New Examples, Bug Fixes, and Layers

New examples:

• Learns Hypotenuse
• Simple Image Classifier with Parallel Convolutions
• Simple Plant Leaf Disease Classifier

Fixes bugs #31 and #32.

Adds new layer types:

• TNNetReLUSqrt: does a ReLU followed by square root.
• TNNetPower: calculates the power function.

Documentation updates.

All fully connected layers now support OpenCL on the forward pass!

The main topics in this release are:

• All fully connected layers now support OpenCL on the forward pass.
• Better documentation.
• A new Autoencoder example that shows an autoencoder built with hyperbolic tangents and trained with Tiny ImageNet 200.

  

• Some small bug fixes.

Super Resolution Example

This release includes a super resolution example:
https://github.com/joaopauloschuler/neural-api/tree/master/examples/SuperResolution

There is also a command line tool so everyone can now increase image resolution with no more than FPC (no external library are required) via command line:

#SuperResolution -i street.png -o street3.png
Loading input file: street.png
Input image size: 158x214x3
Creating Neural Network...
Resizing with tiles...
Neural network file found at ../../../examples/SuperResolution : super-resolution-7-64-sep.nn
Padding input image.
Resizing with tiles to: 288x416x3
Saving output file: street3.png

This release also fixes bug #25 .

CreateVolumesFromImagesFromFolder

There are plenty of image datasets where each folder represents a class of images. To make the pascal coding simpler, a new procedure CreateVolumesFromImagesFromFolder has been added.

New procedure CreateVolumesFromImagesFromFolder has parallel code so classes are loaded into memory in parallel. I consider this code tremendously fast and it outperforms code that I saw in other APIs. I should say thank you to FPC developers for coding FPImage and plenty of other super fast bits and pieces that allowed me to implement a fast CreateVolumesFromImagesFromFolder.

Source code examples:

• Simple Plant Leaf Disease Image Classifier
• Tiny ImageNet 200

Delphi: Support for OpenCL and Threads

v0.984

Fixing error when freeing threads.

Almost everything has been tested! Almost 1.0!

v0.98

Update README.md

We are approaching v1.0!

Some fixes were applied to neuralfit. We are approaching v1.0!

Almost 1.0

v0.962

Adding TNNetSplitChannels.Create(ChannelStart, ChannelLen: integer)

Almost 1.0

Few fixes have been made.

Almost v1.0

CIFAR-100, MNIST and Fashion MNIST are currently in testing.