Profile Job Results
Jobs
j5wev6435
Results Ready
Name
face_attrib_net_quantized
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image
: uint8[1, 3, 128, 128]Completion Time
1/21/2025, 3:37:09 PM
Versions
- TensorFlow Lite: 2.17.0
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
79.6 ms
Estimated Peak Memory Usage
2 ‑ 5 MB
Compute Units
CPU
121
NPU
47
Stage | Time | Memory |
---|---|---|
First App Load | 483 ms | 13‑15 MB |
Subsequent App Load | 159 ms | 17‑20 MB |
Inference | 79.6 ms | 2‑5 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 |
XNNPACK Delegate | Value |
---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device