quic / ai-hub-models

The Qualcomm® AI Hub Models are a collection of state-of-the-art machine learning models optimized for performance (latency, memory etc.) and ready to deploy on Qualcomm® devices.
https://aihub.qualcomm.com
BSD 3-Clause "New" or "Revised" License
338 stars 45 forks source link

Enhanced 'build_apk.py' logic & 'README.md' #41

Closed fangxingSR closed 1 month ago

fangxingSR commented 1 month ago

Enhanced 'build_apk.py' logic & 'README.md'.

There was an issue in 'build_apk.py': when only 'qnnsdk' and 'model_path' were provided as inputs, it incorrectly invoked the 'printmenu()' function to display a model selection menu, despite the model always being renamed to 'classification.tflite'. To address this, I adjusted the logic so that the model selection menu is only printed when neither 'model_name' nor 'model_path' is specified by the user. Specifically, I changed line 45 of 'build_apk.py' to read:
```
if not args.model_name and not args.model_path:
```

Additionally, I made several descriptive improvements to the 'README.md' file. Recognizing that newcomers primarily aim to compile and install the ImageClassification application, I included more concise and efficient instructions tailored to their needs, aiming to minimize their trial-and-error process and facilitate a smoother onboarding experience."
kory commented 1 month ago

Thank you!

kory commented 1 month ago

Thanks! Your contribution is included in release 0.6.0, which is being pushed out today.