45 lines
2.0 KiB
JSON
45 lines
2.0 KiB
JSON
/* This configuration file is the fastest way to get started with the default
|
|
sparsity and default quantization algorithm. It contains only mandatory options
|
|
with commonly used values. All other options can be considered as an advanced
|
|
mode and requires deep knowledge of the quantization process. An overall description
|
|
of all possible parameters can be found in the default_quantization_spec.json */
|
|
|
|
{
|
|
/* Model parameters */
|
|
"model": {
|
|
"model_name": "model_name", // Model name
|
|
"model": "<MODEL_PATH>", // Path to model (.xml format)
|
|
"weights": "<PATH_TO_WEIGHTS>" // Path to weights (.bin format)
|
|
},
|
|
/* Parameters of the engine used for model inference */
|
|
"engine": {
|
|
"config": "<CONFIG_PATH>" // Path to Accuracy Checker config
|
|
},
|
|
/* Optimization hyperparameters */
|
|
"compression": {
|
|
"target_device": "ANY", // Target device, the specificity of which will be taken
|
|
// into account during optimization
|
|
"algorithms": [
|
|
{
|
|
"name": "WeightSparsity",
|
|
"params": {
|
|
"sparsity_level": 0.3,
|
|
"stat_subset_size": 300 // Size of subset to calculate activations statistics that can be used
|
|
// for quantization parameters calculation
|
|
}
|
|
},
|
|
{
|
|
"name": "DefaultQuantization", // Optimization algorithm name
|
|
"params": {
|
|
// Preset [performance, mixed, accuracy] which control the quantization mode
|
|
// (symmetric, mixed (weights symmetric and activations asymmetric) and fully
|
|
// asymmetric respectively)
|
|
"preset": "performance",
|
|
"stat_subset_size": 300 // Size of subset to calculate activations statistics that can be used
|
|
// for quantization parameters calculation
|
|
}
|
|
}
|
|
]
|
|
}
|
|
}
|