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: 0.9714285714285714

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: 0.1192
Accuracy: 0.9714

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: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	5	1.9402	0.1286
No log	2.0	10	1.8379	0.2429
No log	3.0	15	1.6960	0.4
1.7795	4.0	20	1.4423	0.5143
1.7795	5.0	25	1.1295	0.6857
1.7795	6.0	30	0.8280	0.7286
1.7795	7.0	35	0.5572	0.8429
1.0588	8.0	40	0.3855	0.9286
1.0588	9.0	45	0.3107	0.9143
1.0588	10.0	50	0.2564	0.9286
1.0588	11.0	55	0.2050	0.9286
0.591	12.0	60	0.1900	0.9571
0.591	13.0	65	0.1720	0.9286
0.591	14.0	70	0.1881	0.9143
0.591	15.0	75	0.1789	0.9429
0.4609	16.0	80	0.1999	0.9143
0.4609	17.0	85	0.1492	0.9286
0.4609	18.0	90	0.1648	0.9286
0.4609	19.0	95	0.1195	0.9571
0.3941	20.0	100	0.1395	0.9286
0.3941	21.0	105	0.1476	0.9286
0.3941	22.0	110	0.1113	0.9571
0.3941	23.0	115	0.1328	0.9571
0.3475	24.0	120	0.1192	0.9714
0.3475	25.0	125	0.1200	0.9571
0.3475	26.0	130	0.1360	0.9714
0.3475	27.0	135	0.1425	0.9429
0.3542	28.0	140	0.1103	0.9571
0.3542	29.0	145	0.1244	0.9429
0.3542	30.0	150	0.1176	0.9571
0.3542	31.0	155	0.1028	0.9571
0.317	32.0	160	0.1084	0.9571
0.317	33.0	165	0.1269	0.9571
0.317	34.0	170	0.1295	0.9429
0.317	35.0	175	0.1245	0.9571
0.2947	36.0	180	0.1315	0.9429
0.2947	37.0	185	0.1313	0.9571
0.2947	38.0	190	0.1421	0.9429
0.2947	39.0	195	0.1440	0.9571
0.3124	40.0	200	0.1339	0.9571
0.3124	41.0	205	0.1553	0.9429
0.3124	42.0	210	0.1547	0.9429
0.3124	43.0	215	0.1316	0.9571
0.2843	44.0	220	0.1287	0.9571
0.2843	45.0	225	0.1308	0.9571
0.2843	46.0	230	0.1401	0.9571
0.2843	47.0	235	0.1186	0.9571
0.2655	48.0	240	0.1057	0.9571
0.2655	49.0	245	0.1203	0.9571
0.2655	50.0	250	0.1374	0.9571
0.2655	51.0	255	0.1361	0.9571
0.26	52.0	260	0.1198	0.9571
0.26	53.0	265	0.1175	0.9571
0.26	54.0	270	0.1313	0.9571
0.26	55.0	275	0.1398	0.9429
0.2601	56.0	280	0.1354	0.9571
0.2601	57.0	285	0.1271	0.9571
0.2601	58.0	290	0.1242	0.9571
0.2601	59.0	295	0.1233	0.9571
0.2562	60.0	300	0.1235	0.9571

Framework versions

Transformers 4.25.1
Pytorch 1.13.1+cu116
Datasets 2.8.0
Tokenizers 0.13.2