onnxtr 0.3.1__py3-none-any.whl → 0.3.2__py3-none-any.whl

onnxtr/models/preprocessor/base.py

@@ -67,11 +67,12 @@ class PreProcessor(NestedObject):
             if x.dtype not in (np.uint8, np.float32):
                 raise TypeError("unsupported data type for numpy.ndarray")
         x = shape_translate(x, "HWC")
+
+        # Resizing
+        x = self.resize(x)
         # Data type & 255 division
         if x.dtype == np.uint8:
             x = x.astype(np.float32) / 255.0
-        # Resizing
-        x = self.resize(x)
 
         return x
 
@@ -95,13 +96,12 @@ class PreProcessor(NestedObject):
                     raise TypeError("unsupported data type for numpy.ndarray")
             x = shape_translate(x, "BHWC")
 
-            # Data type & 255 division
-            if x.dtype == np.uint8:
-                x = x.astype(np.float32) / 255.0
             # Resizing
             if (x.shape[1], x.shape[2]) != self.resize.output_size:
                 x = np.array([self.resize(sample) for sample in x])
-
+            # Data type & 255 division
+            if x.dtype == np.uint8:
+                x = x.astype(np.float32) / 255.0
             batches = [x]
 
         elif isinstance(x, list) and all(isinstance(sample, np.ndarray) for sample in x):

onnxtr/transforms/base.py

@@ -5,8 +5,8 @@
 
 from typing import Tuple, Union
 
-import cv2
 import numpy as np
+from PIL import Image, ImageOps
 
 __all__ = ["Resize", "Normalize"]
 
@@ -17,64 +17,51 @@ class Resize:
     def __init__(
         self,
         size: Union[int, Tuple[int, int]],
-        interpolation=cv2.INTER_LINEAR,
+        interpolation=Image.Resampling.BILINEAR,
         preserve_aspect_ratio: bool = False,
         symmetric_pad: bool = False,
     ) -> None:
-        super().__init__()
-        self.size = size
+        self.size = size if isinstance(size, tuple) else (size, size)
         self.interpolation = interpolation
         self.preserve_aspect_ratio = preserve_aspect_ratio
         self.symmetric_pad = symmetric_pad
         self.output_size = size if isinstance(size, tuple) else (size, size)
 
-        if not isinstance(self.size, (int, tuple, list)):
-            raise AssertionError("size should be either a tuple, a list or an int")
+        if not isinstance(self.size, (tuple, int)):
+            raise AssertionError("size should be either a tuple or an int")
 
-    def __call__(
-        self,
-        img: np.ndarray,
-    ) -> np.ndarray:
-        if img.ndim == 3:
-            h, w = img.shape[0:2]
-        else:
-            h, w = img.shape[1:3]
-        sh, sw = self.size if isinstance(self.size, tuple) else (self.size, self.size)
+    def __call__(self, img: np.ndarray) -> np.ndarray:
+        img = (img * 255).astype(np.uint8) if img.dtype != np.uint8 else img
+        h, w = img.shape[:2] if img.ndim == 3 else img.shape[1:3]
+        sh, sw = self.size
 
-        # Calculate aspect ratio of the image
-        aspect = w / h
+        if not self.preserve_aspect_ratio:
+            return np.array(Image.fromarray(img).resize((sw, sh), resample=self.interpolation))
 
-        # Compute scaling and padding sizes
-        if self.preserve_aspect_ratio:
-            if aspect > 1:  # Horizontal image
-                new_w = sw
-                new_h = int(sw / aspect)
-            elif aspect < 1:  # Vertical image
-                new_h = sh
-                new_w = int(sh * aspect)
-            else:  # Square image
-                new_h, new_w = sh, sw
-
-            img_resized = cv2.resize(img, (new_w, new_h), interpolation=self.interpolation)
-
-            # Calculate padding
-            pad_top = max((sh - new_h) // 2, 0)
-            pad_bottom = max(sh - new_h - pad_top, 0)
-            pad_left = max((sw - new_w) // 2, 0)
-            pad_right = max(sw - new_w - pad_left, 0)
-
-            # Pad the image
-            img_resized = cv2.copyMakeBorder(  # type: ignore[call-overload]
-                img_resized, pad_top, pad_bottom, pad_left, pad_right, borderType=cv2.BORDER_CONSTANT, value=0
-            )
-
-            # Ensure the image matches the target size by resizing it again if needed
-            img_resized = cv2.resize(img_resized, (sw, sh), interpolation=self.interpolation)
+        actual_ratio = h / w
+        target_ratio = sh / sw
+
+        if target_ratio == actual_ratio:
+            return np.array(Image.fromarray(img).resize((sw, sh), resample=self.interpolation))
+
+        if actual_ratio > target_ratio:
+            tmp_size = (int(sh / actual_ratio), sh)
         else:
-            # Resize the image without preserving aspect ratio
-            img_resized = cv2.resize(img, (sw, sh), interpolation=self.interpolation)
+            tmp_size = (sw, int(sw * actual_ratio))
+
+        img_resized = Image.fromarray(img).resize(tmp_size, resample=self.interpolation)
+        pad_left = pad_top = 0
+        pad_right = sw - img_resized.width
+        pad_bottom = sh - img_resized.height
+
+        if self.symmetric_pad:
+            pad_left = pad_right // 2
+            pad_right -= pad_left
+            pad_top = pad_bottom // 2
+            pad_bottom -= pad_top
 
