Links

Profile TFLite Model

Takes in a TFLite model and returns the latency, RAM and ROM used for this model. Updates are streamed over the websocket API (or can be retrieved through the /stdout endpoint).
post
https://studio.edgeimpulse.com/v1
/api/{projectId}/jobs/profile-tflite
Profile TFLite model

Takes in a TFLite model and returns the latency, RAM and ROM used for this model. Updates are streamed over the websocket API (or can be retrieved through the /stdout endpoint). Use getProfileTfliteJobResult to get the results when the job is completed.

Parameters
Path
projectId*
integer
Project ID
Body
Example
Schema
{
"tfliteFileBase64": "string",
"device": "string",
"referenceModel": "gestures-large-f32"
}
Responses
200: OK
OK
cURL
Python
Node.js
curl --request POST \
--url https://studio.edgeimpulse.com/v1/api/{projectId}/jobs/profile-tflite \
--header 'content-type: application/json' \
--header 'x-jwt-token: REPLACE_KEY_VALUE' \
--data '{"tfliteFileBase64":"string","device":"string","referenceModel":"gestures-large-f32"}'
import http.client
conn = http.client.HTTPSConnection("studio.edgeimpulse.com")
payload = "{\"tfliteFileBase64\":\"string\",\"device\":\"string\",\"referenceModel\":\"gestures-large-f32\"}"
headers = {
'content-type': "application/json",
'x-jwt-token': "REPLACE_KEY_VALUE"
}
conn.request("POST", "/v1/api/{projectId}/jobs/profile-tflite", payload, headers)
res = conn.getresponse()
data = res.read()
print(data.decode("utf-8"))
const request = require('request');
const options = {
method: 'POST',
url: 'https://studio.edgeimpulse.com/v1/api/{projectId}/jobs/profile-tflite',
headers: {'content-type': 'application/json', 'x-jwt-token': 'REPLACE_KEY_VALUE'},
body: {
tfliteFileBase64: 'string',
device: 'string',
referenceModel: 'gestures-large-f32'
},
json: true
};
request(options, function (error, response, body) {
if (error) throw new Error(error);
console.log(body);
});