Profile Job Results
Jobs
jgdex0l65
Results Ready
Name
rtmpose_body2d
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 3, 256, 192]Completion Time
4/8/2025, 1:28:20 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
1.10 s
Estimated Peak Memory Usage
24 ‑ 108,136 GB
Compute Units
NPU
271
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.08 min | 95,052‑96,188 GB |
Subsequent App Load | 9.13 min | 133,744‑136,876 GB |
Inference | 1.10 s | 24‑108,136 GB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device