Profile Job Results
Jobs
jo5m901yg
Results Ready
Name
sam_SAMDecoder
Target Device
- QCS8550 (Proxy)
- Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_embeddings: float32[1, 64, 64, 256]point_coords: float32[1, 1, 2]point_labels: float32[1, 1]mask_input: float32[1, 256, 256, 1]has_mask_input: float32[1]Completion Time
8/11/2024, 6:02:49 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
47.7 ms
Estimated Peak Memory Usage
4 - 308 MB
Compute Units
NPU
337
| Stage | Time | Memory |
|---|---|---|
First App Load | 13.2 s | 256-258 MB |
Subsequent App Load | 250 ms | 15-295 MB |
Inference | 47.7 ms | 4-308 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