GET
/
api
/
{projectId}
/
jobs
/
profile-tflite
/
{jobId}
/
result
Get TFLite profile result (GET)
curl --request GET \
  --url https://studio.edgeimpulse.com/v1/api/{projectId}/jobs/profile-tflite/{jobId}/result \
  --header 'x-api-key: <api-key>'
{
  "success": true,
  "error": "<string>",
  "variant": "int8",
  "device": "<string>",
  "tfliteFileSizeBytes": 123,
  "isSupportedOnMcu": true,
  "memory": {
    "tflite": {
      "ram": 123,
      "rom": 123,
      "arenaSize": 123
    },
    "eon": {
      "ram": 123,
      "rom": 123,
      "arenaSize": 123
    },
    "eonRamOptimized": {
      "ram": 123,
      "rom": 123,
      "arenaSize": 123
    }
  },
  "timePerInferenceMs": 123,
  "mcuSupportError": "<string>",
  "customMetrics": [
    {
      "name": "<string>",
      "value": "<string>"
    }
  ],
  "hasPerformance": true,
  "profilingError": "<string>"
}

Authorizations

x-api-key
string
header
required

Path Parameters

projectId
integer
required

Project ID

jobId
integer
required

Job ID

Response

200 - application/json

OK

success
boolean
required

Whether the operation succeeded

variant
enum<string>
required
Available options:
int8,
float32,
akida
device
string
required
tfliteFileSizeBytes
integer
required
isSupportedOnMcu
boolean
required
customMetrics
object[]
required

Custom, device-specific performance metrics

hasPerformance
boolean
required

If false, then no metrics are available for this target

error
string

Optional error description (set if 'success' was false)

memory
object
timePerInferenceMs
integer
mcuSupportError
string
profilingError
string

Specific error during profiling (e.g. model not supported)