Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgkqzm3og
Results Ready
Name
deeplabv3_resnet50
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 520, 520, 3]
Completion Time
9/28/2025, 10:05:58 AM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.09.23.1
Estimated Inference Time
3.28 s
Estimated Peak Memory Usage
0 ‑ 106 MB
Compute Units
NPU
74
CPU
14
GPU
14
StageTimeMemory
First App Load
37.0 s134‑136 MB
Subsequent App Load
36.6 s98‑101 MB
Inference
3.28 s0‑106 MB
TensorFlow LiteValue
number_of_threads4
NNAPI DelegateValue
accelerator_name"qti-dsp"
execution_preferencekSustainedSpeed
allow_fp16true
NNAPI DelegateValue
accelerator_name"qti-hta"
execution_preferencekSustainedSpeed
allow_fp16true
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
XNNPACK DelegateValue

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

Run on device