The downloadable models provided by PaddleOCR include inference model, trained model, pre-trained model and slim model. The differences between the models are as follows:
| model type | model format | description |
|---|---|---|
| inference model | model、params | Used for reasoning based on Python prediction engine. detail |
| trained model / pre-trained model | *.pdmodel、*.pdopt、*.pdparams | The checkpoints model saved in the training process, which stores the parameters of the model, mostly used for model evaluation and continuous training. |
| slim model | *.nb | Generally used for Lite deployment |
| model name | description | config | model size | download |
|---|---|---|---|---|
| ch_ppocr_mobile_slim_v1.1_det | Slim pruned lightweight model, supporting Chinese, English, multilingual text detection | det_mv3_db_v1.1.yml | 1.4M | inference model / slim model |
| ch_ppocr_mobile_v1.1_det | Original lightweight model, supporting Chinese, English, multilingual text detection | det_mv3_db_v1.1.yml | 2.6M | inference model / trained model |
| ch_ppocr_server_v1.1_det | General model, which is larger than the lightweight model, but achieved better performance | det_r18_vd_db_v1.1.yml | 47.2M | inference model / trained model |
| model name | description | config | model size | download |
|---|---|---|---|---|
| ch_ppocr_mobile_slim_v1.1_rec | Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition | rec_chinese_lite_train_v1.1.yml | 1.6M | inference model / slim model |
| ch_ppocr_mobile_v1.1_rec | Original lightweight model, supporting Chinese, English and number recognition | rec_chinese_lite_train_v1.1.yml | 4.6M | inference model / trained model / pre-trained model |
| ch_ppocr_server_v1.1_rec | General model, supporting Chinese, English and number recognition | rec_chinese_common_train_v1.1.yml | 105M | inference model / trained model / pre-trained model |
Note: The trained model is finetuned on the pre-trained model with real data and synthsized vertical text data, which achieved better performance in real scene. The pre-trained model is directly trained on the full amount of real data and synthsized data, which is more suitable for finetune on your own dataset.
| model name | description | config | model size | download |
|---|---|---|---|---|
| en_ppocr_mobile_slim_v1.1_rec | Slim pruned and quantized lightweight model, supporting English and number recognition | rec_en_lite_train.yml | 0.9M | inference model / slim model |
| en_ppocr_mobile_v1.1_rec | Original lightweight model, supporting English and number recognition | rec_en_lite_train.yml | 2.0M | inference model / trained model |
| model name | description | config | model size | download |
|---|---|---|---|---|
| french_ppocr_mobile_v1.1_rec | Lightweight model for French recognition | rec_french_lite_train.yml | 2.1M | inference model / trained model |
| german_ppocr_mobile_v1.1_rec | German model for French recognition | rec_ger_lite_train.yml | 2.1M | inference model / trained model |
| korean_ppocr_mobile_v1.1_rec | Lightweight model for Korean recognition | rec_korean_lite_train.yml | 3.4M | inference model / trained model |
| japan_ppocr_mobile_v1.1_rec | Lightweight model for Japanese recognition | rec_japan_lite_train.yml | 3.7M | inference model / trained model |
| model name | description | config | model size | download |
|---|---|---|---|---|
| ch_ppocr_mobile_v1.1_cls_quant | Slim quantized model | cls_mv3.yml | 0.5M | inference model / trained model / slim model |
| ch_ppocr_mobile_v1.1_cls | Original model | cls_mv3.yml | 850kb | inference model / trained model |
| model name | description | detection model | recognition model | recognition model supporting space recognition |
|---|---|---|---|---|
| chinese_db_crnn_mobile | 8.6M lightweight OCR model | inference model / trained model | inference model / trained model | inference model / trained model |
| chinese_db_crnn_server | General OCR model | inference model / trained model | inference model / trained model | inference model / trained model |