CompressionOptimizer<T>
Models & Types · AiDotNet.AutoML
Automatically finds the best compression configuration for a model.
For Beginners
Think of this as an automated assistant that tries different ways to compress your model and finds the best one for your needs.
Instead of manually trying:
- Different pruning levels (50%, 70%, 90% of weights removed)
- Different quantization settings (8-bit, 5-bit, etc.)
- Different compression techniques (pruning, clustering, Huffman)
The optimizer automatically:
- Generates compression configurations to try
- Applies each configuration and measures results
- Tracks which configurations work best
- Returns the best compression settings found
Example usage:
How It Works
CompressionOptimizer uses automated machine learning techniques to find the optimal compression configuration for a neural network model. It evaluates different compression techniques and hyperparameters, tracking metrics like compression ratio, accuracy loss, and inference speed.
Constructors
| Constructor | Summary |
|---|---|
CompressionOptimizer(CompressionOptimizerOptions options) |
Initializes a new instance of the CompressionOptimizer class. |
Properties
| Property | Summary |
|---|---|
CompressionTrial<T> BestTrial { get; } |
Gets the best compression trial found so far. |
IReadOnlyList<CompressionTrial<T>> TrialHistory { get; } |
Gets the history of all compression trials. |
Methods
| Method | Summary |
|---|---|
CompressionTrial<T> Optimize(Vector<T> weights, Func<Vector<T>, T> evaluateAccuracy) |
Runs the compression optimization process. |
string GetSummary() |
Gets a summary of the optimization results. |