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: 0.9466666666666667

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: 0.1463
Accuracy: 0.9467

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	0.91	5	2.1248	0.0667
No log	1.91	10	1.9221	0.24
No log	2.91	15	1.7177	0.32
2.0123	3.91	20	1.5490	0.4267
2.0123	4.91	25	1.3192	0.5333
2.0123	5.91	30	1.0764	0.64
2.0123	6.91	35	0.8421	0.76
1.3539	7.91	40	0.6504	0.8267
1.3539	8.91	45	0.5243	0.8667
1.3539	9.91	50	0.4282	0.88
1.3539	10.91	55	0.3950	0.9067
0.7315	11.91	60	0.3617	0.8933
0.7315	12.91	65	0.3167	0.9067
0.7315	13.91	70	0.3023	0.9067
0.7315	14.91	75	0.2440	0.9333
0.5713	15.91	80	0.2475	0.9333
0.5713	16.91	85	0.2443	0.92
0.5713	17.91	90	0.2093	0.96
0.5713	18.91	95	0.2077	0.9467
0.515	19.91	100	0.2124	0.9333
0.515	20.91	105	0.2166	0.96
0.515	21.91	110	0.1940	0.9333
0.515	22.91	115	0.1984	0.9333
0.4582	23.91	120	0.2395	0.9333
0.4582	24.91	125	0.2480	0.92
0.4582	25.91	130	0.2180	0.92
0.4582	26.91	135	0.2232	0.9333
0.4279	27.91	140	0.1977	0.9333
0.4279	28.91	145	0.1847	0.9467
0.4279	29.91	150	0.1922	0.9467
0.4279	30.91	155	0.1787	0.9733
0.4031	31.91	160	0.1626	0.9733
0.4031	32.91	165	0.1667	0.9733
0.4031	33.91	170	0.1871	0.9733
0.4031	34.91	175	0.2015	0.9733
0.3952	35.91	180	0.1836	0.9733
0.3952	36.91	185	0.1856	0.96
0.3952	37.91	190	0.1952	0.9333
0.3952	38.91	195	0.1721	0.96
0.369	39.91	200	0.1619	0.9467
0.369	40.91	205	0.1659	0.96
0.369	41.91	210	0.1569	0.96
0.369	42.91	215	0.1358	0.96
0.3262	43.91	220	0.1371	0.96
0.3262	44.91	225	0.1337	0.9467
0.3262	45.91	230	0.1374	0.9467
0.3262	46.91	235	0.1789	0.96
0.3616	47.91	240	0.2167	0.9467
0.3616	48.91	245	0.1757	0.96
0.3616	49.91	250	0.1729	0.9733
0.3616	50.91	255	0.1722	0.9733
0.303	51.91	260	0.1601	0.9733
0.303	52.91	265	0.1592	0.9733
0.303	53.91	270	0.1613	0.9733
0.303	54.91	275	0.1575	0.9733
0.305	55.91	280	0.1559	0.9733
0.305	56.91	285	0.1489	0.9733
0.305	57.91	290	0.1464	0.96
0.305	58.91	295	0.1463	0.9467
0.3328	59.91	300	0.1463	0.9467

Framework versions

Transformers 4.26.0
Pytorch 1.13.1+cu116
Datasets 2.9.0
Tokenizers 0.13.2