georgeslabreche / opssat-orbitai

The OrbitAI app for the OPS-SAT spacecraft.

georgeslabreche/opssat-orbitai Issues

Improve R plorts based on the paper review from IEEE AeroConf
Updated 3 years ago
Migrate OBSW parameters polling to aggregation service
Updated 3 years ago
Calculate classification metrics for ranger random forest when predicting with the test data
Updated 3 years ago
Implement on the fly prediction with ranger given a single data sample
Closed 3 years ago3
Define configuration properties for random forest training with ranger
Closed 3 years ago3
Update MochiMochi README with Factory Design Pattern explaination
Updated 3 years ago
Update ML Server README with Validation and Batch samples
Updated 3 years ago
ML Server: Handle loading serialized model files that do not exist
Closed 3 years ago
ML Server: save training data and prediction results in CSV files
Closed 3 years ago1
ML Server: implement robust error handling
Updated 3 years ago
ML Server: create MochiProxy class to interface with the MochiMochi library
Closed 3 years ago
ML Server: pull out socket server classes into a dedicated SocketServer class
Closed 3 years ago
ML Server: Pull out logging methods into a dedicated Logging Class
Closed 3 years ago1
Integrate ranger into the OrbitAI app (on the C++ binary side)
Closed 3 years ago
EM Validation - Round 2
Updated 3 years ago
EM Validation - Round 1
Updated 3 years ago
Clarify how to integrate ranger into the OrbitAI app
Closed 3 years ago2
Calculate the classification metrics obtained with ranger's Random Forest model by using the same dataset used in the paper
Updated 3 years ago
Benchmark ranger on the flatsat with realistic amount of data
Updated 3 years ago
Create milestones
Closed 3 years ago
Setup NMF Development Environment
Closed 3 years ago
Finally understand why the NMF app doesn't start anymore on FM
Updated 3 years ago
Refactor C++ ML server
Closed 3 years ago1
Define an interface for experimenters to provide final inputs data with a label
Closed 3 years ago2
Allow selection of training methods and configure their hyperparameters
Updated 3 years ago2
Integrate ranger into the OrbitAI app (on the NMF App side)
Updated 3 years ago
Calculate ranger performances (resources usage on flatsat, accuracy ...)
Closed 3 years ago1
Compile ranger for ARM and check it runs on flatsat
Closed 3 years ago8
Check that ranger fits our needs in terms of functionnalities
Closed 3 years ago4
Compile and run C++ implementation of ranger
Closed 3 years ago
Breakdown Epics into smaller issues
Closed 3 years ago4
Evaluate the ranger library for batch training with Random Forest
Updated 3 years ago
Generalize OrbitAI
Updated 3 years ago2
Attach license to repo prior to making it public.
Closed 3 years ago3
The NMF app's CSV log files is missing the timestamp column in the header row
Closed 3 years ago1
Resolve NaN issue with PA algorithm
Closed 3 years ago
Documentation for tagged release
Closed 3 years ago1