w ing
Reputation: 31
During ML agent training, If I want to change observations, do I have to run the training from the beginning again?
During ML agent training, If I want to change observations(sensor shape, number of sensors, etc), do I have to run the training from the beginning again?
Upvotes: 0
Views: 497
Answers (1)
Noltibus
Reputation: 1360
Short answer: Yes! A bit longer answer: Changes in anything model structure or training data related will lead to starting the training from the beginning. All the popular frameworks transfer their model structure to the GPU while building/compiling the model and there is no way of hot-swapping this during runtime.
Upvotes: 1
Related Questions
- Do I need to train my neural network everytime I run it?
- Update a trained model in ML.NET
- Can I train DQN without updating training agent?
- ML agent not learning a relatively 'simple' task
- How to update the hmmlearn learned object when we have new samples?
- ML Agents - Multiple agents break the training
- Azure ML:- How to retrain the Azure ML model using data from third party system every time the Azure ML web service is invoked
- ML-Agents agent not resetting?
- unity ML Agents and external data
- Updating a Neural Network input