I have deployed T5 tensorrt model on nvidia triton server and below is the config.pbtxt file, but facing problem while inferencing the model using triton client.
As per the config.pbtxt file there should be 4 inputs to the tensorrt model along with the decoder ids. But how can we send decoder as input to the model I think decoder is to be generated from models output.
name: "tensorrt_model"
platform: "tensorrt_plan"
max_batch_size: 0
input [
{
name: "input_ids"
data_type: TYPE_INT32
dims: [ -1, -1 ]
},
{
name: "attention_mask"
data_type: TYPE_INT32
dims: [-1, -1 ]
},
{
name: "decoder_input_ids"
data_type: TYPE_INT32
dims: [ -1, -1]
},
{
name: "decoder_attention_mask"
data_type: TYPE_INT32
dims: [ -1, -1 ]
}
]
output [
{
name: "last_hidden_state"
data_type: TYPE_FP32
dims: [ -1, -1, 768 ]
},
{
name: "input.151"
data_type: TYPE_FP32
dims: [ -1, -1, -1 ]
}
]
instance_group [
{
count: 1
kind: KIND_GPU
}
]
Related
I have below 2 colection
**aggregate collection**
{
_id: '1',
test_name: 'test1',
status: "flaked"
test_ids: [1, 2]
}
{
_id: '2',
test_name: 'test1',
status: "Flaked"
test_ids: [3, 4]
}
**test collection**
{
_id: 1,
run_id: 1,
test_name: 'test1',
status: "fail"
pipeline: "A"
}
{
_id: 2,
run_id: 2
test_name: 'test1',
status: "pass",
pipeline: "A"
}
{
_id: 3,
run_id: 3
test_name: 'test1',
status: "Infra",
pipeline: "B"
}
{
_id: 4,
run_id: 4
status: "pass",
test_name: 'test1',
pipeline: "B"
}
I am trying to % of how many times the test flaked like No of Flakes/ no of runs. Above should give me (1/4).
Test is considered flake only when aggregate result is flaked and one of test is failed. Can this be built with one query.
If a have a following structure :
{
_id: 1,
name: 'a',
info: []
},
{
_id: 2,
name: 'b',
info: [
{
infoID: 100,
infoData: 'my info'
}
]
},
{
_id: 3,
name: 'c',
info: [
{
infoID: 200,
infoData: 'some info 200'
},
{
infoID: 300,
infoData: 'some info 300'
}
]
}
I need to query in such a way to obtain the documents where infoID is 100 showing the infoData, or nothing if info is empty, or contains subdocuments with infoID different from 100.
That is, I would want the following output:
{
_id: 1,
name: 'a',
infoData100: null
},
{
_id: 2,
name: 'b',
infoData100: 'my info'
},
{
_id: 3,
name: 'c',
infoData100: null
}
If I $unwind by info and $match by infoID: 100, I lose records 1 and 3.
Thanks for your responses.
Try below query :
Query :
db.collection.aggregate([
/** Adding a new field or you can use $project instead of addFields */
{
$addFields: {
infoData100: {
$cond: [
{
$in: [100, "$info.infoID"] // Check if any of objects 'info.infoID' has value 100
},
{
// If any of those has get that object & get infoData & assign it to 'infoData100' field
$let: {
vars: {
data: {
$arrayElemAt: [
{
$filter: {
input: "$info",
cond: { $eq: ["$$this.infoID", 100] }
}
},
0
]
}
},
in: "$$data.infoData"
}
},
null // If none has return NULL
]
}
}
}
]);
Test : MongoDB-Playground
I have a dataset with metrics collected from a group of sensors.
My dataset looks like this:
{type: 1, display: 'foo', value: 'A'}
{type: 2, display: 'bar', value: 'B'}
{type: 2, display: 'foo', value: 'B'}
I am trying to aggregate the results and get some meaning insights via a REST API. I am somehow trying to produce aggregated results as:
[{
type: 1,
displays: [
{
name: 'foo',
count: 1
}
],
values: [
{
name: 'A',
count: 1
}
],
total_count: 1
},{
type: 2,
displays: [
{
name: 'foo',
count: 1
} , {
name: 'bar',
count: 1
}
],
values: [
{
name: 'B',
count: 2
}
],
total_count: 2
}]
Summarizing the aggregated results and producing shallow results is straight forward, I am struggling though as I can't created the nested counters for types and displays all together.
