From 6d2bc9f573736a54965b0b656db9fd8d12a32726 Mon Sep 17 00:00:00 2001
From: liuhongen1234567 <65936492+liuhongen1234567@users.noreply.github.com>
Date: Mon, 2 Dec 2024 20:03:12 +0800
Subject: [PATCH] add d2s_train_image_shape for static train (#14312)

---
 configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml       | 1 +
 configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml | 2 +-
 configs/rec/SVTRv2/rec_repsvtr_ch.yml          | 1 +
 configs/rec/SVTRv2/rec_svtrv2_ch.yml           | 2 +-
 configs/rec/rec_latex_ocr.yml                  | 1 +
 configs/table/SLANet_ch.yml                    | 1 +
 ppocr/modeling/heads/rec_nrtr_head.py          | 3 ++-
 7 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml b/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml
index 827f5eef3..8bdb819b5 100644
--- a/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml
+++ b/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec.yml
@@ -19,6 +19,7 @@ Global:
   use_space_char: true
   distributed: true
   save_res_path: ./output/rec/predicts_ppocrv3.txt
+  d2s_train_image_shape: [3, 48, 320]
 
 
 Optimizer:
diff --git a/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml b/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml
index dba966e7c..7316dbeba 100644
--- a/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml
+++ b/configs/rec/PP-OCRv4/ch_PP-OCRv4_rec_hgnet.yml
@@ -19,7 +19,7 @@ Global:
   use_space_char: true
   distributed: true
   save_res_path: ./output/rec/predicts_ppocrv3.txt
-
+  d2s_train_image_shape: [3, 48, 320]
 
 Optimizer:
   name: Adam
diff --git a/configs/rec/SVTRv2/rec_repsvtr_ch.yml b/configs/rec/SVTRv2/rec_repsvtr_ch.yml
index 4fd643bc9..d1f692350 100644
--- a/configs/rec/SVTRv2/rec_repsvtr_ch.yml
+++ b/configs/rec/SVTRv2/rec_repsvtr_ch.yml
@@ -19,6 +19,7 @@ Global:
   use_space_char: true
   distributed: true
   save_res_path: ./output/rec/predicts_repsvtr.txt
+  d2s_train_image_shape: [3, 48, 320]
 
 Optimizer:
   name: AdamW
diff --git a/configs/rec/SVTRv2/rec_svtrv2_ch.yml b/configs/rec/SVTRv2/rec_svtrv2_ch.yml
index 70efe1093..e954ec904 100644
--- a/configs/rec/SVTRv2/rec_svtrv2_ch.yml
+++ b/configs/rec/SVTRv2/rec_svtrv2_ch.yml
@@ -19,7 +19,7 @@ Global:
   use_space_char: true
   distributed: true
   save_res_path: ./output/rec/predicts_svrtv2.txt
-
+  d2s_train_image_shape: [3, 48, 320]
 
 Optimizer:
   name: AdamW
diff --git a/configs/rec/rec_latex_ocr.yml b/configs/rec/rec_latex_ocr.yml
index 2c604bf81..f87a10848 100644
--- a/configs/rec/rec_latex_ocr.yml
+++ b/configs/rec/rec_latex_ocr.yml
@@ -18,6 +18,7 @@ Global:
   use_space_char: False
   rec_char_dict_path:  ppocr/utils/dict/latex_ocr_tokenizer.json
   save_res_path: ./output/rec/predicts_latexocr.txt
+  d2s_train_image_shape: [1,256,256]
 
 Optimizer:
   name: AdamW
diff --git a/configs/table/SLANet_ch.yml b/configs/table/SLANet_ch.yml
index c16f7efed..70ea66970 100644
--- a/configs/table/SLANet_ch.yml
+++ b/configs/table/SLANet_ch.yml
@@ -21,6 +21,7 @@ Global:
   infer_mode: False
   use_sync_bn: True
   save_res_path: output/infer
+  d2s_train_image_shape: [3, 488, 488]
 
 Optimizer:
   name: Adam
diff --git a/ppocr/modeling/heads/rec_nrtr_head.py b/ppocr/modeling/heads/rec_nrtr_head.py
index ad01438be..423d5a11a 100644
--- a/ppocr/modeling/heads/rec_nrtr_head.py
+++ b/ppocr/modeling/heads/rec_nrtr_head.py
@@ -355,7 +355,8 @@ class Transformer(nn.Layer):
         """
         mask = paddle.zeros([sz, sz], dtype="float32")
         mask_inf = paddle.triu(
-            paddle.full(shape=[sz, sz], dtype="float32", fill_value="-inf"), diagonal=1
+            paddle.full(shape=[sz, sz], dtype="float32", fill_value=float("-inf")),
+            diagonal=1,
         )
         mask = mask + mask_inf
         return mask.unsqueeze([0, 1])