README.md

metadata

license: other
base_model: nvidia/mit-b0
tags:
  - generated_from_trainer
datasets:
  - imagefolder
metrics:
  - accuracy
model-index:
  - name: architectural_styles_classifier
    results:
      - task:
          name: Image Classification
          type: image-classification
        dataset:
          name: imagefolder
          type: imagefolder
          config: default
          split: validation
          args: default
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.7223300970873786

architectural_styles_classifier

This model is a fine-tuned version of nvidia/mit-b0 on the Architectural styles dataset, retrieved from https://www.kaggle.com/datasets/dumitrux/architectural-styles-dataset. It achieves the following results on the evaluation set:

• Loss: 0.9412
• Accuracy: 0.7223

Model description

Presentation about the model: https://www.canva.com/design/DAGLBMAs1K4/d8qvLN2nchSYVmnrwYzx0w/edit?utm_content=DAGLBMAs1K4&utm_campaign=designshare&utm_medium=link2&utm_source=sharebutton

You can try the model from Huggingface Space this link: https://huggingface.co/spaces/hanslab37/technospire

Intended uses & limitations

The model were developed as part of experiment to learn about training a model and developing Image Classification model with Gradio in Huggingface. You can use it for experiment only. Not recommended for daily use.

Training and evaluation data

https://www.kaggle.com/datasets/dumitrux/architectural-styles-dataset

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.0005
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=0.0003
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.8855	0.9960	110	1.7753	0.4457
1.583	1.9921	220	1.6208	0.4829
1.4343	2.9972	331	1.3291	0.5851
1.2836	3.9932	441	1.2550	0.6005
1.2885	4.9983	552	1.1483	0.6298
1.1226	5.9943	662	1.1245	0.6491
0.985	6.9994	773	1.1381	0.6397
0.9963	7.9955	883	1.0964	0.6605
0.88	8.9915	993	1.0407	0.6739
0.7688	9.9966	1104	1.0288	0.6918
0.763	10.9926	1214	0.9835	0.6898
0.6287	11.9977	1325	1.0049	0.7037
0.6229	12.9938	1435	1.1010	0.6918
0.5731	13.9989	1546	0.9910	0.7082
0.5076	14.9949	1656	1.0457	0.7112
0.554	16.0	1767	1.0141	0.7007
0.382	16.9960	1877	1.0606	0.6928
0.459	17.9921	1987	1.0091	0.7161
0.4018	18.9972	2098	1.0011	0.7072
0.3981	19.9208	2200	0.9821	0.7310

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0
• Datasets 2.19.1
• Tokenizers 0.19.1