File size: 1,822 Bytes
596a24b ebeb80f 596a24b ebeb80f 596a24b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 |
version: 1.0
model: # mandatory. used to specify model specific information.
name: fer
framework: onnxrt_qlinearops # mandatory. supported values are tensorflow, pytorch, pytorch_ipex, onnxrt_integer, onnxrt_qlinear or mxnet; allow new framework backend extension.
quantization: # optional. tuning constraints on model-wise for advance user to reduce tuning space.
approach: post_training_static_quant # optional. default value is post_training_static_quant.
calibration:
dataloader:
batch_size: 1
dataset:
dummy:
shape: [1, 3, 112, 112]
low: -1.0
high: 1.0
dtype: float32
label: True
model_wise: # optional. tuning constraints on model-wise for advance user to reduce tuning space.
weight:
granularity: per_tensor
scheme: asym
dtype: int8
algorithm: minmax
activation:
granularity: per_tensor
scheme: asym
dtype: int8
algorithm: minmax
tuning:
accuracy_criterion:
relative: 0.02 # optional. default value is relative, other value is absolute. this example allows relative accuracy loss: 1%.
exit_policy:
timeout: 0 # optional. tuning timeout (seconds). default value is 0 which means early stop. combine with max_trials field to decide when to exit.
max_trials: 50 # optional. max tune times. default value is 100. combine with timeout field to decide when to exit.
random_seed: 9527 # optional. random seed for deterministic tuning.
|