Comments (5)
It is not surprising that a model trained on white characters and black background cannot be used to predict the inverse. The model can only predict what it knowns: Usually this should be black foreground and white background in the case of Calamari.
Calamari does not support color features, since it converts all data to grayscale. However, you need to train on gray-scale images in order to receive meaningful results.
The actual prediction time for predicting a single line are about 0.3 Seconds per line on a single CPU. I guess most of the time is needed to load the model, however this must only be done once. Thus, to reach these times, you must manually create and store a calamari_ocr.ocr.Predictor
-Object and initialize it. Then use this model to predict a line:
E. g. (but untested)
from calamari_ocr.ocr import Predictor, create_dataset, DataSetType, DataSetMode
# Load (only once)
predictor = Predictor('PATH_TO_THE_MODEL_WITHOUT_EXT')
# Predict
data = create_dataset(
DataSetType.RAW, # if you already have np.arrays or DataSetType.File to load from the filesystem
DataSetMode.PREDICT,
images=[raw_image_or_path_to_image],
)
prediction, _ = list(predictor.predict_dataset(data))[0]
from calamari.
thank you for response.
from calamari.
well,i've already create a data like this :
data=FileDataSet(DataSetMode.PREDICT,input_image_files) or
data=RawDataSet(DataSetMode.PREDICT,images)
the first one works well,input_image_files=path to the images(str)
my question is about the second one, the description of the parameter images is the list of images,Is that mean the np.arrays of the image or the list of np.arrays?
from calamari.
images
is a list of np.array
's for a RawDataSet
from calamari.
that's great,thank you!!!
from calamari.
Related Issues (20)
- Cannot convert a symbolic Tensor - Cannot even initialize the Predictor object HOT 2
- Characters coordinates HOT 1
- training: Cannot convert a symbolic Tensor to a numpy array HOT 7
- HDF5 dataset format: how to convert HOT 4
- calamari-train: warmstart not working without also giving network spec
- featreq: when warmstart-training, init weights of new chars from existing ones HOT 2
- calamari-eval: skip missing pairs HOT 3
- calamari-eval: unknown arguments HOT 6
- calamari-eval: confusion table miscalculates relative frequency HOT 3
- Error when convert old trained model to latest version model HOT 1
- Got exception during training HOT 4
- calamari-ocr 2.2.2 on ubuntu 22.04 partial success, difficulty with GPU software
- Prediction from calamari trained .pb model HOT 5
- Issue while using the model and json HOT 8
- setup.py on Ubuntu20.04: tensorflow is wrong version HOT 7
- Model very sensitive on PNG input HOT 3
- calamari/1.0: hold Tensorflow and Protobuf dependencies HOT 6
- What is the accuracy on Chinese/Japanese text? HOT 2
- Attention layer
- "No training configuration" for code that should not have one HOT 5
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 calamari.