diff --git a/doc/doc_ch/dataset/layout_datasets.md b/doc/doc_ch/dataset/layout_datasets.md index e7055b4e607aae358a9ec1e93f3640b2b68ea4a1..728a9be5fdd33a78482adb1e705afea7117a3037 100644 --- a/doc/doc_ch/dataset/layout_datasets.md +++ b/doc/doc_ch/dataset/layout_datasets.md @@ -15,8 +15,8 @@ - **数据简介**:publaynet数据集的训练集合中包含35万张图像,验证集合中包含1.1万张图像。总共包含5个类别,分别是: `text, title, list, table, figure`。部分图像以及标注框可视化如下所示。
- - + +
- **下载地址**:https://developer.ibm.com/exchanges/data/all/publaynet/ @@ -30,8 +30,8 @@ - **数据简介**:CDLA据集的训练集合中包含5000张图像,验证集合中包含1000张图像。总共包含10个类别,分别是: `Text, Title, Figure, Figure caption, Table, Table caption, Header, Footer, Reference, Equation`。部分图像以及标注框可视化如下所示。
- - + +
- **下载地址**:https://github.com/buptlihang/CDLA @@ -45,8 +45,8 @@ - **数据简介**:TableBank数据集包含Latex(训练集187199张,验证集7265张,测试集5719张)与Word(训练集73383张,验证集2735张,测试集2281张)两种类别的文档。仅包含`Table` 1个类别。部分图像以及标注框可视化如下所示。
- - + +
- **下载地址**:https://doc-analysis.github.io/tablebank-page/index.html diff --git a/ppocr/modeling/backbones/kie_unet_sdmgr.py b/ppocr/modeling/backbones/kie_unet_sdmgr.py index 793c68c6ddd5883ff9fddf51c8f1ef752211a7c2..4b1bd8030060b26acb9e60bd671a5b23d936347b 100644 --- a/ppocr/modeling/backbones/kie_unet_sdmgr.py +++ b/ppocr/modeling/backbones/kie_unet_sdmgr.py @@ -176,11 +176,6 @@ class Kie_backbone(nn.Layer): x = self.img_feat(img) boxes, rois_num = self.bbox2roi(gt_bboxes) feats = paddle.vision.ops.roi_align( - x, - boxes, - spatial_scale=1.0, - pooled_height=7, - pooled_width=7, - rois_num=rois_num) + x, boxes, spatial_scale=1.0, output_size=7, boxes_num=rois_num) feats = self.maxpool(feats).squeeze(-1).squeeze(-1) return [relations, texts, feats] diff --git a/tools/export_model.py b/tools/export_model.py index c0cbcd361cec31c51616a7154836c234f076a86e..3ea0228f857a2fadb36678ecd3b91bc865e56e46 100755 --- a/tools/export_model.py +++ b/tools/export_model.py @@ -76,7 +76,7 @@ def export_single_model(model, arch_config, save_path, logger, quanter=None): else: infer_shape = [3, -1, -1] if arch_config["model_type"] == "rec": - infer_shape = [3, 32, -1] # for rec model, H must be 32 + infer_shape = [3, 48, -1] # for rec model, H must be 32 if "Transform" in arch_config and arch_config[ "Transform"] is not None and arch_config["Transform"][ "name"] == "TPS":