EVEAI is a Deep Learning Library based on python Keras and Tensorflow. EVEAI dll allows embedding inference images from keras models into user-written applications. Under Windows, the EVEAI training Tool provides services to train user specific image datasets and EVEAI dll provides services to existing Windows applications which support inference images.
Assigning a label to an image, for example:Labeling an image is a cat or a dog.
Segmenting pixels in an image to different categories of object, for example: street view image segmentation.
this demo images are from KITTI VISUAL ODOMETRY DATASET
Tracking multiple objects in an image,for example: real-time tracking chinese chess positions. This algorithm source code is written by fizyr
.png)
-
Installer for EVEAI runtime
Download Link:CPU tensorflow1.14.0 Version
- No GPU needed but process speed is lower than GPU version.
- It's almost impossible for train models , but still usefual for predict.
Download Link:GPU tensorflow1.14.0 Version
- Need Nvidia GPU Compute Capability > 3.5 tensorflow link
- Need NVIDIA Driver version > 410.x Nvidia driver link
-
Installer for EVEAI training Tool ,EVEAI dll and example codes
Download Link:EVEAI
-
Installer for Trained Examples:
Download Link:Fruilt 360 Image Dataset
Download Link:Malaria Cell Image Dataset
Download Link:LEGO brick Image Dataset
Download Link:Dogs and Cats Image Dataset
Download Link:Flowers Image Dataset
Download Link:Car Video Dataset
Download Link:KolektorSDD Dataset this images are fromVisual Cognitive Systems Laboratory
Download Link:Chinese Chess Dataset
LabVIEW (https://youtu.be/baybKe7CMdU)
C++ builder (https://youtu.be/2BYF84C7bdE)
Visual Studio C++ (plan to:Delphi/CVI/Visual Studio C#)
EVEAI dll is written in C++ Builder using Embarcadero RAD Studio 10.3.1 Rio Community Edition.
EVE AI run-time Executable is written in python packages into stand-alone executables by pyinstaller.