Profile Job Results

Jobs
jlpe678vg
Results Ready
Name
swin_small
Target Device
  • XR2 Gen 2 (Proxy)
  • Android 13
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]
Completion Time
8/11/2024, 6:43:39 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
83.9 ms
Estimated Peak Memory Usage
7 - 343 MB
Compute Units
NPU
1538
CPU
23
GPU
2
StageTimeMemory
First App Load
25.4 s893-903 MB
Subsequent App Load
996 ms78-418 MB
Inference
83.9 ms7-343 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue
NNAPI DelegateValue
accelerator_name"qti-dsp"
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