If you own an oscilloscope, sooner or later the urge to see something other than signals on the screen will strike. Some people ignore the urge and go about their normal business while others give in, spending hours carefully crafting images, games, and more. The process is time consuming and tricky as our own [Kevin Dady] discovered, but rewards come in the form of geek cred and are hard to pass up.
via HackADay
 Quantized Neural Networks for FPGA InferenceSponsored by Intel Implementing a low precision network in FPGA hardware for efficient inferencing provides numerous advantages when it comes to meeting demanding specifications. The increased flexibility allows optimization of throughput, overall power consumption, resource usage, device size, TOPs/watt, and deterministic latency. These are important benefits where scaling and efficiency are inherent requirements of the application. |
