Filter message by a classification threshold.
The Filter Detections module is used to filter rows from a dataframe based on values in a tensor using a specified
criteria. Rows in the meta
dataframe are excluded if their associated value in the probs
array is less than or equal
to threshold
.
Parameter |
Type |
Description |
Example Value |
Default Value |
---|---|---|---|---|
|
boolean |
Whether to copy the rows or slice them |
true |
|
|
string |
Name of the field to filter on |
“probs” |
|
|
string |
Source of the filter field |
“AUTO” |
|
|
dictionary |
Schema configuration |
See Below |
|
|
float |
Threshold value to filter on |
0.5 |
|
Key |
Type |
Description |
Example Value |
Default Value |
---|---|---|---|---|
|
string |
Encoding |
“latin1” |
|
|
string |
Pickled message type |
“pickle_message_type” |
|
|
string |
Schema string |
“string” |
|
{
"field_name": "probs",
"threshold": 0.5,
"filter_source": "AUTO",
"copy": true,
"schema": {
"input_message_type": "pickle_message_type",
"encoding": "utf-8"
}
}
Property |
Value |
---|---|
copy |
False |
field_name |
probs |
filter_source |
AUTO |
threshold |
0.5 |