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: 0.1787
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	1	2.0794	0.0588
No log	1.8	2	2.0047	0.1176
No log	2.8	3	1.8666	0.1765
No log	3.8	4	1.6800	0.2353
No log	4.8	5	1.4622	0.3529
No log	5.8	6	1.2880	0.5882
No log	6.8	7	1.1316	0.8824
No log	7.8	8	0.9925	0.8824
No log	8.8	9	0.8822	0.8824
No log	9.8	10	0.7928	0.8824
No log	10.8	11	0.7266	0.8824
No log	11.8	12	0.6715	0.8824
No log	12.8	13	0.6238	0.8824
No log	13.8	14	0.5793	0.8824
No log	14.8	15	0.5423	0.8824
No log	15.8	16	0.5103	0.8824
No log	16.8	17	0.4865	0.9412
No log	17.8	18	0.4635	0.9412
No log	18.8	19	0.4399	0.9412
1.3142	19.8	20	0.4119	0.9412
1.3142	20.8	21	0.3843	0.9412
1.3142	21.8	22	0.3497	0.9412
1.3142	22.8	23	0.3161	0.9412
1.3142	23.8	24	0.2850	0.9412
1.3142	24.8	25	0.2581	0.9412
1.3142	25.8	26	0.2363	0.9412
1.3142	26.8	27	0.2179	0.9412
1.3142	27.8	28	0.2029	0.9412
1.3142	28.8	29	0.1903	0.9412
1.3142	29.8	30	0.1787	1.0
1.3142	30.8	31	0.1676	1.0
1.3142	31.8	32	0.1581	1.0
1.3142	32.8	33	0.1487	1.0
1.3142	33.8	34	0.1410	1.0
1.3142	34.8	35	0.1349	1.0
1.3142	35.8	36	0.1301	1.0
1.3142	36.8	37	0.1266	1.0
1.3142	37.8	38	0.1243	1.0
1.3142	38.8	39	0.1230	1.0
0.4316	39.8	40	0.1223	1.0

Framework versions

Transformers 4.21.2
Pytorch 1.12.1+cu113
Datasets 2.4.0
Tokenizers 0.12.1