Trying to recognize image that contain vertical Traditional Chinese text by the following code.
import cv2
import pytesseract
# Read image
img = cv2.imread('image3.png')
custom_config = r'--oem 2 --psm 5'
result = pytesseract.image_to_string(img, lang='chi_tra_vert', config=custom_config)
print(result)
It got the following error.
File "ic03.py", line 49, in <module>
result = pytesseract.image_to_string(img, lang='chi_tra_vert', config=custom_config)
File "/mnt/data1/home/ray/pyenv/venv/lib/python3.8/site-packages/pytesseract/pytesseract.py", line 423, in image_to_string
return {
File "/mnt/data1/home/ray/pyenv/venv/lib/python3.8/site-packages/pytesseract/pytesseract.py", line 426, in <lambda>
Output.STRING: lambda: run_and_get_output(*args),
File "/mnt/data1/home/ray/pyenv/venv/lib/python3.8/site-packages/pytesseract/pytesseract.py", line 288, in run_and_get_output
run_tesseract(**kwargs)
File "/mnt/data1/home/ray/pyenv/venv/lib/python3.8/site-packages/pytesseract/pytesseract.py", line 264, in run_tesseract
raise TesseractError(proc.returncode, get_errors(error_string))
pytesseract.pytesseract.TesseractError: (1, "Error: Tesseract (legacy) engine requested, but components are not present in /usr/share/tesseract-ocr/4.00/tessdata/chi_tra_vert.traineddata!! Failed loading language 'chi_tra_vert'
Same code work for lang='chi_tra' which recognize Horizontal Chinese Text and lang='eng'.
I have already downloaded and updated the file from the repo https://github.com/tesseract-ocr/tessdata.
Please advise what else I can try. Thanks.
A want to resolve coreferences without Internet using AllenNLP and coref-spanbert-large model.
I try to do it in the way that is describing here https://demo.allennlp.org/coreference-resolution
My code:
from allennlp.predictors.predictor import Predictor
import allennlp_models.tagging
predictor = Predictor.from_path(r"C:\Users\aap\Desktop\coref-spanbert-large-2021.03.10.tar.gz")
example = 'Paul Allen was born on January 21, 1953, in Seattle, Washington, to Kenneth Sam Allen and Edna Faye Allen.Allen attended Lakeside School, a private school in Seattle, where he befriended Bill Gates, two years younger, with whom he shared an enthusiasm for computers.'
pred = predictor.predict(document=example)
coref_res = predictor.coref_resolved(example)
print(pred)
print(coref_res)
When I have an access to internet the code works correctly.
But when I don't have an access to internet I get the following errors:
Traceback (most recent call last):
File "C:/Users/aap/Desktop/CoreNLP/Coref_AllenNLP.py", line 14, in <module>
predictor = Predictor.from_path(r"C:\Users\aap\Desktop\coref-spanbert-large-2021.03.10.tar.gz")
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\predictors\predictor.py", line 361, in from_path
load_archive(archive_path, cuda_device=cuda_device, overrides=overrides),
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\models\archival.py", line 206, in load_archive
config.duplicate(), serialization_dir
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\models\archival.py", line 232, in _load_dataset_readers
dataset_reader_params, serialization_dir=serialization_dir
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 604, in from_params
**extras,
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 632, in from_params
kwargs = create_kwargs(constructor_to_inspect, cls, params, **extras)
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 200, in create_kwargs
cls.__name__, param_name, annotation, param.default, params, **extras
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 307, in pop_and_construct_arg
return construct_arg(class_name, name, popped_params, annotation, default, **extras)
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 391, in construct_arg
**extras,
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 341, in construct_arg
return annotation.from_params(params=popped_params, **subextras)
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 604, in from_params
**extras,
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\from_params.py", line 634, in from_params
return constructor_to_call(**kwargs) # type: ignore
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\data\token_indexers\pretrained_transformer_mismatched_indexer.py", line 63, in __init__
**kwargs,
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\data\token_indexers\pretrained_transformer_indexer.py", line 58, in __init__
model_name, tokenizer_kwargs=tokenizer_kwargs
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\data\tokenizers\pretrained_transformer_tokenizer.py", line 71, in __init__
model_name, add_special_tokens=False, **tokenizer_kwargs
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\allennlp\common\cached_transformers.py", line 110, in get_tokenizer
**kwargs,
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\models\auto\tokenization_auto.py", line 362, in from_pretrained
config = AutoConfig.from_pretrained(pretrained_model_name_or_path, **kwargs)
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\models\auto\configuration_auto.py", line 368, in from_pretrained
config_dict, _ = PretrainedConfig.get_config_dict(pretrained_model_name_or_path, **kwargs)
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\configuration_utils.py", line 424, in get_config_dict
use_auth_token=use_auth_token,
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\file_utils.py", line 1087, in cached_path
local_files_only=local_files_only,
File "C:\Users\aap\Desktop\CoreNLP\corenlp\lib\site-packages\transformers\file_utils.py", line 1268, in get_from_cache
"Connection error, and we cannot find the requested files in the cached path."
