Profile Job Results
Jobs
jqp4eyx1g
Results Ready
Name
trocr_TrOCREncoder
Target Device
- QCS8550 (Proxy)
- Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]Completion Time
8/11/2024, 5:50:28 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
170 ms
Estimated Peak Memory Usage
10 - 17 MB
Compute Units
NPU
579
CPU
11
GPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.83 s | 521-523 MB |
Subsequent App Load | 435 ms | 26-380 MB |
Inference | 170 ms | 10-17 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 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device