Skip to content

Available Models

Model Zoo

Optimized, ready to use models with config files for inference or fine-tuning.

Model Name Size Arch b=1 Avg. Latency (ms) Plates/sec (PPS) Model Config Plate Config
cct-s-v1-global-model S CCT 0.5877 1701.63 link link
cct-xs-v1-global-model XS CCT 0.3232 3094.21 link link
Benchmarking Setup

These results were obtained with:

  • Hardware: NVIDIA RTX 3090 GPU
  • Execution Providers: ['TensorrtExecutionProvider', 'CUDAExecutionProvider', 'CPUExecutionProvider']
  • Install dependencies: 
    pip install fast-plate-ocr[onnx-gpu]

Legacy Models

These are pre-trained models from earlier iterations of fast-plate-ocr, primarily kept for inference purposes.

Model Name Time b=1
(ms)[1]		 Throughput
(plates/second)[1]		 Accuracy[2] Dataset
argentinian-plates-cnn-model 2.1 476 94.05% Non-synthetic, plates up to 2020. Dataset arg_plate_dataset.zip.
argentinian-plates-cnn-synth-model 2.1 476 94.19% Plates up to 2020 + synthetic plates. Dataset arg_plate_dataset_plus_synth.zip.
european-plates-mobile-vit-v2-model 2.9 344 92.5%[3] European plates (from +40 countries, trained on 40k+ plates).
global-plates-mobile-vit-v2-model 2.9 344 93.3%[4] Worldwide plates (from +65 countries, trained on 85k+ plates).
Legacy Notice

These are older models maintained for compatibility and inference only. They are not recommended for fine-tuning or continued development. For best results, use the newer models from the Model Zoo.

Inference & Evaluation Info

[1] Inference on Mac M1 chip using CPUExecutionProvider. Utilizing CoreMLExecutionProvider accelerates speed by 5x in the CNN models.

[2] Accuracy is what we refer as plate_acc. See metrics section.

[3] For detailed accuracy for each country see results and the corresponding val split used.

[4] For detailed accuracy for each country see results.

Reproduce results

Calculate Inference Time:

pip install fast-plate-ocr[onnx-gpu]

from fast_plate_ocr import LicensePlateRecognizer

m = LicensePlateRecognizer("argentinian-plates-cnn-model")
m.benchmark()

Calculate Model accuracy:

pip install fast-plate-ocr[train]
curl -LO https://github.com/ankandrew/fast-plate-ocr/releases/download/arg-plates/arg_cnn_ocr_config.yaml
curl -LO https://github.com/ankandrew/fast-plate-ocr/releases/download/arg-plates/arg_cnn_ocr.keras
curl -LO https://github.com/ankandrew/fast-plate-ocr/releases/download/arg-plates/arg_plate_benchmark.zip
unzip arg_plate_benchmark.zip
fast-plate-ocr valid \
    -m arg_cnn_ocr.keras \
    --config-file arg_cnn_ocr_config.yaml \
    --annotations benchmark/annotations.csv