magic-pdf 1.3.11__py3-none-any.whl → 1.3.12__py3-none-any.whl

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/modeling/necks/rnn.py

@@ -9,14 +9,27 @@ class Im2Seq(nn.Module):
         super().__init__()
         self.out_channels = in_channels
 
+    # def forward(self, x):
+    #     B, C, H, W = x.shape
+    #     # assert H == 1
+    #     x = x.squeeze(dim=2)
+    #     # x = x.transpose([0, 2, 1])  # paddle (NTC)(batch, width, channels)
+    #     x = x.permute(0, 2, 1)
+    #     return x
+
     def forward(self, x):
         B, C, H, W = x.shape
-        # assert H == 1
-        x = x.squeeze(dim=2)
-        # x = x.transpose([0, 2, 1])  # paddle (NTC)(batch, width, channels)
-        x = x.permute(0, 2, 1)
-        return x
+        # 处理四维张量，将空间维度展平为序列
+        if H == 1:
+            # 原来的处理逻辑，适用于H=1的情况
+            x = x.squeeze(dim=2)
+            x = x.permute(0, 2, 1)  # (B, W, C)
+        else:
+            # 处理H不为1的情况
+            x = x.permute(0, 2, 3, 1)  # (B, H, W, C)
+            x = x.reshape(B, H * W, C)  # (B, H*W, C)
 
+        return x
 
 class EncoderWithRNN_(nn.Module):
     def __init__(self, in_channels, hidden_size):

magic_pdf/model/sub_modules/ocr/paddleocr2pytorch/pytorchocr/utils/resources/arch_config.yaml

@@ -104,6 +104,22 @@ ch_PP-OCRv4_det_infer:
     name: DBHead
     k: 50
 
+ch_PP-OCRv5_det_infer:
+  model_type: det
+  algorithm: DB
+  Transform: null
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.75
+    det: True
+  Neck:
+    name: RSEFPN
+    out_channels: 96
+    shortcut: True
+  Head:
+    name: DBHead
+    k: 50
+
 ch_PP-OCRv4_det_server_infer:
   model_type: det
   algorithm: DB
@@ -196,6 +212,58 @@ ch_PP-OCRv4_rec_server_doc_infer:
           nrtr_dim: 384
           max_text_length: 25
 
+ch_PP-OCRv5_rec_server_infer:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: PPHGNetV2_B4
+    text_rec: True
+  Head:
+    name: MultiHead
+    out_channels_list:
+      CTCLabelDecode: 18385
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [ 1, 3 ]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: 25
+
+ch_PP-OCRv5_rec_infer:
+  model_type: rec
+  algorithm: SVTR_HGNet
+  Transform:
+  Backbone:
+    name: PPLCNetV3
+    scale: 0.95
+  Head:
+    name: MultiHead
+    out_channels_list:
+      CTCLabelDecode: 18385
+    head_list:
+      - CTCHead:
+          Neck:
+            name: svtr
+            dims: 120
+            depth: 2
+            hidden_dims: 120
+            kernel_size: [ 1, 3 ]
+            use_guide: True
+          Head:
+            fc_decay: 0.00001
+      - NRTRHead:
+          nrtr_dim: 384
+          max_text_length: 25
+
 chinese_cht_PP-OCRv3_rec_infer:
   model_type: rec
   algorithm: SVTR