public final class SmoothGradConfig extends GeneratedMessageV3 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
Fields
public static final int FEATURE_NOISE_SIGMA_FIELD_NUMBER
Field Value
public static final int NOISE_SIGMA_FIELD_NUMBER
Field Value
public static final int NOISY_SAMPLE_COUNT_FIELD_NUMBER
Field Value
Methods
public boolean equals(Object obj)
Parameter
Returns
Overrides
public static SmoothGradConfig getDefaultInstance()
Returns
public SmoothGradConfig getDefaultInstanceForType()
Returns
public static final Descriptors.Descriptor getDescriptor()
Returns
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;
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;
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;
| 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;
| Type | Description |
| int | The noisySampleCount.
|
public Parser<SmoothGradConfig> getParserForType()
Returns
Overrides
public int getSerializedSize()
Returns
Overrides
public final UnknownFieldSet getUnknownFields()
Returns
Overrides
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;
| 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;
| Type | Description |
| boolean | Whether the noiseSigma field is set.
|
Returns
Overrides
protected GeneratedMessageV3.FieldAccessorTable internalGetFieldAccessorTable()
Returns
Overrides
public final boolean isInitialized()
Returns
Overrides
public static SmoothGradConfig.Builder newBuilder()
Returns
public static SmoothGradConfig.Builder newBuilder(SmoothGradConfig prototype)
Parameter
Returns
public SmoothGradConfig.Builder newBuilderForType()
Returns
protected SmoothGradConfig.Builder newBuilderForType(GeneratedMessageV3.BuilderParent parent)
Parameter
Returns
Overrides
protected Object newInstance(GeneratedMessageV3.UnusedPrivateParameter unused)
Parameter
Returns
Overrides
public static SmoothGradConfig parseDelimitedFrom(InputStream input)
Parameter
Returns
Exceptions
public static SmoothGradConfig parseDelimitedFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static SmoothGradConfig parseFrom(byte[] data)
Parameter
| Name | Description |
| data | byte[]
|
Returns
Exceptions
public static SmoothGradConfig parseFrom(byte[] data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static SmoothGradConfig parseFrom(ByteString data)
Parameter
Returns
Exceptions
public static SmoothGradConfig parseFrom(ByteString data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static SmoothGradConfig parseFrom(CodedInputStream input)
Parameter
Returns
Exceptions
public static SmoothGradConfig parseFrom(CodedInputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static SmoothGradConfig parseFrom(InputStream input)
Parameter
Returns
Exceptions
public static SmoothGradConfig parseFrom(InputStream input, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static SmoothGradConfig parseFrom(ByteBuffer data)
Parameter
Returns
Exceptions
public static SmoothGradConfig parseFrom(ByteBuffer data, ExtensionRegistryLite extensionRegistry)
Parameters
Returns
Exceptions
public static Parser<SmoothGradConfig> parser()
Returns
public SmoothGradConfig.Builder toBuilder()
Returns
public void writeTo(CodedOutputStream output)
Parameter
Overrides
Exceptions