I have tried to use various aggregation operators with no luck.
Basically I can get one group by types or displays as:
db.logs.aggregate([
{
$group: {
_id: {
type: '$type',
display: '$display'
},
count: { $sum: 1 }
}
}, {
$group: {
_id: '$_id.type',
displays: {
$push: {
name: "$_id.display",
count: "$count"
}
}
}
}
]);
Any help will be highly appreciated.
I am using Highcharts for generating a two column bar graph. Means for each day I am showing the number of downloads and number of signups. Now I need to have a drilldown, which shows up the hourly data. The Highcharts docs is showing an example for Signle column by specifying the y value. But as I am showing stached bar, I have two y values for the same date. The code I am using is as follows :
series: [{
name : 'Signups,
color : '#0066FF',
data : <?=$series_1?>, //data in JSON format from PHP
drilldown: true
}, {
name : 'Downloads',
color : '#E81531',
data : <?=$series_2?>, //data in JSON format from PHP
drilldown: true
}],
Example for you for drilldown with two series, with stacking: 'normal': http://jsfiddle.net/6zYmJ/10/
$('#container').highcharts({
chart: {
type: 'column'
},
title: {
text: 'Basic drilldown'
},
xAxis: {
type: 'category'
},
legend: {
enabled: false
},
plotOptions: {
series: {
stacking: 'normal',
borderWidth: 0,
dataLabels: {
enabled: true,
}
}
},
series: [{
name: 'Things',
colorByPoint: true,
data: [{
name: 'Animals',
y: 5,
drilldown: 'animals'
}, {
name: 'Fruits',
y: 2,
drilldown: 'fruits'
}, {
name: 'Cars',
y: 4,
drilldown: 'cars'
}]
}, {
name: 'Things2',
colorByPoint: true,
data: [{
name: 'Animals2',
y: 5,
drilldown: 'animals2'
}, {
name: 'Fruits2',
y: 2,
drilldown: 'fruits2'
}, {
name: 'Cars2',
y: 4,
drilldown: 'cars2'
}]
}],
drilldown: {
series: [{
id: 'animals',
data: [
['Cats', 4],
['Dogs', 2],
['Cows', 1],
['Sheep', 2],
['Pigs', 1]
]
}, {
id: 'fruits',
data: [
['Apples', 4],
['Oranges', 2]
]
}, {
id: 'cars',
data: [
['Toyota', 4],
['Opel', 2],
['Volkswagen', 2]
]
},{
id: 'animals2',
data: [
['Cats', 4],
['Dogs', 2],
['Cows', 1],
['Sheep', 2],
['Pigs', 1]
]
}, {
id: 'fruits2',
data: [
['Apples', 4],
['Oranges', 2]
]
}, {
id: 'cars2',
data: [
['Toyota', 4],
['Opel', 2],
['Volkswagen', 2]
]
}]
}
})
Adding to Pawel Response-
Just replace in plotOptions with this value
column: {
pointPadding: 0.2,
borderWidth: 0
}
,
Here i m putting code of my json file..can anyone help me "How to parse this json file?".I tried a lot of tutorials.I got some hints.But in my json file i dont have array name.so i couldnt use any key value to access those objects.
[
{
id: 1,
name: "Ice Cube",
properties: [
{
propertyMeta: {
name: "Color",
type: 5
},
value: "Venfield"
},
{
propertyMeta: {
name: "Size",
type: 1
},
value: "38"
}
]
},
{
id: 2,
name: "Lite Shirt",
properties: [
{
propertyMeta: {
name: "Color",
type: 5
},
value: "Otto"
},
{
propertyMeta: {
name: "Size",
type: 1
},
value: "42"
}
]
},
{
id: 3,
name: "Holiday Tops",
properties: [
{
propertyMeta: {
name: "Color",
type: 5
},
value: "Van Heusen"
},
{
propertyMeta: {
name: "Size",
type: 1
},
value: "39"
}
]
}
]
If you're using SBJSON you'd just:
NSArray *myArray = [myJSONString JSONvalue];
And then loop through it as normal