CubbyDNN
CubbyDNN copied to clipboard
utilForever
Implement Image class
To put image to a tensor, implementation of image class is needed
Basic Features
- Support some image types(jpg, png, gif, bmp)
- Load and save images
- Resizable and croppable
- Rotate, transform
- Convertable to tensor(or array)
Additional features
- Gaussian blur
- Noise
- Adjust hue, rgb etc...
- ETC...
How does this design work together with video streams? One very important use case of a DL environment is object recognition and tracking, with our without optical flow.
Make certain that the image class works well together with video processing workloads.
There'll be a video class which can return an image class per frame. And the video class will be implemented after this work is completed.
Awesome.
What about optical flow-based video analysis? Do you know what is needed for that use case? I don't know, so asking in earnest.
I'm not familiar with flow-based video analysis. I saw a dataset whose r, g and b represents x, y, z-axis movements respectively. But actually I don't know what is needed for that use case specifically.
We should look into what the best practice is for optical flow. I believe that most insect visual systems are optical flow based, and I would think that this translates to DL for autonomous systems such as drones. It might be a separate cognitive system, so a fancy drone may have a 3D visual system for object recognition and tracking, and an optical flow DL system for control.
Let's make certain that CubbyDNN can support these use cases.
We separate task that implements load images.
- @Yoogeonhui: Load bmp and gif file format
- @utilForever: Load png and jpg file format
