public static final class SmoothGradConfig.Builder extends GeneratedMessageV3.Builder<SmoothGradConfig.Builder> implements SmoothGradConfigOrBuilder
Config for SmoothGrad approximation of gradients.
When enabled, the gradients are approximated by averaging the gradients from
noisy samples in the vicinity of the inputs. Adding noise can help improve
the computed gradients. Refer to this paper for more details:
https://arxiv.org/pdf/1706.03825.pdf
Protobuf type google.cloud.aiplatform.v1.SmoothGradConfig
Methods
public SmoothGradConfig.Builder addRepeatedField(Descriptors.FieldDescriptor field, Object value)
Parameters
Returns
Overrides
public SmoothGradConfig build()
Returns
public SmoothGradConfig buildPartial()
Returns
public SmoothGradConfig.Builder clear()
Returns
Overrides
public SmoothGradConfig.Builder clearFeatureNoiseSigma()
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Returns
public SmoothGradConfig.Builder clearField(Descriptors.FieldDescriptor field)
Parameter
Returns
Overrides
public SmoothGradConfig.Builder clearGradientNoiseSigma()
Returns
public SmoothGradConfig.Builder clearNoiseSigma()
This is a single float value and will be used to add noise to all the
features. Use this field when all features are normalized to have the
same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where
features are normalized to have 0-mean and 1-variance. Learn more about
normalization.
For best results the recommended value is about 10% - 20% of the standard
deviation of the input feature. Refer to section 3.2 of the SmoothGrad
paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.
If the distribution is different per feature, set
feature_noise_sigma instead
for each feature.
float noise_sigma = 1;
Returns
public SmoothGradConfig.Builder clearNoisySampleCount()
The number of gradient samples to use for
approximation. The higher this number, the more accurate the gradient
is, but the runtime complexity increases by this factor as well.
Valid range of its value is [1, 50]. Defaults to 3.
int32 noisy_sample_count = 3;
Returns
public SmoothGradConfig.Builder clearOneof(Descriptors.OneofDescriptor oneof)
Parameter
Returns
Overrides
public SmoothGradConfig.Builder clone()
Returns
Overrides
public SmoothGradConfig getDefaultInstanceForType()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
public Descriptors.Descriptor getDescriptorForType()
Returns
Overrides
public FeatureNoiseSigma getFeatureNoiseSigma()
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Returns
public FeatureNoiseSigma.Builder getFeatureNoiseSigmaBuilder()
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Returns
public FeatureNoiseSigmaOrBuilder getFeatureNoiseSigmaOrBuilder()
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Returns
public SmoothGradConfig.GradientNoiseSigmaCase getGradientNoiseSigmaCase()
Returns
public float getNoiseSigma()
This is a single float value and will be used to add noise to all the
features. Use this field when all features are normalized to have the
same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where
features are normalized to have 0-mean and 1-variance. Learn more about
normalization.
For best results the recommended value is about 10% - 20% of the standard
deviation of the input feature. Refer to section 3.2 of the SmoothGrad
paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.
If the distribution is different per feature, set
feature_noise_sigma instead
for each feature.
float noise_sigma = 1;
Returns
Type | Description |
float | The noiseSigma.
|
public int getNoisySampleCount()
The number of gradient samples to use for
approximation. The higher this number, the more accurate the gradient
is, but the runtime complexity increases by this factor as well.
Valid range of its value is [1, 50]. Defaults to 3.
int32 noisy_sample_count = 3;
Returns
Type | Description |
int | The noisySampleCount.
|
public boolean hasFeatureNoiseSigma()
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Returns
Type | Description |
boolean | Whether the featureNoiseSigma field is set.
|
public boolean hasNoiseSigma()
This is a single float value and will be used to add noise to all the
features. Use this field when all features are normalized to have the
same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where
features are normalized to have 0-mean and 1-variance. Learn more about
normalization.
For best results the recommended value is about 10% - 20% of the standard
deviation of the input feature. Refer to section 3.2 of the SmoothGrad
paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.
If the distribution is different per feature, set
feature_noise_sigma instead
for each feature.
float noise_sigma = 1;
Returns
Type | Description |
boolean | Whether the noiseSigma field is set.
|
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public SmoothGradConfig.Builder mergeFeatureNoiseSigma(FeatureNoiseSigma value)
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Parameter
Returns
public SmoothGradConfig.Builder mergeFrom(SmoothGradConfig other)
Parameter
Returns
public SmoothGradConfig.Builder mergeFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Overrides
Exceptions
public SmoothGradConfig.Builder mergeFrom(Message other)
Parameter
Returns
Overrides
public final SmoothGradConfig.Builder mergeUnknownFields(UnknownFieldSet unknownFields)
Parameter
Returns
Overrides
public SmoothGradConfig.Builder setFeatureNoiseSigma(FeatureNoiseSigma value)
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Parameter
Returns
public SmoothGradConfig.Builder setFeatureNoiseSigma(FeatureNoiseSigma.Builder builderForValue)
This is similar to noise_sigma, but
provides additional flexibility. A separate noise sigma can be provided
for each feature, which is useful if their distributions are different.
No noise is added to features that are not set. If this field is unset,
noise_sigma will be used for all
features.
.google.cloud.aiplatform.v1.FeatureNoiseSigma feature_noise_sigma = 2;
Parameter
Returns
public SmoothGradConfig.Builder setField(Descriptors.FieldDescriptor field, Object value)
Parameters
Returns
Overrides
public SmoothGradConfig.Builder setNoiseSigma(float value)
This is a single float value and will be used to add noise to all the
features. Use this field when all features are normalized to have the
same distribution: scale to range [0, 1], [-1, 1] or z-scoring, where
features are normalized to have 0-mean and 1-variance. Learn more about
normalization.
For best results the recommended value is about 10% - 20% of the standard
deviation of the input feature. Refer to section 3.2 of the SmoothGrad
paper: https://arxiv.org/pdf/1706.03825.pdf. Defaults to 0.1.
If the distribution is different per feature, set
feature_noise_sigma instead
for each feature.
float noise_sigma = 1;
Parameter
Name | Description |
value | float
The noiseSigma to set.
|
Returns
public SmoothGradConfig.Builder setNoisySampleCount(int value)
The number of gradient samples to use for
approximation. The higher this number, the more accurate the gradient
is, but the runtime complexity increases by this factor as well.
Valid range of its value is [1, 50]. Defaults to 3.
int32 noisy_sample_count = 3;
Parameter
Name | Description |
value | int
The noisySampleCount to set.
|
Returns
public SmoothGradConfig.Builder setRepeatedField(Descriptors.FieldDescriptor field, int index, Object value)
Parameters
Returns
Overrides
public final SmoothGradConfig.Builder setUnknownFields(UnknownFieldSet unknownFields)
Parameter
Returns
Overrides