Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into dygraph

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。
 
 <div align="center">
-    <img src="../datasets/publaynet_demo/gt_PMC3724501_00006.jpg" width="500">
-    <img src="../datasets/publaynet_demo/gt_PMC5086060_00002.jpg" width="500">
+    <img src="../../datasets/publaynet_demo/gt_PMC3724501_00006.jpg" width="500">
+    <img src="../../datasets/publaynet_demo/gt_PMC5086060_00002.jpg" width="500">
 </div>
 
 - **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。
 
 <div align="center">
-    <img src="../datasets/CDLA_demo/val_0633.jpg" width="500">
-    <img src="../datasets/CDLA_demo/val_0941.jpg" width="500">
+    <img src="../../datasets/CDLA_demo/val_0633.jpg" width="500">
+    <img src="../../datasets/CDLA_demo/val_0941.jpg" width="500">
 </div>
 
 - **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。
 
 <div align="center">
-    <img src="../datasets/tablebank_demo/004.png" height="700">
-    <img src="../datasets/tablebank_demo/005.png" height="700">
+    <img src="../../datasets/tablebank_demo/004.png" height="700">
+    <img src="../../datasets/tablebank_demo/005.png" height="700">
 </div>
 
 - **下载地址**：https://doc-analysis.github.io/tablebank-page/index.html

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]

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":