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: 0.8571428571428571

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: 0.7036
Accuracy: 0.8571

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	1.0	1	1.9875	0.1429
No log	2.0	2	1.9132	0.1429
No log	3.0	3	1.7585	0.4286
No log	4.0	4	1.5935	0.4286
No log	5.0	5	1.5026	0.4286
No log	6.0	6	1.4699	0.4286
No log	7.0	7	1.4361	0.4286
No log	8.0	8	1.3962	0.4286
No log	9.0	9	1.3457	0.4286
No log	10.0	10	1.2874	0.4286
No log	11.0	11	1.2240	0.4286
No log	12.0	12	1.1643	0.4286
No log	13.0	13	1.1016	0.5714
No log	14.0	14	1.0356	0.5714
No log	15.0	15	0.9719	0.7143
No log	16.0	16	0.9120	0.7143
No log	17.0	17	0.8606	0.7143
No log	18.0	18	0.8117	0.7143
No log	19.0	19	0.7707	0.7143
0.5111	20.0	20	0.7367	0.7143
0.5111	21.0	21	0.7157	0.7143
0.5111	22.0	22	0.7067	0.7143
0.5111	23.0	23	0.7012	0.7143
0.5111	24.0	24	0.6977	0.7143
0.5111	25.0	25	0.6974	0.7143
0.5111	26.0	26	0.6977	0.7143
0.5111	27.0	27	0.7036	0.8571
0.5111	28.0	28	0.7074	0.8571
0.5111	29.0	29	0.7062	0.8571
0.5111	30.0	30	0.7056	0.8571
0.5111	31.0	31	0.7050	0.8571
0.5111	32.0	32	0.7050	0.8571
0.5111	33.0	33	0.7031	0.8571
0.5111	34.0	34	0.7016	0.8571
0.5111	35.0	35	0.6996	0.8571
0.5111	36.0	36	0.6971	0.8571
0.5111	37.0	37	0.6953	0.8571
0.5111	38.0	38	0.6939	0.8571
0.5111	39.0	39	0.6938	0.8571
0.1719	40.0	40	0.6936	0.8571

Framework versions

Transformers 4.21.2
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1