github aidlearning/AidLearning-FrameWork v0.87
Add tflite GPU acceleration using python

latest releases: v1.3.0, v1.2.1, v0.92...
3 years ago
  1. Fix the problem that cannot upgrade, fix the problem that Perl version does not match, and fix update

  2. Vscode updates to the latest version, and supports online quick installation of plug-ins, including golang. Built in examples can load AI models in vscode

  3. Built in chromedriver automatic control module

  4. Repair and installation of MySQL server

  5. Repair of X-mode display size, over display and magnification on PC side

  6. The example of built-in aidbot smart car supports USB control of smart car and openbot control at the same time 🚗

  7. Fix the camera display problem in sl4a mode
    8, support usbcam, you can connect the USB camera directly to the mobile phone through OTG, and you can see the real-time video picture of the USB camera through the return key under the full screen command line, which can be recorded.

  8. Solve the problem of incomplete display of the browser on the tablet selection screen

  9. Fix the problem of apt update source. Domestic users have built-in Huawei source, which is very fast

  10. Python 3 has built-in Tkinter module, which can be directly imported to Tkinter

  11. Built in ADB command

  12. Python has built-in uiautomator2 package. Uiautomator2 is a library that can use Python to automate the UI of Android devices. The bottom layer is based on Google UI Automator, which can obtain any control property on the screen.

  13. Update the document and add drag and drop function. You can directly drag and drop the computer files to the document on the computer side, and the files will be automatically copied to the folder in aid

  14. Py2apk major update, support the development of GPU program packaged

  15. Write permission of external SD card (to be verified)

  16. New developer debugging mode is added in X mode, which can simulate the touch screen feeling of mobile phone in X mode. Click debugging mode, and the document can scroll directly without dragging the scroll bar.

  17. Add a new app application center, which can graphically install your apt package and related linux software like native Linux

  18. Finally, aid adds CPU acceleration and GPU acceleration, and tflite is built into version 0.87. tflite GPU module can fully release the GPU performance of mobile phone, support CPU + GPU mode, and speed up at the same time! tflite.NNModel (model_ Path, inshape, outshape, 4,0) # - 4 represents 4 CPU threads, 0 represents GPU, - 1 represents CPU, and 1 represents the number of nnapi threads. I set 4 threads on aid. You can flexibly set the number of threads and use GPU + CPU mode

  19. Optimize and support the open camera function of OpenCV. With cvs package, you can set the resolution of the camera and access it more simply. You don't need to define the display dialog box any more.
    from cvs import *
    cap= cvs.VideoCapture (0)
    while True:
    img = cap.read ()
    cvs.imshow (img)

  20. An excellent example of high-performance AI is added. In examples, you can learn how to use tflite GPU to speed up your AI application using python.

Don't miss a new AidLearning-FrameWork release

NewReleases is sending notifications on new releases.