开启时会模糊预览图，关闭后正常显示
RT @darshil: having tried both @superpower and @rythmhealth, there is a clear winner one took over a month to create an action plan the ot…
making everything for sale
RT @a16z: Mark Zuckerberg says progress comes from inventing tools that let us observe the world in a new way, from the microscope to AI mo…
Thread
the distribution is anything but normal
RT @doodlestein: This is just the beginning. This kind of stuff will find huge bipartisan support. Companies that replace human employees w…
Former Quant Investor, now building @lumera (formerly called Pastel Network) | My Open Source Projects: https://t.co/9qbOCDlaqM
smh Charles the AI just got delayed even further.
gpus and tractors Neural networks from Scratch book: https://t.co/hyMkWyUP7R https://t.co/8WGZRkUGsn
If you're using Colab and you feel like training your model on GPU is slow, switch to the TPU runtime and tune the "steps_per_execution" parameter in model.compile() (higher = more work being done on device before moving back to host RAM) Can often see a 4-5x speedup.
Co-founder @ndea. Co-founder @arcprize. Creator of Keras and ARC-AGI. Author of 'Deep Learning with Python'.