Configuration for calibration during quantization.
Defines calibration and quantization parameterization used to derive activation/weight scales and related statistics during quantized compilation.
- Parameters
-
| method | int. Calibration method index:
0: WChALayer - Weight per-channel, Activation per-layer.
1: WChAMulti - Weight per-channel, Activation multi-layer.
2: WChALayerZeropoint - Weight per-channel, Activation per-layer with zeropoint.
3: WChAMultiZeropoint - Weight per-channel, Activation multi-layer with zeropoint.
|
| output | int. Output quantization type index:
0: Layer - Per-layer quantization.
1: Ch - Per-channel quantization.
2: Sigmoid - Sigmoid-based quantization.
|
| mode | int. Quantization mode index:
0: Max - Maximum value calibration.
1: MaxPercentile - Maximum percentile calibration.
2: Histogram - Histogram-based calibration.
|
| clustering_methods | int. LUT clustering method:
0: Scale - Scale-based 1D clustering.
1: Scale2D - Scale-based 2D clustering.
2: ReparameterizedL2 - Reparameterized L2 distance clustering.
3: SubgraphIoU - Subgraph intersection-over-union clustering.
4: DomainAwareL2 - Domain-aware L2 distance on common absolute grid.
5: OverlapWeightedL2 - L2 weighted by domain overlap (IoU).
6: Fast - Minimal search space for fast LUT optimization.
|
| act_scale_min | float. Minimum allowed activation scale (lower bound clamp) |
| act16_scale_min | float. Minimum 16-bit activation scale (actScaleMin / 256) |
| weight_scale_min | float. Minimum allowed weight scale (lower bound clamp) |
| weight16_scale_min | float. Minimum 16-bit weight scale (weightScaleMin / 256) |
| min_clip_ratio | float. Minimum clip ratio constraint applied during calibration |
| max_calib_data_size | int. Maximum number of calibration samples kept after loading or generation |
| max_percentile | MaxPercentile. MaxPercentile mode configuration |
| fast_dist | FastDist. Fast distribution calibration configuration |
| histogram | Histogram. Histogram-based calibration configuration |
| layer_overrides | LayerOverrides. Layer-specific override settings for calibration |
| statistics | Statistics. Statistics save/load configuration with percentile selection |
Definition at line 141 of file models.py.