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: 1

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: 0.0447
Accuracy: 1.0

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	0.86	3	1.7166	0.2245
No log	1.86	6	1.5816	0.4082
No log	2.86	9	1.4084	0.5510
No log	3.86	12	1.1761	0.6327
No log	4.86	15	0.9245	0.7347
No log	5.86	18	0.6986	0.7959
1.608	6.86	21	0.5158	0.8367
1.608	7.86	24	0.3753	0.8776
1.608	8.86	27	0.3092	0.8980
1.608	9.86	30	0.2584	0.9388
1.608	10.86	33	0.2159	0.9184
1.608	11.86	36	0.1908	0.9592
1.608	12.86	39	0.1802	0.9592
0.6473	13.86	42	0.1682	0.9592
0.6473	14.86	45	0.1560	0.9592
0.6473	15.86	48	0.1322	0.9592
0.6473	16.86	51	0.1101	0.9592
0.6473	17.86	54	0.0938	0.9592
0.6473	18.86	57	0.0889	0.9796
0.3855	19.86	60	0.1025	0.9796
0.3855	20.86	63	0.0984	0.9796
0.3855	21.86	66	0.0867	0.9592
0.3855	22.86	69	0.0813	0.9592
0.3855	23.86	72	0.0768	0.9592
0.3855	24.86	75	0.0734	0.9796
0.3855	25.86	78	0.0698	0.9796
0.306	26.86	81	0.0618	0.9592
0.306	27.86	84	0.0547	0.9796
0.306	28.86	87	0.0538	0.9592
0.306	29.86	90	0.0487	0.9796
0.306	30.86	93	0.0447	1.0
0.306	31.86	96	0.0425	1.0
0.306	32.86	99	0.0451	1.0
0.2966	33.86	102	0.0497	1.0
0.2966	34.86	105	0.0558	1.0
0.2966	35.86	108	0.0582	0.9796
0.2966	36.86	111	0.0616	0.9592
0.2966	37.86	114	0.0657	0.9592
0.2966	38.86	117	0.0679	0.9592
0.2535	39.86	120	0.0684	0.9592

Framework versions

Transformers 4.23.1
Pytorch 1.12.1+cu113
Datasets 2.6.1
Tokenizers 0.13.1