Comments (3)
A zip archive is a very simple and valid solution.
I was trying to use tensorflow's 'freeze' function which also would result in a single file, there were however some issues regarding the cudnn-lstm cells when loading such a network. This is why I stuck with the ugly 4-file solution.
from calamari.
See also #44
from calamari.
A zip archive is a very simple and valid solution.
I was trying to use tensorflow's 'freeze' function which also would result in a single file, there were however some issues regarding the cudnn-lstm cells when loading such a network. This is why I stuck with the ugly 4-file solution.
Sorry for being a few years late, but I also had this issue with my Keras models (depending on whether I wanted to load LSTM weights on CPU or GPU), so I decided to stuff all the necessary configuration for recompiling the model into the HDF5 dictionaries. It's pretty flexible, you can embed all the metadata there I believe. (It would still be multiple .h5 for multiple checkpoints though. And users would not have the advantage of easily inspecting the model codec, postprocessing etc anymore. But you could then make a dedicated tool for inspection...)
from calamari.
Related Issues (20)
- output_dir parameter does not work as described in doc string
- PAGE XML: explicit namespace prefixes are missing when writing new elements HOT 3
- calamari-predict: Glyph Coordinates are "strange"
- Argument "val.preload" documented but not known HOT 1
- 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
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.