neural-fortran

neural-fortran copied to clipboard

Start-to-finish example

1

Hi. I've recently tried to link neural-fortran to a fortran physics code. I was wondering if it would be possible to add a bit more documentation on how to use...

OsAmaro

Test failure with ifx

6

Hi, Is ifx (intel nex generation fortran compiler that is replacing ifort) supported, I'm getting the following failures with ifx 2023.1.0: ``` The following tests FAILED: 6 - test_maxpool2d_layer (Failed)...

aminiussi

Supported HDF5 version

7

Hi, We tried to build with HDF5 1.14.x and it either fails at compile time or crashes at runtime (depending on platforms). Was it tested with that 1.14.0 version ?...

aminiussi

Implementing basic RNN

6

A work in progress. I'm mostly interested in loading a TF model from HDF and applying predict(), but I'll do my best in doing a complete implementation coherent with the...

castelao

Some tests and examples fail with segmentation fault in serial production build, but not in debug build

1

I cloned the repository to my laptop and built with the flag -DSERIAL=1; however, several examples (including simple) failed with a segmentation fault, apparently always when calling the subroutine print_info...

asandrock

Building client code with CMake

2

Hi, I would like to link against neural-form from my code built with CMake. Is there a FindNeuralFortran.cmake or something similar somewhere ? Thanks

aminiussi

scaling

2

Is there already a solution to scale the input? I'm currently scaling my features manually before feeding into nf. It would be nice if we could incorporate such scaling in...

castelao

Added Batch Normalization Layer modules

7

Addresses #155 @milancurcic , I've included the structure of the batch normalization layer. Could you please review it and confirm whether I'm in the correct direction?

Spnetic-5

In support of #155. This will impact the `forward` and `backward` methods in: * `network` type * `layer` type * `dense_layer` type * `conv2d_layer` type Effectively, rather than looping over...

milancurcic

Originally requested by @rweed in #114. A batch normalization is possibly the next most widely used layer after dense, convolutional, and maxpooling layers, and is an important tool in optimization...

milancurcic