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: 0.2180
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	0.57	1	1.7779	0.2727
No log	1.57	2	1.7088	0.3182
No log	2.57	3	1.5921	0.5455
No log	3.57	4	1.4587	0.5909
No log	4.57	5	1.3256	0.5455
No log	5.57	6	1.2211	0.5
No log	6.57	7	1.1066	0.6818
No log	7.57	8	0.9768	0.7727
No log	8.57	9	0.8590	0.8636
No log	9.57	10	0.7718	0.9091
No log	10.57	11	0.6999	0.9091
No log	11.57	12	0.6385	0.9091
No log	12.57	13	0.5761	0.9545
No log	13.57	14	0.5189	0.9545
No log	14.57	15	0.4646	0.9545
No log	15.57	16	0.4137	0.9091
No log	16.57	17	0.3679	0.9091
No log	17.57	18	0.3291	0.9091
No log	18.57	19	0.2937	0.9545
1.8863	19.57	20	0.2642	0.9545
1.8863	20.57	21	0.2366	0.9545
1.8863	21.57	22	0.2180	1.0
1.8863	22.57	23	0.2061	1.0
1.8863	23.57	24	0.1984	1.0
1.8863	24.57	25	0.1918	1.0
1.8863	25.57	26	0.1787	1.0
1.8863	26.57	27	0.1605	1.0
1.8863	27.57	28	0.1412	1.0
1.8863	28.57	29	0.1269	1.0
1.8863	29.57	30	0.1142	1.0
1.8863	30.57	31	0.1051	1.0
1.8863	31.57	32	0.0995	1.0
1.8863	32.57	33	0.0946	1.0
1.8863	33.57	34	0.0911	1.0
1.8863	34.57	35	0.0892	1.0
1.8863	35.57	36	0.0876	1.0
1.8863	36.57	37	0.0865	1.0
1.8863	37.57	38	0.0857	1.0
1.8863	38.57	39	0.0854	1.0
0.6775	39.57	40	0.0853	1.0

Framework versions

Transformers 4.21.3
Pytorch 1.12.1+cpu
Datasets 2.4.0
Tokenizers 0.12.1