From 88f53144557c93ffce766a4a87712e4d0b29bbc0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?M=C3=A9lodie=20Boillet?= <boillet@teklia.com>
Date: Wed, 24 May 2023 14:09:36 +0200
Subject: [PATCH] Remove padding for ctc loss
---
dan/manager/ocr.py | 31 -------------------------------
1 file changed, 31 deletions(-)
diff --git a/dan/manager/ocr.py b/dan/manager/ocr.py
index ec98755a..45d851c3 100644
--- a/dan/manager/ocr.py
+++ b/dan/manager/ocr.py
@@ -14,7 +14,6 @@ from dan.ocr.utils import LM_str_to_ind
from dan.utils import (
pad_image,
pad_image_width_random,
- pad_image_width_right,
pad_images,
pad_sequences_1D,
rand,
@@ -154,37 +153,7 @@ class OCRDataset(GenericDataset):
sample["img_shape"] / self.reduce_dims_factor
).astype(int)
- # Padding to handle CTC requirements
if self.set_name == "train":
- max_label_len = 0
- height = 1
- ctc_padding = False
- if "CTC_line" in self.params["config"]["constraints"]:
- max_label_len = sample["label_len"]
- ctc_padding = True
- if "CTC_va" in self.params["config"]["constraints"]:
- max_label_len = max(sample["line_label_len"])
- ctc_padding = True
- if "CTC_pg" in self.params["config"]["constraints"]:
- max_label_len = sample["label_len"]
- height = max(sample["img_reduced_shape"][0], 1)
- ctc_padding = True
- if (
- ctc_padding
- and 2 * max_label_len + 1 > sample["img_reduced_shape"][1] * height
- ):
- sample["img"] = pad_image_width_right(
- sample["img"],
- int(
- np.ceil((2 * max_label_len + 1) / height)
- * self.reduce_dims_factor[1]
- ),
- self.padding_value,
- )
- sample["img_shape"] = sample["img"].shape
- sample["img_reduced_shape"] = np.ceil(
- sample["img_shape"] / self.reduce_dims_factor
- ).astype(int)
sample["img_reduced_shape"] = [
max(1, t) for t in sample["img_reduced_shape"]
]
--
GitLab