Watch LIVE (recorded) as we a train a Keras CNN model with audio spectrograms for bird species identification on a V100 GPU - launching the notebook, checking TensorFlow for the GPU, and creating the next notebook to classify the audio data while it trains!
Check out the app at [ Ссылка ]!
In this video as part of our FL Bird Audio Sound Classification training process, we're launching a Google Cloud VM with a V100 GPU to train our Keras CNN model with audio spectrograms that are stored in a TensorFlow dataset in TFRecord files.
This is the UNABRIDGED version where mistakes are made, code is written on-the-fly, and sometimes we pause (but keep recording) to look things up. It's sometimes nice to watch at 1.5-2x speed, or check out one of the other (abridged) videos.
