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: 0.96875

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: 0.1835
Accuracy: 0.9688

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	0.89	4	2.0074	0.1562
No log	1.89	8	1.8896	0.25
No log	2.89	12	1.7421	0.4062
No log	3.89	16	1.5892	0.4375
1.973	4.89	20	1.3623	0.6094
1.973	5.89	24	1.1093	0.6094
1.973	6.89	28	0.7901	0.7812
1.973	7.89	32	0.5773	0.8438
1.973	8.89	36	0.3857	0.8906
1.0433	9.89	40	0.3254	0.9062
1.0433	10.89	44	0.2461	0.9219
1.0433	11.89	48	0.2340	0.9219
1.0433	12.89	52	0.1835	0.9688
1.0433	13.89	56	0.1779	0.9375
0.5842	14.89	60	0.1545	0.9531
0.5842	15.89	64	0.1487	0.9531
0.5842	16.89	68	0.1996	0.9219
0.5842	17.89	72	0.1619	0.9062
0.5842	18.89	76	0.1350	0.9688
0.4616	19.89	80	0.1706	0.9375
0.4616	20.89	84	0.1579	0.9219
0.4616	21.89	88	0.1630	0.9375
0.4616	22.89	92	0.2080	0.9062
0.4616	23.89	96	0.1463	0.9375
0.3898	24.89	100	0.1185	0.9688
0.3898	25.89	104	0.1445	0.9219
0.3898	26.89	108	0.2051	0.9219
0.3898	27.89	112	0.1928	0.9375
0.3898	28.89	116	0.1365	0.9375
0.3511	29.89	120	0.1057	0.9531
0.3511	30.89	124	0.1091	0.9531
0.3511	31.89	128	0.1894	0.9375
0.3511	32.89	132	0.1208	0.9531
0.3511	33.89	136	0.1101	0.9688
0.3286	34.89	140	0.1409	0.9375
0.3286	35.89	144	0.1830	0.9219
0.3286	36.89	148	0.1519	0.9219
0.3286	37.89	152	0.1031	0.9531
0.3286	38.89	156	0.0962	0.9688
0.3095	39.89	160	0.0903	0.9688
0.3095	40.89	164	0.0886	0.9688
0.3095	41.89	168	0.1033	0.9688
0.3095	42.89	172	0.1117	0.9531
0.3095	43.89	176	0.1192	0.9375
0.3056	44.89	180	0.0984	0.9531
0.3056	45.89	184	0.0820	0.9531
0.3056	46.89	188	0.0857	0.9531
0.3056	47.89	192	0.1058	0.9531
0.3056	48.89	196	0.1163	0.9375
0.255	49.89	200	0.1121	0.9531
0.255	50.89	204	0.1004	0.9688
0.255	51.89	208	0.0954	0.9688
0.255	52.89	212	0.0925	0.9688
0.255	53.89	216	0.0892	0.9688
0.2494	54.89	220	0.0893	0.9688
0.2494	55.89	224	0.0901	0.9688
0.2494	56.89	228	0.0896	0.9688
0.2494	57.89	232	0.0903	0.9688
0.2494	58.89	236	0.0913	0.9688
0.2588	59.89	240	0.0918	0.9688

Framework versions

Transformers 4.25.1
Pytorch 1.13.0+cu116
Datasets 2.8.0
Tokenizers 0.13.2