opssat-smartcam
opssat-smartcam copied to clipboard
georgeslabreche
On November 8, 2020, this project achieved the first use of deep convolutional neural networks (CNN) on-board a spacecraft.
The option only exists for Tensorflow Lite model nodes.
- Metadata data key-value properties in the classification JSON output are processed as possible labels to apply to the image. - If those metadata properties have numerical values that are...
- Check if the input exists already before recreating it. - Include a config flag to force regenerating the resized image if needed (e.g. in case two models take in...
Here are some pointers on how to get started with png support for the SmartCam's image classifier. ## A. Getting familiar with the development environment/setup **A1.** Go through [this readme](https://github.com/georgeslabreche/tensorflow-opssat-smartcam/blob/opssat-smartcam/README.md)...
### Context - Classification pipeline programs output a JSON object as stdout. - The JSON object is made out of key-value pairs representing the classification label (key) and the prediction...
## Background The execution time between the moment the camera captures an image and when that image gets classified can be reduced by eliminating the number of times an image...
See the repo's [README](https://github.com/georgeslabreche/tensorflow-opssat-smartcam#what-happened-here) for more details. **Todo:** - [ ] Recreate [the image classifier repo](https://github.com/georgeslabreche/tensorflow-opssat-smartcam) to only host the code required to build and run the image classifier and...
Metadata
Owner
Metadata
On November 8, 2020, this project achieved the first use of deep convolutional neural networks (CNN) on-board a spacecraft.