From 514d47f3aeb0ae22ddeb063bbb75c5c820abe62e Mon Sep 17 00:00:00 2001 From: Felix Chen Date: Thu, 7 Jul 2022 17:49:48 +0800 Subject: [PATCH 1/7] add write_kie_result to kie infer tool --- tools/infer_kie.py | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/tools/infer_kie.py b/tools/infer_kie.py index 0cb0b8702..187b27adb 100755 --- a/tools/infer_kie.py +++ b/tools/infer_kie.py @@ -89,6 +89,29 @@ def draw_kie_result(batch, node, idx_to_cls, count): cv2.imwrite(save_path, vis_img) logger.info("The Kie Image saved in {}".format(save_path)) +def write_kie_result(fout, node, data): + """ + Write infer result to output file, sorted by the predict label of each line. + The format keeps the same as the input with additional score attribute. + """ + import json + label = data['label'] + annotations = json.loads(label) + max_value, max_idx = paddle.max(node, -1), paddle.argmax(node, -1) + node_pred_label = max_idx.numpy().tolist() + node_pred_score = max_value.numpy().tolist() + res = [] + for i, label in enumerate(node_pred_label): + pred_score = '{:.2f}'.format(node_pred_score[i]) + pred_res = { + 'label': label, + 'transcription': annotations[i]['transcription'], + 'score': pred_score, + 'points': annotations[i]['points'], + } + res.append(pred_res) + res.sort(key=lambda x: x['label']) + fout.writelines([json.dumps(res, ensure_ascii=False) + '\n']) def main(): global_config = config['Global'] @@ -116,7 +139,7 @@ def main(): warmup_times = 0 count_t = [] - with open(save_res_path, "wb") as fout: + with open(save_res_path, "w") as fout: with open(config['Global']['infer_img'], "rb") as f: lines = f.readlines() for index, data_line in enumerate(lines): @@ -141,6 +164,8 @@ def main(): node = F.softmax(node, -1) count_t.append(time.time() - st) draw_kie_result(batch, node, idx_to_cls, index) + write_kie_result(fout, node, data) + fout.close() logger.info("success!") logger.info("It took {} s for predict {} images.".format( np.sum(count_t), len(count_t))) From 081e7081378a80194aa97377cbda7e59fe88bc69 Mon Sep 17 00:00:00 2001 From: Double_V Date: Mon, 18 Jul 2022 18:40:03 +0800 Subject: [PATCH 2/7] Update algorithm_det_east.md --- doc/doc_ch/algorithm_det_east.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/doc_ch/algorithm_det_east.md b/doc/doc_ch/algorithm_det_east.md index b89018e34..ec949d4ed 100644 --- a/doc/doc_ch/algorithm_det_east.md +++ b/doc/doc_ch/algorithm_det_east.md @@ -27,7 +27,7 @@ |模型|骨干网络|配置文件|precision|recall|Hmean|下载链接| | --- | --- | --- | --- | --- | --- | --- | |EAST|ResNet50_vd|88.71%| 81.36%| 84.88%| [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)| -|EAST| MobileNetV3| 78.2%| 79.1%| 78.65%| [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)| +|EAST| MobileNetV3| 78.2%| 79.1%| 78.65%| [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)| From a3fef33bd4ef1a93817e7d09f480be55453cc400 Mon Sep 17 00:00:00 2001 From: Double_V Date: Mon, 18 Jul 2022 18:42:54 +0800 Subject: [PATCH 3/7] Update algorithm_det_east.md --- doc/doc_ch/algorithm_det_east.