ValueError: Connection error, and we cannot find the requested files in the cached path. Please try again or make sure your Internet connection is on.
Process finished with exit code 1
Please, say me, what do I need to do my code works without Internet?
You will need a local copy of transformer model's configuration file and vocabulary so that the tokenizer and token indexer don't need to download those:
from transformers import AutoConfig, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained(transformer_model_name)
config = AutoConfig.from_pretrained(transformer_model_name)
tokenizer.save_pretrained(local_config_path)
config.to_json_file(local_config_path + "/config.json")
You will then need to override the transformer model name in the configuration file to the local directory (local_config_path) where you saved these things:
predictor = Predictor.from_path(
r"C:\Users\aap\Desktop\coref-spanbert-large-2021.03.10.tar.gz",
overrides={
"dataset_reader.token_indexers.tokens.model_name": local_config_path,
"validation_dataset_reader.token_indexers.tokens.model_name": local_config_path,
"model.text_field_embedder.tokens.model_name": local_config_path,
},
)
I have run into similar problem when using structured-prediction-srl-bert without internet, and I saw in the logs 4 item for downloads:
dataset_reader.bert_model_name = bert-base-uncased, Downloading 4 files
model INFO vocabulary.py - Loading token dictionary from data/structured-prediction-srl-bert.2020.12.15/vocabulary. Downloading... 4x smaller files
Spacy models 'en_core_web_sm' not found
later on, [nltk_data] Error loading punkt: <urlopen error [Errno -3] Temporary failure in name resolution> [nltk_data] Error loading wordnet: <urlopen error [Errno -3] Temporary failure in name resolution>
I have solved it with these steps:
structured-prediction-srl-bert:
I have downloaded the structured-prediction-srl-bert.2020.12.15.tar.gz from the https://demo.allennlp.org/semantic-role-labeling (Model Card tab) -
https://storage.googleapis.com/allennlp-public-models/structured-prediction-srl-bert.2020.12.15.tar.gz
I have unzipped it into ./data/structured-prediction-srl-bert.2020.12.15
The code:
pip install allennlp==2.10.0 allennlp-models==2.10.0
from allennlp.predictors.predictor import Predictor
predictor = Predictor.from_path("./data/structured-prediction-srl-bert.2020.12.15/")
bert-base-uncased
I have created a folder ./data/bert-base-uncased and there I have downloaded these files from https://huggingface.co/bert-base-uncased/tree/main
config.json
tokenizer.json
tokenizer_config.json
vocab.txt
pytorch_model.bin
Aditionally, I had to change the "bert_model_name" from "bert-base-uncased" into a path "./data/bert-base-uncased", the earlier causes the download. This has to be done in the ./data/structured-prediction-srl-bert.2020.12.15/config.json , and there are two occurences.
python -m spacy download en_core_web_sm
python -c 'import nltk; nltk.download("punkt"); nltk.download("wordnet")'
After these steps the allennlp did not need internet anymore.
I'm using a NAO robot with naoqi version 2.1 and Choregraphe on Windows. I want to parse json from an attached file to the behavior. I attached the file like in that link.
Code:
def onLoad(self):
self.filepath = os.path.join(os.path.dirname(ALFrameManager.getBehaviorPath(self.behaviorId)), "fileName.json")
def onInput_onStart(self):
with open(self.filepath, "r") as f:
self.data = self.json.load(f.get_Response())
self.dataFromFile = self.data['value']
self.log("Data from file: " + str(self.dataFromFile))
But when I run this code on the robot (connected with a router) I'll get an error:
[ERROR] behavior.box :_safeCallOfUserMethod:281 _Behavior__lastUploadedChoregrapheBehaviorbehavior_1136151280__root__AbfrageKontostand_3__AuslesenJSONDatei_1: Traceback (most recent call last):
File "/usr/lib/python2.7/site-packages/naoqi.py", line 271, in _safeCallOfUserMethod
func()
File "<string>", line 20, in onInput_onStart
File "/usr/lib/python2.7/site-packages/inaoqi.py", line 265, in <lambda>
__getattr__ = lambda self, name: _swig_getattr(self, behavior, name)
File "/usr/lib/python2.7/site-packages/inaoqi.py", line 55, in _swig_getattr
raise AttributeError(name)
AttributeError: json
I already tried to understand the code from the correspondending lines but I couldn't fixed the error. But I know that the type of my object f is 'file'. How can I open the json file as a json file?
