nilda's Issues
Add more cost functions
Check dropout backprop implementation
Prefectch the input data
Padding for backward conv2d might be wrong
Gradient sanity check fails with 2 CV layers and padding
const bool padding = true;
NilDa::layer* l0 = new NilDa::inputLayer({rI, cI, chI});
NilDa::layer* l1 = new NilDa::conv2DLayer(
nFilters,
{rF, cF},
{rS, cS},
padding,
"relu"
);
NilDa::layer* l2 = new NilDa::conv2DLayer(
nFilters,
{rF, cF},
{rS, cS},
padding, // <-------- the problem is here
"relu"
);
NilDa::layer* l3 = new NilDa::denseLayer(3, "softmax");
LoadModel not able to reproduce the same results of the original model
After loading the model, the accuracy of the original model and the one loaded is different
Add batch normalization layer
Add real sparse cross entropy loss function
Missing template for the labels
Check the backprop of conv2d with stride > 1
I am not sure if the transpose of the conv2d with stride different from 1 is doing what is suppose to do.
Compare with this: https://datascience.stackexchange.com/questions/6107/what-are-deconvolutional-layers
Add output layer
There is no check about they type of the last layer.
Add more optimization algorithms
NN with dense layers on the MNIST database give NaN in single precision
The NN give NaN after 1/2 epochs with single precision. This happens when relu and softmax/sigmoid layer because the output goes out of bound. Probably some normalization is required.
See:
https://developer.nvidia.com/blog/mixed-precision-training-deep-neural-networks/
Add png/jpg image importer
Improved the handling of Scalar
Add binary crossentropy loss
Missing check for correct number of input channels in CNN
Backprop gradient sanity is not correct if two conv layers are used
NilDa::layer* l0 = new NilDa::inputLayer({rI, cI, chI});
NilDa::layer* l1 = new NilDa::conv2DLayer(
nFilters,
{rF, cF},
{rS, cS},
padding,
"relu"
);
NilDa::layer* l2 = new NilDa::conv2DLayer(
nFilters,
{rF, cF},
{rS, cS},
padding,
"relu"
);
NilDa::layer* l3 = new NilDa::denseLayer(3, "softmax");
Optimize sparse class crossentropy loss
Add unit test for conv2d and maxPool2D
Add debug checks for conv2D and maxPool2D
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.