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/doc_ch/algorithm_det_east.md b/doc/doc_ch/algorithm_det_east.md index ec949d4ed..104e70927 100644 --- a/doc/doc_ch/algorithm_det_east.md +++ b/doc/doc_ch/algorithm_det_east.md @@ -26,8 +26,8 @@ |模型|骨干网络|配置文件|precision|recall|Hmean|下载链接| | --- | --- | --- | --- | --- | --- | --- | -|EAST|ResNet50_vd|88.71%| 81.36%| 84.88%| [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)| -|EAST| MobileNetV3| 78.2%| 79.1%| 78.65%| [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)| +|EAST|ResNet50_vd|[det_r50_vd_east.yml](../../configs/det/det_r50_vd_east.yml)|88.71%| 81.36%| 84.88%| [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_east_v2.0_train.tar)| +|EAST|MobileNetV3|[det_mv3_east.yml](../../configs/det/det_mv3_east.yml)| 78.2%| 79.1%| 78.65%| [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_mv3_east_v2.0_train.tar)| From 3f62ea21d40bdc4779b561fff8bb7e7d24abbf1d Mon Sep 17 00:00:00 2001 From: xiaoting <31891223+tink2123@users.noreply.github.com> Date: Tue, 19 Jul 2022 17:05:49 +0800 Subject: [PATCH 4/7] Update inference_ppocr.md --- doc/doc_ch/inference_ppocr.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/doc/doc_ch/inference_ppocr.md b/doc/doc_ch/inference_ppocr.md index 622ac995d..3ac9faa12 100644 --- a/doc/doc_ch/inference_ppocr.md +++ b/doc/doc_ch/inference_ppocr.md @@ -87,9 +87,9 @@ Predicts of ./doc/imgs_words/ch/word_4.jpg:('实力活力', 0.9956803321838379) ``` # 下载英文数字识别模型： -wget https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar -tar xf en_PP-OCRv3_det_infer.tar -python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./en_PP-OCRv3_det_infer/" --rec_char_dict_path="ppocr/utils/en_dict.txt" +wget https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar +tar xf en_PP-OCRv3_rec_infer.tar +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/en/word_1.png" --rec_model_dir="./en_PP-OCRv3_rec_infer/" --rec_char_dict_path="ppocr/utils/en_dict.txt" ``` ![](../imgs_words/en/word_1.png) From 05a2382198de43834013d99e67369f42d6741a7e Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Wed, 27 Jul 2022 17:08:35 +0800 Subject: [PATCH 5/7] Update README.md --- applications/README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/applications/README.md b/applications/README.md index f4c911dd9..53339630d 100644 --- a/applications/README.md +++ b/applications/README.md @@ -57,3 +57,7 @@ PaddleOCR场景应用覆盖通用，制造、金融、交通行业的主要OCR 如果您是企业开发者且未在上述场景中找到合适的方案，可以填写[OCR应用合作调研问卷](https://paddle.wjx.cn/vj/QwF7GKw.aspx)，免费与官方团队展开不同层次的合作，包括但不限于问题抽象、确定技术方案、项目答疑、共同研发等。如果您已经使用PaddleOCR落地项目，也可以填写此问卷，与飞桨平台共同宣传推广，提升企业技术品宣。期待您的提交！ + + +traffic + From 5350b8c549fda3195e32d34fd73214b0106b4d17 Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Wed, 27 Jul 2022 17:09:21 +0800 Subject: [PATCH 6/7] Update quickstart.md --- doc/doc_ch/quickstart.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/doc/doc_ch/quickstart.md b/doc/doc_ch/quickstart.md index e425cdd8a..6f5c617af 100644 --- a/doc/doc_ch/quickstart.md +++ b/doc/doc_ch/quickstart.md @@ -201,3 +201,7 @@ im_show.save('result.jpg') 通过本节内容，相信您已经熟练掌握PaddleOCR whl包的使用方法并获得了初步效果。 PaddleOCR是一套丰富领先实用的OCR工具库，打通数据、模型训练、压缩和推理部署全流程，您可以参考[文档教程](../../README_ch.md#文档教程)，正式开启PaddleOCR的应用之旅。 + + +traffic + From 32a76e5fbfe77631a2c55cd16b9b1e1bdace6047 Mon Sep 17 00:00:00 2001 From: Evezerest <50011306+Evezerest@users.noreply.github.com> Date: Wed, 27 Jul 2022 17:10:16 +0800 Subject: [PATCH 7/7] Update quickstart.md --- doc/doc_ch/quickstart.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/doc/doc_ch/quickstart.md b/doc/doc_ch/quickstart.md index 6f5c617af..997ead3e7 100644 --- a/doc/doc_ch/quickstart.md +++ b/doc/doc_ch/quickstart.md @@ -203,5 +203,5 @@ im_show.save('result.jpg') PaddleOCR是一套丰富领先实用的OCR工具库，打通数据、模型训练、压缩和推理部署全流程，您可以参考[文档教程](../../README_ch.md#文档教程)，正式开启PaddleOCR的应用之旅。 -traffic +trackgit-views