-        return img_resized
+        img_resized = ImageOps.expand(img_resized, (pad_left, pad_top, pad_right, pad_bottom))
+        return np.array(img_resized)
 
     def __repr__(self) -> str:
         interpolate_str = self.interpolation

onnxtr/utils/fonts.py

@@ -5,14 +5,16 @@
 
 import logging
 import platform
-from typing import Optional
+from typing import Optional, Union
 
 from PIL import ImageFont
 
 __all__ = ["get_font"]
 
 
-def get_font(font_family: Optional[str] = None, font_size: int = 13) -> ImageFont.ImageFont:
+def get_font(
+    font_family: Optional[str] = None, font_size: int = 13
+) -> Union[ImageFont.FreeTypeFont, ImageFont.ImageFont]:
     """Resolves a compatible ImageFont for the system
 
     Args:
@@ -29,7 +31,7 @@ def get_font(font_family: Optional[str] = None, font_size: int = 13) -> ImageFon
         try:
             font = ImageFont.truetype("FreeMono.ttf" if platform.system() == "Linux" else "Arial.ttf", font_size)
         except OSError:  # pragma: no cover
-            font = ImageFont.load_default()
+            font = ImageFont.load_default()  # type: ignore[assignment]
             logging.warning(
                 "unable to load recommended font family. Loading default PIL font,"
                 "font size issues may be expected."

onnxtr/version.py

@@ -1 +1 @@
-__version__ = 'v0.3.1'
+__version__ = 'v0.3.2'

{onnxtr-0.3.1.dist-info → onnxtr-0.3.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: onnxtr
-Version: 0.3.1
+Version: 0.3.2
 Summary: Onnx Text Recognition (OnnxTR): docTR Onnx-Wrapper for high-performance OCR on documents.
 Author-email: Felix Dittrich <felixdittrich92@gmail.com>
 Maintainer: Felix Dittrich

