Comments (12)
Выполняю в папке train/py
python3.6 options.py
from nomeroff-net.
Залил посвежее датасет -- должно работать
from nomeroff-net.
Почему-то не заводится...
Traceback (most recent call last):
File "options.py", line 40, in <module>
numberClassificator.prepare(PATH_TO_DATASET)
File "/nomeroff-net/NomeroffNet/OptionsDetector.py", line 159, in prepare
self.train_generator = self.compile_train_generator(train_dir, (self.HEIGHT, self.WEIGHT), self.BATCH_SIZE)
File "/nomeroff-net/NomeroffNet/OptionsDetector.py", line 330, in compile_train_generator
imageGenerator.build_data()
File "/nomeroff-net/NomeroffNet/Base/ImgGenerator.py", line 49, in build_data
to_categorical(disc[1], self.labels_counts[1]),
File "/usr/local/lib/python3.6/site-packages/keras/utils/np_utils.py", line 52, in to_categorical
categorical[np.arange(n), y] = 1
IndexError: index 10 is out of bounds for axis 1 with size 8
from nomeroff-net.
Проблема на моей стороне или что-то не так с datasets ?:)
from nomeroff-net.
from nomeroff-net.
Как Вы написали, получилось, если я пишу так self.CLASS_REGION = ["ru"] - таже ошибка
from nomeroff-net.
Спасибо! Все заработало!
from nomeroff-net.
Доброго времени суток!
Появилась новая ошибка, когда запускаю
Traceback (most recent call last):
File "mrcnn.py", line 27, in <module>
nnet = Detector(MASK_RCNN_DIR, MASK_RCNN_LOG_DIR)
File "/nomeroff-net/NomeroffNet/Detector.py", line 42, in __init__
from .nnmrcnn import InferenceConfig
File "/nomeroff-net/NomeroffNet/nnmrcnn.py", line 6, in <module>
from mrcnn.config import Config
File "/nomeroff-net/train/py/mrcnn.py", line 27, in <module>
nnet = Detector(MASK_RCNN_DIR, MASK_RCNN_LOG_DIR)
File "/nomeroff-net/NomeroffNet/Detector.py", line 42, in __init__
from .nnmrcnn import InferenceConfig
ImportError: cannot import name 'InferenceConfig'
from nomeroff-net.
Эта ошибка возникает из за путаницы в подключаемых модулей,
Модуль /nomeroff-net/train/py/mrcnn.py называется так же как и подключаемый внешний модуль mrcnn.
from nomeroff-net.
Спасибо! переименовал, все заработало... не специалист по питону)
from nomeroff-net.
Использовал этот dataset: https://nomeroff.net.ua/datasets/autoriaNumberplateDataset-2019-03-06.zip
Упала ошибка:
Traceback (most recent call last):
File "m.py", line 41, in <module>
nnet.train()
File "/nomeroff-net/NomeroffNet/Detector.py", line 243, in train
layers=self.CONFIG.LAYERS )
File "/usr/local/lib/python3.6/site-packages/mrcnn/model.py", line 2374, in train
use_multiprocessing=True,
File "/usr/local/lib/python3.6/site-packages/keras/legacy/interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.6/site-packages/keras/engine/training.py", line 1658, in fit_generator
initial_epoch=initial_epoch)
File "/usr/local/lib/python3.6/site-packages/keras/engine/training_generator.py", line 181, in fit_generator
generator_output = next(output_generator)
File "/usr/local/lib/python3.6/site-packages/keras/utils/data_utils.py", line 733, in get
six.reraise(*sys.exc_info())
File "/.local/lib/python3.6/site-packages/six.py", line 693, in reraise
raise value
File "/usr/local/lib/python3.6/site-packages/keras/utils/data_utils.py", line 702, in get
inputs = future.get(timeout=30)
File "/usr/local/lib/python3.6/multiprocessing/pool.py", line 608, in get
raise self._value
IndexError: index 1159 is out of bounds for axis 1 with size 1080
from nomeroff-net.
Та там есть проблемы с непочищенными EXIF-тегами. У меня на компе есть более "свежий" исправленый датасет, просто нет времени его зарелизить. Поэтому можно решить проблему так: почистить теги скриптом в папках test, val, train:
for file in `ls *.jpeg`; do
Orientation=`exiftool -Orientation -n ${file} | awk '{print $3}'`;
if [[ $Orientation -gt 1 ]]
then
echo "Fixing '${file}' - $Orientation "
exiftool -Orientation=1 -n ${file}
fi
done
Предварительно установите exiftool. Для Fedora, на которой я работаю, есть уже собраный пакет
yum install perl-Image-ExifTool
from nomeroff-net.
Related Issues (20)
- Вырезание номеров из фото HOT 5
- Dataset for Detection + OCR pipeline and comparison with Nomeroff-Net HOT 2
- ModuleNotFoundError: No module named 'modelhub_client' HOT 6
- Failed to run get-started-demo.py in docker container HOT 3
- обучать пользовательский набор данных HOT 7
- I have error about checkpoint HOT 5
- KeyError: 'pytorch-lightning_version' HOT 3
- How to train OCR model? HOT 3
- ImportError: cannot import name 'efficientnet_v2_s' from 'torchvision.models' HOT 1
- when change name of folder nomer_net code not work HOT 5
- Size of docker image HOT 1
- Multiline example doesn't return correct recognitions
- draw rectangle bbox on plate HOT 4
- Некорректное распознавание российских номер с регионом 799, 977 HOT 1
- Некорректное распознавание номеров в 3 строки
- Ошибка при установке пакета в req.txt HOT 1
- Columns and DataType Not Explicitly Set on line 157 of datasets_tools.py
- Error in nomeroff-net setup command: 'install_requires' HOT 1
- Label 'md' not in dict_keys && Label changed on default 'eu_ua_2015'
- Realtime Video performance / Benchmrk
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from nomeroff-net.