805	0.9385
0.6335	15.84	64	0.2135	0.9077
0.6335	16.84	68	0.1889	0.9231
0.6335	17.84	72	0.1601	0.9538
0.6335	18.84	76	0.1412	0.9692
0.5133	19.84	80	0.1497	0.9538
0.5133	20.84	84	0.1545	0.9538
0.5133	21.84	88	0.1298	0.9538
0.5133	22.84	92	0.1415	0.9538
0.5133	23.84	96	0.1685	0.9231
0.4383	24.84	100	0.1381	0.9385
0.4383	25.84	104	0.1296	0.9846
0.4383	26.84	108	0.1107	0.9538
0.4383	27.84	112	0.1237	0.9385
0.4383	28.84	116	0.1366	0.9538
0.4149	29.84	120	0.1349	0.9692
0.4149	30.84	124	0.1046	0.9846
0.4149	31.84	128	0.0882	0.9846
0.4149	32.84	132	0.1022	0.9846
0.4149	33.84	136	0.1207	0.9692
0.3657	34.84	140	0.1168	0.9538
0.3657	35.84	144	0.0922	0.9846
0.3657	36.84	148	0.0931	0.9846
0.3657	37.84	152	0.1006	0.9692
0.3657	38.84	156	0.0987	0.9692
0.3294	39.84	160	0.1128	0.9692
0.3294	40.84	164	0.1152	0.9538
0.3294	41.84	168	0.0997	0.9538
0.3294	42.84	172	0.0968	0.9692
0.3294	43.84	176	0.0819	0.9846
0.3198	44.84	180	0.0729	0.9846
0.3198	45.84	184	0.0744	0.9846
0.3198	46.84	188	0.0951	0.9692
0.3198	47.84	192	0.0966	0.9692
0.3198	48.84	196	0.0833	0.9846
0.2936	49.84	200	0.0694	0.9846
0.2936	50.84	204	0.0691	0.9846
0.2936	51.84	208	0.0736	0.9846
0.2936	52.84	212	0.0805	0.9692
0.2936	53.84	216	0.0801	0.9846
0.3127	54.84	220	0.0826	0.9846
0.3127	55.84	224	0.0857	0.9692
0.3127	56.84	228	0.0864	0.9846
0.3127	57.84	232	0.0878	0.9846
0.3127	58.84	236	0.0877	0.9846
0.285	59.84	240	0.0874	0.9846

Framework versions

Transformers 4.25.1
Pytorch 1.13.0+cu116
Datasets 2.8.0
Tokenizers 0.13.2