This notebook provides basic example code to build, run, and fine-tune MoViNets (Mobile Video Networks). The models are trained on the Kinetics-600 dataset to be able to recognize 600 different human actions (such as playing trumpet, robot dancing, bowling, and more) and can classify video streams captured on a modern smartphone in real-time. You can download the pre-trained TensorFlow Lite models from TensorFlow Hub or try it out using our Android and Raspberry Pi demo apps, as well as fine-tune your own MoViNets with the Colab demo and the code in the TensorFlow Model Garden
Everything looks fine with the notebook, you can go to “runtim” and select “run all” to execute all the cells, without any errors. However, there are some parts (like downloading dataset and modules) which may take some time to execute as mentioned in the comments in notebook.
For smaller models like (a0-A2), simple CPU is enough, but for fine tuning, GPU is recommended to speed up the process.
Notebook Credit 🌟