From bcc8f208ec28f7cef033f59d63e1069ed0ebe408 Mon Sep 17 00:00:00 2001 From: MissPenguin Date: Mon, 21 Sep 2020 16:27:01 +0800 Subject: [PATCH] add det_mv3_db_v1.1.yml & update config link for rec model --- configs/det/det_mv3_db.yml | 1 - configs/det/det_mv3_db_v1.1.yml | 59 +++++++++++++++++++++++++++++++++ doc/doc_ch/models_list.md | 12 +++---- doc/doc_en/models_list_en.md | 12 +++---- 4 files changed, 71 insertions(+), 13 deletions(-) create mode 100755 configs/det/det_mv3_db_v1.1.yml diff --git a/configs/det/det_mv3_db.yml b/configs/det/det_mv3_db.yml index 5f67ca1d..91a8e86f 100755 --- a/configs/det/det_mv3_db.yml +++ b/configs/det/det_mv3_db.yml @@ -24,7 +24,6 @@ Backbone: function: ppocr.modeling.backbones.det_mobilenet_v3,MobileNetV3 scale: 0.5 model_name: large - disable_se: true Head: function: ppocr.modeling.heads.det_db_head,DBHead diff --git a/configs/det/det_mv3_db_v1.1.yml b/configs/det/det_mv3_db_v1.1.yml new file mode 100755 index 00000000..afc11aa0 --- /dev/null +++ b/configs/det/det_mv3_db_v1.1.yml @@ -0,0 +1,59 @@ +Global: + algorithm: DB + use_gpu: true + epoch_num: 1200 + log_smooth_window: 20 + print_batch_step: 2 + save_model_dir: ./output/det_db/ + save_epoch_step: 200 + # evaluation is run every 5000 iterations after the 4000th iteration + eval_batch_step: [4000, 5000] + train_batch_size_per_card: 16 + test_batch_size_per_card: 16 + image_shape: [3, 640, 640] + reader_yml: ./configs/det/det_db_icdar15_reader.yml + pretrain_weights: ./pretrain_models/MobileNetV3_large_x0_5_pretrained/ + checkpoints: + save_res_path: ./output/det_db/predicts_db.txt + save_inference_dir: + +Architecture: + function: ppocr.modeling.architectures.det_model,DetModel + +Backbone: + function: ppocr.modeling.backbones.det_mobilenet_v3,MobileNetV3 + scale: 0.5 + model_name: large + disable_se: true + +Head: + function: ppocr.modeling.heads.det_db_head,DBHead + model_name: large + k: 50 + inner_channels: 96 + out_channels: 2 + +Loss: + function: ppocr.modeling.losses.det_db_loss,DBLoss + balance_loss: true + main_loss_type: DiceLoss + alpha: 5 + beta: 10 + ohem_ratio: 3 + +Optimizer: + function: ppocr.optimizer,AdamDecay + base_lr: 0.001 + beta1: 0.9 + beta2: 0.999 + decay: + function: cosine_decay_warmup + step_each_epoch: 16 + total_epoch: 1200 + +PostProcess: + function: ppocr.postprocess.db_postprocess,DBPostProcess + thresh: 0.3 + box_thresh: 0.6 + max_candidates: 1000 + unclip_ratio: 1.5 diff --git a/doc/doc_ch/models_list.md b/doc/doc_ch/models_list.md index 24068f47..d88a780e 100644 --- a/doc/doc_ch/models_list.md +++ b/doc/doc_ch/models_list.md @@ -20,9 +20,9 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 ### 一、文本检测模型 |模型名称|模型简介|配置文件|推理模型大小|下载地址| |-|-|-|-|-| -|ch_ppocr_mobile_slim_v1.1_det|slim裁剪版超轻量模型，支持中英文、多语种文本检测|[det_mv3_db.yml](../../configs/det/det_mv3_db.yml)|1.4M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_infer.tar) / [slim模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)| -|ch_ppocr_mobile_v1.1_det|原始超轻量模型，支持中英文、多语种文本检测|[det_mv3_db.yml](../../configs/det/det_mv3_db.yml)|2.6M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar)| -|ch_ppocr_server_v1.1_det|通用模型，支持中英文、多语种文本检测，比超轻量模型更大，但效果更好|[det_r18_vd_db.yml](../../configs/det/det_r18_vd_db.yml)|47.2M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_train.tar)| +|ch_ppocr_mobile_slim_v1.1_det|slim裁剪版超轻量模型，支持中英文、多语种文本检测|[det_mv3_db_v1.1.yml](../../configs/det/det_mv3_db_v1.1.yml)|1.4M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_infer.tar) / [slim模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)| +|ch_ppocr_mobile_v1.1_det|原始超轻量模型，支持中英文、多语种文本检测|[det_mv3_db_v1.1.yml](../../configs/det/det_mv3_db_v1.1.yml)|2.6M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar)| +|ch_ppocr_server_v1.1_det|通用模型，支持中英文、多语种文本检测，比超轻量模型更大，但效果更好|[det_r18_vd_db_v1.1.yml](../../configs/det/det_r18_vd_db_v1.1.yml)|47.2M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_train.tar)| @@ -32,9 +32,9 @@ PaddleOCR提供的可下载模型包括`推理模型`、`训练模型`、`预训 #### 1. 