frugally-deep
frugally-deep copied to clipboard
Dobiasd
A lightweight header-only library for using Keras (TensorFlow) models in C++.
If the frugally-deep library is included in the file that generates the dynamic link library, it will prompt that the file content is wrong. The configuration of project has involve...
Hello. I tried to use frugally, but i cannot pass the load_mode stage. I have converted my keras model (look converted fine), validated the output json (also seems frine), but...
Different convolution implementations might perform differently depending on the convolution settings (input size/depth, kernel size/count) and depending on the hardware (mostly CPU/memory) used. Right now, for example, we have [a...
First off, I would like to say that this is a really great piece of work! I have been using it with LSTMs for time-series data and have found frugally-deep...
Performance on fairly simple 1D model with stacked branches / bottlenecks / inception blocks was surprisingly poor (>300x slower). ## Keras on CPU (tensorflow lite for the same model is...
How about supporting ONNX in frugally? You could have a protobuf importer for ONNX models or add a tool which converts ONNX to the JSON format you use? Just a...
Conv3D
Hi, I'd like to use your library with models that are trained on 3d images. How hard do you think would it be for me to add support for 3d...
@JinhoPark-SNU [mentioned](https://github.com/Dobiasd/frugally-deep/issues/8#issuecomment-438579249) having masking layers would be nice. @n-Guard [wrote](https://github.com/Dobiasd/frugally-deep/issues/8#issuecomment-438661171) "the fdeep `lstm_impl()` function can easily be modified to skip those timesteps that are equal to the masking value that...
As a way to explore neural network, I wrote some example learning of logical operators (AND, OR, XOR) and was wondering if it would be of any use for the...
Encountering issues compiling (at the linker stage, it appears), even with the simple example from the readme.md. Compiling in Linux in a similar manner has no issues. I'm not sure...
