Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class Visualization.
Visualization configurations for image explanation.
Generated from protobuf message google.cloud.aiplatform.v1.ExplanationMetadata.InputMetadata.Visualization
Namespace
Google \ Cloud \ AIPlatform \ V1 \ ExplanationMetadata \ InputMetadataMethods
__construct
Constructor.
| Parameters | |
|---|---|
| Name | Description |
data |
array
Optional. Data for populating the Message object. |
↳ type |
int
Type of the image visualization. Only applicable to Integrated Gradients attribution. OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES. |
↳ polarity |
int
Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE. |
↳ color_map |
int
The color scheme used for the highlighted areas. Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue. |
↳ clip_percent_upperbound |
float
Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9. |
↳ clip_percent_lowerbound |
float
Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62. |
↳ overlay_type |
int
How the original image is displayed in the visualization. Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE. |
getType
Type of the image visualization. Only applicable to Integrated Gradients attribution.
OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
| Returns | |
|---|---|
| Type | Description |
int |
|
setType
Type of the image visualization. Only applicable to Integrated Gradients attribution.
OUTLINES shows regions of attribution, while PIXELS shows per-pixel attribution. Defaults to OUTLINES.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getPolarity
Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
| Returns | |
|---|---|
| Type | Description |
int |
|
setPolarity
Whether to only highlight pixels with positive contributions, negative or both. Defaults to POSITIVE.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getColorMap
The color scheme used for the highlighted areas.
Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
| Returns | |
|---|---|
| Type | Description |
int |
|
setColorMap
The color scheme used for the highlighted areas.
Defaults to PINK_GREEN for Integrated Gradients attribution, which shows positive attributions in green and negative in pink. Defaults to VIRIDIS for XRAI attribution, which highlights the most influential regions in yellow and the least influential in blue.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getClipPercentUpperbound
Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
| Returns | |
|---|---|
| Type | Description |
float |
|
setClipPercentUpperbound
Excludes attributions above the specified percentile from the highlighted areas. Using the clip_percent_upperbound and clip_percent_lowerbound together can be useful for filtering out noise and making it easier to see areas of strong attribution. Defaults to 99.9.
| Parameter | |
|---|---|
| Name | Description |
var |
float
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getClipPercentLowerbound
Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
| Returns | |
|---|---|
| Type | Description |
float |
|
setClipPercentLowerbound
Excludes attributions below the specified percentile, from the highlighted areas. Defaults to 62.
| Parameter | |
|---|---|
| Name | Description |
var |
float
|
| Returns | |
|---|---|
| Type | Description |
$this |
|
getOverlayType
How the original image is displayed in the visualization.
Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
| Returns | |
|---|---|
| Type | Description |
int |
|
setOverlayType
How the original image is displayed in the visualization.
Adjusting the overlay can help increase visual clarity if the original image makes it difficult to view the visualization. Defaults to NONE.
| Parameter | |
|---|---|
| Name | Description |
var |
int
|
| Returns | |
|---|---|
| Type | Description |
$this |
|