Profile Job Results
Jobs
jp4dqoe1p
Results Ready
Name
easyocr_EasyOCRDetector
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 3, 608, 800]Completion Time
9/27/2025, 10:44:25 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.38.0.250901140452_125126
- QNN TfLite Delegate: v2.38.0.250901140452_125126
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
41.0 ms
Estimated Peak Memory Usage
2 ‑ 141 MB
Compute Units
NPU
42
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.03 s | 443‑444 MB |
Subsequent App Load | 2.03 s | 466‑469 MB |
Inference | 41.0 ms | 2‑141 MB |
| 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