Comments (2)
My initial finding is that this error results from your input dimension being equal to 1.
I'm trying to fix it but haven't quite cracked it yet. A short term fix is to pad your input with an additional input which you could always set to zero.
from fkb.
Hello, I see, thanks a lot for help!
As a little follow up, I would like to ask you an expert opinion.
I'm, let's say, investing some time to interface my scikit or tensorflow/keras networks with fortran or c/c++ main code solvers. The main hope is to be able to use the trained network to predict something which could be directly injected in the fortran or C/C++ solvers. Nevertheless, after a long literature review and hands-on experience I have the feeling that nobody does this because it will be hardly competitive with pure python/tensorflow applications.
This is particularly true when the prediction is done inside some intensive loop (many times), for example, since the communication cost becomes considerable even if the prediction time is much less than the computation without ML/NN.
And I see that even by using other approaches like CFFI, Cython, SWIG, Babel, f2py and so on, will not satisfactorily fix the issue.
Clearly, the situation may be different if the prediction is done just once outside of the computationally intensive parts.
What do you think about it? Am I right?
Thank you,
Lorenzo
from fkb.
Related Issues (19)
- dense layer with no biases can't be converted HOT 1
- multi-input multi-output regression HOT 2
- Unsupported layer found! Skipping... HOT 4
- Incompatibilities with Tensorflow 2
- Wrong derivative of leaky-relu activation HOT 1
- Typo "usable" not "usuable" in README HOT 1
- Performance enhancements (batched predictions using GEMM) HOT 1
- Keras saved mode is not .h5 file HOT 2
- No "tanh" activation in "convert_weights.py"
- add topics HOT 1
- FKB with threading turned on
- Should linear_prime return 1 instead of x? HOT 1
- Recognize InputLayer HOT 1
- Undefined TBP (train()) used in src/tests/example_simple.F90 and example_mnist.F90 HOT 1
- Possible typo (filename) in the header comment of test_training.F90 HOT 1
- Redundant evaluation of db in dense_backward() in mod_dense_layer.F90 ? HOT 1
- "Unable to open object (object 'dense_1' doesn't exist)" HOT 2
- how can we put the value from one subroutine to another subroutine, containing a function? 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 fkb.