Profile Job Results

Jobs
jn5q4dwng
Results Ready
Name
detr_resnet101
Target Device
  • QCS8550 (Proxy)
  • Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 480, 480, 3]
Completion Time
8/11/2024, 8:38:52 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
24.8 ms
Estimated Peak Memory Usage
2 - 9 MB
Compute Units
NPU
855
GPU
1
StageTimeMemory
First App Load
15.6 s1 GB
Subsequent App Load
414 ms0-444 MB
Inference
24.8 ms2-9 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue
GPUv2 DelegateValue
inference_preferenceTFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED
inference_priority1TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY
inference_priority2TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE
inference_priority3TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION

Sign up to run this model on a hosted Qualcomm® device!

Run on device