中文识别模型 |模型名称|模型简介|配置文件|推理模型大小|下载地址| |-|-|-|-|-| -|ch_ppocr_mobile_slim_v1.1_rec|slim裁剪量化版超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train.yml](../../configs/rec/rec_chinese_lite_train.yml)|1.6M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar) / [slim模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)| -|ch_ppocr_mobile_v1.1_rec|原始超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train.yml](../../configs/rec/rec_chinese_lite_train.yml)|4.6M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_pre.tar)| -|ch_ppocr_server_v1.1_rec|通用模型，支持中英文、数字识别|[rec_chinese_common_train.yml](../../configs/rec/rec_chinese_common_train.yml)|105M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_pre.tar)| +|ch_ppocr_mobile_slim_v1.1_rec|slim裁剪量化版超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_v1.1.yml](../../configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yml)|1.6M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar) / [slim模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)| +|ch_ppocr_mobile_v1.1_rec|原始超轻量模型，支持中英文、数字识别|[rec_chinese_lite_train_v1.1.yml](../../configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yml)|4.6M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_pre.tar)| +|ch_ppocr_server_v1.1_rec|通用模型，支持中英文、数字识别|[rec_chinese_common_train_v1.1.yml](../../configs/rec/ch_ppocr_v1.1/rec_chinese_common_train_v1.1.yml)|105M|[推理模型](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_train.tar) / [预训练模型](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_pre.tar)| **说明：** `训练模型`是基于预训练模型在真实数据与竖排合成文本数据上finetune得到的模型，在真实应用场景中有着更好的表现，`预训练模型`则是直接基于全量真实数据与合成数据训练得到，更适合用于在自己的数据集上finetune。 diff --git a/doc/doc_en/models_list_en.md b/doc/doc_en/models_list_en.md index d9a19639..cf137c20 100644 --- a/doc/doc_en/models_list_en.md +++ b/doc/doc_en/models_list_en.md @@ -20,9 +20,9 @@ The downloadable models provided by PaddleOCR include `inference model`, `traine ### 1. Text Detection Model |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.yml](../../configs/det/det_mv3_db.yml)|1.4M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)| -|ch_ppocr_mobile_v1.1_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[det_mv3_db.yml](../../configs/det/det_mv3_db.yml)|2.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar)| -|ch_ppocr_server_v1.1_det|General model, which is larger than the lightweight model, but achieved better performance|[det_r18_vd_db.yml](../../configs/det/det_r18_vd_db.yml)|47.2M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_train.tar)| +|ch_ppocr_mobile_slim_v1.1_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|[det_mv3_db_v1.1.yml](../../configs/det/det_mv3_db_v1.1.yml)|1.4M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/det/ch_ppocr_mobile_v1.1_det_prune_opt.nb)| +|ch_ppocr_mobile_v1.1_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[det_mv3_db_v1.1.yml](../../configs/det/det_mv3_db_v1.1.yml)|2.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/det/ch_ppocr_mobile_v1.1_det_train.tar)| +|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](../../configs/det/det_r18_vd_db_v1.1.yml)|47.2M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/det/ch_ppocr_server_v1.1_det_train.tar)| @@ -32,9 +32,9 @@ The downloadable models provided by PaddleOCR include `inference model`, `traine #### Chinese Recognition 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.yml](../../configs/rec/rec_chinese_lite_train.yml)|1.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)| -|ch_ppocr_mobile_v1.1_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train.yml](../../configs/rec/rec_chinese_lite_train.yml)|4.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_pre.tar)| -|ch_ppocr_server_v1.1_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train.yml](../../configs/rec/rec_chinese_common_train.yml)|105M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_pre.tar)| +|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](../../configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yml)|1.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_infer.tar) / [slim model](https://paddleocr.bj.bcebos.com/20-09-22/mobile-slim/rec/ch_ppocr_mobile_v1.1_rec_quant_opt.nb)| +|ch_ppocr_mobile_v1.1_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v1.1.yml](../../configs/rec/ch_ppocr_v1.1/rec_chinese_lite_train_v1.1.yml)|4.6M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/mobile/rec/ch_ppocr_mobile_v1.1_rec_pre.tar)| +|ch_ppocr_server_v1.1_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train_v1.1.yml](../../configs/rec/ch_ppocr_v1.1/rec_chinese_common_train_v1.1.yml)|105M|[inference model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/20-09-22/server/rec/ch_ppocr_server_v1.1_rec_pre.tar)| **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. -- GitLab