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: 0.1871
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	0.8	3	1.8912	0.0392
No log	1.8	6	1.7519	0.2745
No log	2.8	9	1.5549	0.4706
No log	3.8	12	1.2851	0.6667
No log	4.8	15	0.9968	0.7647
No log	5.8	18	0.7826	0.7843
1.787	6.8	21	0.6010	0.8824
1.787	7.8	24	0.4301	0.9020
1.787	8.8	27	0.3233	0.8824
1.787	9.8	30	0.2303	0.9412
1.787	10.8	33	0.1871	1.0
1.787	11.8	36	0.1600	0.9608
1.787	12.8	39	0.1334	0.9804
0.7554	13.8	42	0.1025	1.0
0.7554	14.8	45	0.0909	1.0
0.7554	15.8	48	0.0733	1.0
0.7554	16.8	51	0.0625	1.0
0.7554	17.8	54	0.0602	1.0
0.7554	18.8	57	0.0613	1.0
0.4731	19.8	60	0.0506	1.0
0.4731	20.8	63	0.0588	1.0
0.4731	21.8	66	0.0655	0.9804
0.4731	22.8	69	0.0517	1.0
0.4731	23.8	72	0.0414	1.0
0.4731	24.8	75	0.0408	1.0
0.4731	25.8	78	0.0417	1.0
0.4248	26.8	81	0.0389	1.0
0.4248	27.8	84	0.0376	1.0
0.4248	28.8	87	0.0361	1.0
0.4248	29.8	90	0.0351	1.0
0.4248	30.8	93	0.0299	1.0
0.4248	31.8	96	0.0284	1.0
0.4248	32.8	99	0.0279	1.0
0.3657	33.8	102	0.0275	1.0
0.3657	34.8	105	0.0279	1.0
0.3657	35.8	108	0.0279	1.0
0.3657	36.8	111	0.0278	1.0
0.3657	37.8	114	0.0276	1.0
0.3657	38.8	117	0.0274	1.0
0.3115	39.8	120	0.0274	1.0

Framework versions

Transformers 4.24.0
Pytorch 1.12.1+cu113
Datasets 2.6.1
Tokenizers 0.13.2