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: 0.9259259259259259

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: 0.2419
Accuracy: 0.9259

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	1.8673	0.2222
No log	1.8	6	1.7421	0.2593
No log	2.8	9	1.5910	0.4259
No log	3.8	12	1.4371	0.5
No log	4.8	15	1.2871	0.5741
No log	5.8	18	1.1511	0.5741
1.8164	6.8	21	0.9363	0.7222
1.8164	7.8	24	0.7903	0.7778
1.8164	8.8	27	0.6839	0.7593
1.8164	9.8	30	0.5661	0.7778
1.8164	10.8	33	0.4638	0.8519
1.8164	11.8	36	0.4015	0.8704
1.8164	12.8	39	0.3809	0.8704
0.8525	13.8	42	0.3214	0.9074
0.8525	14.8	45	0.3114	0.8704
0.8525	15.8	48	0.3026	0.8889
0.8525	16.8	51	0.2970	0.8889
0.8525	17.8	54	0.2597	0.8889
0.8525	18.8	57	0.2792	0.8889
0.4831	19.8	60	0.3209	0.8704
0.4831	20.8	63	0.2929	0.9074
0.4831	21.8	66	0.2419	0.9259
0.4831	22.8	69	0.2496	0.9074
0.4831	23.8	72	0.2953	0.9074
0.4831	24.8	75	0.3094	0.8889
0.4831	25.8	78	0.2792	0.9259
0.3889	26.8	81	0.2522	0.9259
0.3889	27.8	84	0.2451	0.9259
0.3889	28.8	87	0.2541	0.9074
0.3889	29.8	90	0.2718	0.9074
0.3889	30.8	93	0.2738	0.9074
0.3889	31.8	96	0.2639	0.9259
0.3889	32.8	99	0.2561	0.9259
0.3407	33.8	102	0.2497	0.9259
0.3407	34.8	105	0.2501	0.9259
0.3407	35.8	108	0.2455	0.9259
0.3407	36.8	111	0.2381	0.9259
0.3407	37.8	114	0.2340	0.9259
0.3407	38.8	117	0.2321	0.9259
0.3112	39.8	120	0.2315	0.9259

Framework versions

Transformers 4.24.0
Pytorch 1.12.1+cu113
Datasets 2.7.1
Tokenizers 0.13.2