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: 0.9491525423728814

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: 0.1253
Accuracy: 0.9492

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	0.94	4	1.8882	0.1186
No log	1.94	8	1.6799	0.3559
No log	2.94	12	1.4260	0.5763
No log	3.94	16	1.1092	0.6780
1.7242	4.94	20	0.8653	0.7458
1.7242	5.94	24	0.6787	0.7797
1.7242	6.94	28	0.5506	0.8305
1.7242	7.94	32	0.4174	0.8814
1.7242	8.94	36	0.3643	0.8814
0.8337	9.94	40	0.2680	0.9322
0.8337	10.94	44	0.2705	0.8983
0.8337	11.94	48	0.2270	0.9153
0.8337	12.94	52	0.1790	0.9492
0.8337	13.94	56	0.1694	0.9322
0.493	14.94	60	0.1776	0.9153
0.493	15.94	64	0.1831	0.9322
0.493	16.94	68	0.1765	0.9322
0.493	17.94	72	0.1575	0.9322
0.493	18.94	76	0.1472	0.9322
0.3966	19.94	80	0.1360	0.9322
0.3966	20.94	84	0.1448	0.9492
0.3966	21.94	88	0.1658	0.9322
0.3966	22.94	92	0.1652	0.9322
0.3966	23.94	96	0.1565	0.9322
0.3645	24.94	100	0.1701	0.9322
0.3645	25.94	104	0.1830	0.9322
0.3645	26.94	108	0.1682	0.9322
0.3645	27.94	112	0.1410	0.9492
0.3645	28.94	116	0.1291	0.9492
0.3358	29.94	120	0.1248	0.9492
0.3358	30.94	124	0.1275	0.9492
0.3358	31.94	128	0.1257	0.9492
0.3358	32.94	132	0.1288	0.9492
0.3358	33.94	136	0.1246	0.9492
0.3049	34.94	140	0.1219	0.9492
0.3049	35.94	144	0.1224	0.9492
0.3049	36.94	148	0.1246	0.9492
0.3049	37.94	152	0.1243	0.9492
0.3049	38.94	156	0.1248	0.9492
0.2962	39.94	160	0.1253	0.9492

Framework versions

Transformers 4.25.1
Pytorch 1.13.0+cu116
Datasets 2.8.0
Tokenizers 0.13.2