Profile Job Results
Jobs
jg9jod1v5
Results Ready
Name
easyocr_EasyOCRDetector
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 3, 608, 800]Completion Time
5/21/2025, 6:29:28 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.6.250402152434_116405
- QNN TfLite Delegate: v2.32.6.250402152434_116405
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.05.14.0
Estimated Inference Time
30.1 ms
Estimated Peak Memory Usage
16 ‑ 74 MB
Compute Units
NPU
42
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.87 s | 396‑403 MB |
Subsequent App Load | 1.93 s | 364‑491 MB |
Inference | 30.1 ms | 16‑74 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