| @@ -362,8 +362,9 @@ class Conv2dBnFoldQuantOneConv(Cell): | |||
| var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the | |||
| variance vector. Default: 'ones'. | |||
| fake (bool): Whether Conv2dBnFoldQuant Cell adds FakeQuantWithMinMaxObserver. Default: True. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| Inputs: | |||
| @@ -573,8 +574,9 @@ class Conv2dBnFoldQuant(Cell): | |||
| var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the | |||
| variance vector. Default: 'ones'. | |||
| fake (bool): Whether Conv2dBnFoldQuant Cell adds FakeQuantWithMinMaxObserver. Default: True. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| freeze_bn (int): The quantization freeze BatchNormal op is according to the global step. Default: 100000. | |||
| @@ -750,8 +752,9 @@ class Conv2dBnWithoutFoldQuant(Cell): | |||
| weight_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the convolution kernel. | |||
| Default: 'normal'. | |||
| bias_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the bias vector. Default: 'zeros'. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| Inputs: | |||
| @@ -862,8 +865,9 @@ class Conv2dQuant(Cell): | |||
| weight_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the convolution kernel. | |||
| Default: 'normal'. | |||
| bias_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the bias vector. Default: 'zeros'. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| Inputs: | |||
| @@ -967,8 +971,9 @@ class DenseQuant(Cell): | |||
| has_bias (bool): Specifies whether the layer uses a bias vector. Default: True. | |||
| activation (Union[str, Cell, Primitive]): The regularization function applied to the output of the layer, | |||
| eg. 'relu'. Default: None. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| Inputs: | |||
| @@ -1077,8 +1082,9 @@ class ActQuant(_QuantActivation): | |||
| ema (bool): The exponential Moving Average algorithm updates min and max. Default: False. | |||
| ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999. | |||
| fake_before (bool): Whether add fake quantized operation before activation. Default: False. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| Inputs: | |||
| @@ -1141,8 +1147,9 @@ class TensorAddQuant(Cell): | |||
| Args: | |||
| ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| Inputs: | |||
| @@ -1192,8 +1199,9 @@ class MulQuant(Cell): | |||
| Args: | |||
| ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999. | |||
| quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default: | |||
| both set to default FakeQuantWithMinMaxObserver. | |||
| quant_config (QuantConfig): Configs the oberser types and quant settings of weight and activation. Can be | |||
| generated by compression.quant.create_quant_config method. | |||
| Default: both set to default FakeQuantWithMinMaxObserver. | |||
| quant_dtype (QuantDtype): Specifies the FakeQuant datatype. Default: QuantDtype.INT8. | |||
| Inputs: | |||