Your problem comes from this:
self.json.load(f.get_Response())
... there is no such thing as "self.json" on a Choregraphe box, import json and then do json.load. And what is get_Response ? That method doesn't exist on anything in Python that I know of.
You might want to first try making a standalone python script (that doesn't use the robot) that can read your json file before you try it with choregraphe. It will be easier.
I am trying to use stanford POS tagger in NLTK by the following code:
import nltk
from nltk.tag.stanford import POSTagger
st = POSTagger('E:\Assistant\models\english-bidirectional-distsim.tagger',
'E:\Assistant\stanford-postagger.jar')
st.tag('What is the airspeed of an unladen swallow?'.split())
and here is the output:
Traceback (most recent call last):
File "E:\J2EE\eclipse\WSNLP\nlp\src\tagger.py", line 5, in <module>
st.tag('What is the airspeed of an unladen swallow?'.split())
File "C:\Python34\lib\site-packages\nltk\tag\stanford.py", line 59, in tag
return self.tag_sents([tokens])[0]
File "C:\Python34\lib\site-packages\nltk\tag\stanford.py", line 81, in tag_sents
stdout=PIPE, stderr=PIPE)
File "C:\Python34\lib\site-packages\nltk\internals.py", line 153, in java
p = subprocess.Popen(cmd, stdin=stdin, stdout=stdout, stderr=stderr)
File "C:\Python34\lib\subprocess.py", line 858, in __init__
restore_signals, start_new_session)
File "C:\Python34\lib\subprocess.py", line 1111, in _execute_child
startupinfo)
OSError: [WinError 193] %1 is not a valid Win32 application
P.S. My java home is set and I have no problem with my java installation. Can someone explain what this error is talking about? It is not informative for me. Thanks in advance.
Looks like your Java installation is botched or missing.
It worked after a lot of trial and error:
It seems that NLTK Internal cannot find the java binary automatically on windows, so we need to identify it as follows:
import os
import nltk
from nltk.tag.stanford import POSTagger
os.environ['JAVA_HOME'] = r'C:\Program Files\Java\jre6\bin'
st = POSTagger('E:\stanford-postagger-2014-10-26\models\english-left3words-distsim.tagger',
'E:\stanford-postagger-2014-10-26\stanford-postagger.jar')
st.tag(nltk.word_tokenize('What is the airspeed of an unladen swallow?'))
As one of the gurus said to me: "don't forget to add "r" while working with "\" in strings."
I have a question to Ctypes and do not know what I do wrong. And yes, I am a newbie for Python and searched the other posts in here. So any advice is appreciated.
What do I want to do :
I simply want to load the FXCM C++ APP fundtions into Python 3.3 so I can call them for connecting to their server.
As it seems Ctypes seems to be the best tool. So a simple code in Python :
import os
dirlist = os.listdir('ForexConnectAPIx64/bin')
from pprint import pprint
pprint(dirlist)
from ctypes import *
myDll = cdll.LoadLibrary ("ForexConnectAPIx64/bin/ForexConnect.dll")
gives a result :
Traceback (most recent call File "C:\Users\scaberia3\Python_Projects \FTC\ListDir_Test.py", line 20, in <module>
myDll = cdll.LoadLibrary ("ForexConnectAPIx64/bin/ForexConnect.dll")
File "C:\Python33\lib\ctypes\__init__.py", line 431, in LoadLibrary
return self._dlltype(name)
File "C:\Python33\lib\ctypes\__init__.py", line 353, in __init__
self._handle = _dlopen(self._name, mode)
OSError: [WinError 126] Das angegebene Modul wurde nicht gefunden (Module not found)
['ForexConnect.dll',
'fxmsg.dll',
'gsexpat.dll',
'gslibeay32.dll',
'gsssleay32.dll',
'gstool2.dll',
'gszlib.dll',
'java',
'log4cplus.dll',
'msvcp80.dll',
'msvcr80.dll',
'net',
'pdas.dll']
Means the path is correct ForextConnect.dll is present and I might do some very simple wrong, but have no clue what.
You can either use Dependency Walker to figure out the correct sequence to manually load the DLLs, or simply add the directory to the system search path:
dllpath = os.path.abspath('ForexConnectAPIx64/bin')
os.environ['PATH'] += os.pathsep + dllpath
myDLL = CDLL('ForexConnect.dll')