{onnxtr-0.3.1.dist-info → onnxtr-0.3.2.dist-info}/RECORD

@@ -1,7 +1,7 @@
 onnxtr/__init__.py,sha256=h7Wc2tuHLsaoCk5xNpEFEK-g11A6SJA7nAasA76TQ_Y,100
 onnxtr/file_utils.py,sha256=WjUKalEdR53aoeIY4e-ihy3r7J_C9qFxL40JHGPfutc,1107
 onnxtr/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-onnxtr/version.py,sha256=ywGt0EZ270HVUZZWcczHcQLiONeX32LjZhVbRTZg_qk,23
+onnxtr/version.py,sha256=Mqv-IS8XNTfhjRfomiPmqTyHtOUKl9tLeE2KEmYIkeM,23
 onnxtr/contrib/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 onnxtr/contrib/artefacts.py,sha256=tdmfhvfXVRYEH7uj4_hqf2cuUGoTieyNK8bXsD3zHwo,5383
 onnxtr/contrib/base.py,sha256=KyJ8_zDSKEWSFBszgCbLjEeI7SKg4N_iH_ZQNf90SWQ,3288
@@ -39,7 +39,7 @@ onnxtr/models/predictor/__init__.py,sha256=XL25XkRkgyK7mldF-CWhg2MMakSdP5vLpDLwL
 onnxtr/models/predictor/base.py,sha256=VUs1OIsb8FW91U1ehB1sBaxG4Suz8iS-Ut50Zt6_SHo,8860
 onnxtr/models/predictor/predictor.py,sha256=etxgAvT8cYhboPyHiDRO0BL1rBoTw5lL1vhZP4dHWqw,6247
 onnxtr/models/preprocessor/__init__.py,sha256=ERmmOxz_9mUkIuccNbzUa5Y6gVLLVDdyc4cCxbCCUbY,20
-onnxtr/models/preprocessor/base.py,sha256=f0t0rMCzvuxwgq7jlKvcVWyjeDOx7yCLUw52quEaETM,3990
+onnxtr/models/preprocessor/base.py,sha256=8ZCKsB-o9uRaUm0x4x9FYpYxLXpwHyq2nVv_TlRgaMw,3990
 onnxtr/models/recognition/__init__.py,sha256=h1bZs55iLJBMATtzS4ntTKwfD6OGXBiiqGv_hEnOFnE,41
 onnxtr/models/recognition/core.py,sha256=0Q1dVXqRcDUr_ycT5tpoSH9-zuDF58GtnmxWpUS8Ibo,739
 onnxtr/models/recognition/utils.py,sha256=04abbjx-_OuF5iEANWIAOK3tQQl1tExPmBQx4IG04Lc,3569
@@ -54,20 +54,20 @@ onnxtr/models/recognition/predictor/__init__.py,sha256=ERmmOxz_9mUkIuccNbzUa5Y6g
 onnxtr/models/recognition/predictor/_utils.py,sha256=ZNm5I7ibiWfTlz302uiifCkUOu65YWa-oUBUMPrrUuQ,3406
 onnxtr/models/recognition/predictor/base.py,sha256=YvqSNEM3rCEttxl6hsC9zl1R97N9zO2WZfD5_-nfkR0,2483
 onnxtr/transforms/__init__.py,sha256=ERmmOxz_9mUkIuccNbzUa5Y6gVLLVDdyc4cCxbCCUbY,20
-onnxtr/transforms/base.py,sha256=KohBfq5qNkw9aznZtlGlphNlfKSRBhm5An6TcUiFA7M,3965
+onnxtr/transforms/base.py,sha256=sVQIIQLzPRl0Uc6OyDGrJ4H_f6CMune5j0C9VVRAV0s,3577
 onnxtr/utils/__init__.py,sha256=pESRJKtcQyjRxiMgZPhtPYeLbCj-YSGyMVRHTbcMONU,94
 onnxtr/utils/common_types.py,sha256=eC_NyIwbo9qVF33LiNPqHKfyabWq9mYEKD9gAloo5UU,601
 onnxtr/utils/data.py,sha256=Dh0mgeHJhyPwmm63J90uDVmIYbrp63hh1_SnYLnpgJI,4354
-onnxtr/utils/fonts.py,sha256=OiOHFwkjN4L7QBrzMi7Ex7qj_KcTEJ1sHEJWSfiGNZU,1281
+onnxtr/utils/fonts.py,sha256=27v0cojgUrVxNF8Krb1FybSoykoxFy1XjG8lHRUuiEY,1353
 onnxtr/utils/geometry.py,sha256=u9ei6WW8Yd29rtwnrDYercAY-tWkOLkzBd5Oi6NNyDI,17774
 onnxtr/utils/multithreading.py,sha256=30T7AylM3rb52ZEI3Pk1pfB0VYraTbc7yO2vNODVVFY,2011
 onnxtr/utils/reconstitution.py,sha256=Hx1_ddLevKLzuxXc19UelPdsGlAwqi4f6vRSYKHDUB4,2617
 onnxtr/utils/repr.py,sha256=kfbjGL6KymGT8spo2UL4FJXZ0XRwa7CO7Y1dTVR8dIk,2129
 onnxtr/utils/visualization.py,sha256=CX09qvDnNIw3BFW5F3jM4R9OcpLWAeZyoDyTAOGRvls,9925
 onnxtr/utils/vocabs.py,sha256=SCQ4XQjbHSxunj1tg2iHRiPfE8OaTAMhcJbKq5BNvFs,3138
-onnxtr-0.3.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-onnxtr-0.3.1.dist-info/METADATA,sha256=5bzc3Hu83w_57K6-kow6sJ8rf25eJE9KxJtzGpSUkKU,29802
-onnxtr-0.3.1.dist-info/WHEEL,sha256=mguMlWGMX-VHnMpKOjjQidIo1ssRlCFu4a4mBpz1s2M,91
-onnxtr-0.3.1.dist-info/top_level.txt,sha256=r_MSUTpspp4pWEEWvly-s7ZkfCg1KwrK6-kBlXkWKU8,7
-onnxtr-0.3.1.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
-onnxtr-0.3.1.dist-info/RECORD,,
+onnxtr-0.3.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+onnxtr-0.3.2.dist-info/METADATA,sha256=I9n5apYunvpxpSy36h-UtfNYl8eW3WOLpnPujaKUzgo,29802
+onnxtr-0.3.2.dist-info/WHEEL,sha256=y4mX-SOX4fYIkonsAGA5N0Oy-8_gI4FXw5HNI1xqvWg,91
+onnxtr-0.3.2.dist-info/top_level.txt,sha256=r_MSUTpspp4pWEEWvly-s7ZkfCg1KwrK6-kBlXkWKU8,7
+onnxtr-0.3.2.dist-info/zip-safe,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
+onnxtr-0.3.2.dist-info/RECORD,,

{onnxtr-0.3.1.dist-info → onnxtr-0.3.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (70.1.1)
+Generator: setuptools (70.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any