Profile Job Results
Jobs
j5q6z94ep
Results Ready
Name
deeplabv3_plus_mobilenet_quantized
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 520, 520, 3]Completion Time
11/26/2024, 4:42:11 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
164 ms
Estimated Peak Memory Usage
4 ‑ 12 MB
Compute Units
NPU
136
| Stage | Time | Memory |
|---|---|---|
First App Load | 580 ms | 2‑8 MB |
Subsequent App Load | 288 ms | 0‑8 MB |
Inference | 164 ms | 4‑12 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| NNAPI Delegate | Value |
|---|---|
| accelerator_name | "qti-dsp" |
| execution_preference | kSustainedSpeed |
| allow_fp16 | true |
| NNAPI Delegate | Value |
|---|---|
| accelerator_name | "qti-hta" |
| execution_preference | kSustainedSpeed |
| allow_fp16 | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device