Car Body Classifier

--- language: - tr - en license: other license_name: restricted-research-evaluation license_link: LICENSE.md library_name: timm pipeline_tag: image-classification tags: - pytorch - timm - efficientnetv2 - image-classification - vehicle-classification - car-body-type datasets: - custom metrics: - accuracy - f1 base_model: timm/tf_efficientnetv2_s.in21k_ft_in1k base_model_relation: finetune model-index: - name: EfficientNetV2-S Car Body Classifier results: - task: type: image-classification name: Image Classification dataset: type: custom name: Custom car body image dataset split: test metrics: - type: accuracy value: 0.96663 name: Test Accuracy - type: f1 value: 0.954043 name: Test Macro F1 - type: f1 value: 0.966779 name: Test Weighted F1 --- # EfficientNetV2-S Car Body Classifier This repository contains a PyTorch/timm EfficientNetV2-S image classifier for 8 vehicle body types. The model predicts one of `SUV`, `VAN`, `STATION_WAGON`, `MICRO`, `ACIK_TEKERLEKLI_F1_ARACLARI`, `SEDAN`, `HATCHBACK`, or `PICK_UP` from a single RGB vehicle image. The checkpoint is a fine-tuned `tf_efficientnetv2_s` model with an 8-class classification head. Probability outputs should be temperature-calibrated with `temperature = 0.565484`. ## Files | File | Purpose | |---|---| | `efficientnetv2_s_best.pt` | PyTorch state dict checkpoint. | | `model.safetensors` | Safetensors copy of the same state dict for safer public download workflows. | | `config.json` | Repository-level model/task configuration. | | `metadata.json` | Training, class, artifact, and metric metadata. | | `preprocessor_config.json` | Image size, normalization, and preprocessing contract. | | `calibration.json` | Temperature scaling configuration and raw/calibrated metrics. | | `requirements.txt` | Minimal runtime dependencies. | ## Intended Use Use this model for educational or prototype vehicle body-type classification from visible car images. It is intended for controlled project demos, non-commercial research evaluation, model-serving experiments, and API integration tests where inputs are ordinary car images. ## Out-of-Scope Use Do not use this model for commercial products, public hosted inference services, redistribution, or as the sole basis for safety-critical, insurance, legal, financial, or law-enforcement decisions. Do not assume robust performance on non-car v...