[Fix] Fix wrong ic13 textspotting split data; add lexicons to ic13, ic15 and totaltext (#1758)

* [Fix] Fix wrong ic13 textspotting split data; add lexicons to ic13, ic15 and totaltext

* [Fix] Fix wrong ic13 textspotting split data; add lexicons to ic13, ic15 and totaltext

* update

Author: gaotongxiao

dataset_zoo/icdar2013/textspotting.py

@@ -1,8 +1,38 @@
 _base_ = ['textdet.py']
 
 _base_.train_preparer.gatherer.img_dir = 'textdet_imgs/train'
-_base_.test_preparer.gatherer.img_dir = 'textdet_imgs/test'
 _base_.train_preparer.packer.type = 'TextSpottingPacker'
+
 _base_.test_preparer.packer.type = 'TextSpottingPacker'
+_base_.test_preparer.gatherer.img_dir = 'textdet_imgs/test'
+_base_.test_preparer.obtainer.files = [
+    dict(
+        url='https://rrc.cvc.uab.es/downloads/'
+        'Challenge2_Test_Task12_Images.zip',
+        save_name='ic13_textdet_test_img.zip',
+        md5='af2e9f070c4c6a1c7bdb7b36bacf23e3',
+        content=['image'],
+        mapping=[['ic13_textdet_test_img', 'textdet_imgs/test']]),
+    dict(
+        url='https://download.openmmlab.com/mmocr/data/1.x/'
+        'textspotting/icdar2013/ic13_textspotting_test_gt.zip',
+        save_name='ic13_textspotting_test_gt.zip',
+        md5='d0d95e800504795d153f4f21d4d8ce07',
+        content=['annotation'],
+        mapping=[['ic13_textspotting_test_gt', 'annotations/test']]),
+    dict(
+        url='https://download.openmmlab.com/mmocr/data/1.x/'
+        'textspotting/icdar2013/lexicons.zip',
+        save_name='icdar2013_lexicons.zip',
+        md5='4ba017ab0637dae7a66fa471ac0a3253',
+        content=['annotation'],
+        mapping=[['icdar2013_lexicons/lexicons', 'lexicons']]),
+]
+_base_.test_preparer.parser = dict(
+    type='ICDARTxtTextDetAnnParser', encoding='utf-8-sig')
 
+delete = [
+    'annotations', 'ic13_textdet_train_img', 'ic13_textdet_train_gt',
+    'ic13_textdet_test_img', 'ic13_textdet_test_gt', 'icdar2013_lexicons'
+]
 config_generator = dict(type='TextSpottingConfigGenerator')

dataset_zoo/icdar2015/textspotting.py

@@ -1,7 +1,35 @@
 _base_ = ['textdet.py']
+
 _base_.train_preparer.gatherer.img_dir = 'textdet_imgs/train'
-_base_.test_preparer.gatherer.img_dir = 'textdet_imgs/test'
 _base_.train_preparer.packer.type = 'TextSpottingPacker'
+
+_base_.test_preparer.gatherer.img_dir = 'textdet_imgs/test'
 _base_.test_preparer.packer.type = 'TextSpottingPacker'
+_base_.test_preparer.obtainer.files = [
+    dict(
+        url='https://rrc.cvc.uab.es/downloads/ch4_test_images.zip',
+        save_name='ic15_textdet_test_img.zip',
+        md5='97e4c1ddcf074ffcc75feff2b63c35dd',
+        content=['image'],
+        mapping=[['ic15_textdet_test_img', 'textdet_imgs/test']]),
+    dict(
+        url='https://rrc.cvc.uab.es/downloads/'
+        'Challenge4_Test_Task4_GT.zip',
+        save_name='ic15_textdet_test_gt.zip',
+        md5='8bce173b06d164b98c357b0eb96ef430',
+        content=['annotation'],
+        mapping=[['ic15_textdet_test_gt', 'annotations/test']]),
+    dict(
+        url='https://download.openmmlab.com/mmocr/data/1.x/'
+        'textspotting/icdar2015/lexicons.zip',
+        save_name='icdar2015_lexicons.zip',
+        md5='daec48ee72de25a4293a6b12cdc181f5',
+        content=['annotation'],
+        mapping=[['icdar2015_lexicons/lexicons', 'lexicons']]),
+]
 
 config_generator = dict(type='TextSpottingConfigGenerator')
+delete = [
+    'annotations', 'ic15_textdet_test_img', 'ic15_textdet_train_img',
+    'icdar2015_lexicons'
+]

dataset_zoo/totaltext/textspotting.py

@@ -1,8 +1,34 @@
 _base_ = ['textdet.py']
 
 _base_.train_preparer.gatherer.img_dir = 'textdet_imgs/train'
-_base_.test_preparer.gatherer.img_dir = 'textdet_imgs/test'
 _base_.train_preparer.packer.type = 'TextSpottingPacker'
+
+_base_.test_preparer.gatherer.img_dir = 'textdet_imgs/test'
 _base_.test_preparer.packer.type = 'TextSpottingPacker'
+_base_.test_preparer.obtainer.files = [
+    dict(
+        url='https://universityofadelaide.box.com/shared/static/'
+        '8xro7hnvb0sqw5e5rxm73tryc59j6s43.zip',
+        save_name='totaltext.zip',
+        md5='5b56d71a4005a333cf200ff35ce87f75',
+        content=['image'],
+        mapping=[['totaltext/Images/Test', 'textdet_imgs/test']]),
+    dict(
+        url='https://universityofadelaide.box.com/shared/static/'
+        '2vmpvjb48pcrszeegx2eznzc4izan4zf.zip',
+        save_name='txt_format.zip',
+        md5='53377a83420b4a0244304467512134e8',
+        content=['annotation'],
+        mapping=[['txt_format/Test', 'annotations/test']]),
+    dict(
+        url='https://download.openmmlab.com/mmocr/data/1.x/'
+        'textspotting/totaltext/lexicons.tar.gz',
+        save_name='totaltext_lexicons.tar.gz',
+        md5='59e3dd01ee83355043ac69437e2e2ff2',
+        content=['annotation'],
+        mapping=[['totaltext_lexicons/lexicons', 'lexicons']]),
+]
+
+delete = ['totaltext', 'txt_format', 'annotations', 'totaltext_lexicons']
 
 config_generator = dict(type='TextSpottingConfigGenerator')