Train Your Own Deep Net  --  How-to Video

Train deep nets that can work on low-end hardware, use only a few kB of memory while drawing power in the sub-µW range.

A download link to the trained net will be emailed to you about a day after you upload the data.

This portal lives on the Google Cloud and requires a Google or G Suite account for sign-in. If you use Gmail, you already have a Google account.

After you have signed in, click on Continue.

Application Domain

The INFXL deep net is ideal for energy-constrained IoT edge devices and wearables. It is targeted at data from temperature, pressure, vibration, acceleration, speed, angular velocity, tilt, flow, smell, taste, and environmental sensors.

Ultra-Low Power, Fast, Compact Deep Nets

The INFXL deep net runs well on low-end hardware, but it can provide 10x the throughput of conventional nets on higher-end MCUs and FPGAs. It will be sent to you as optimized C code, free from floating-point ops or multiplications.

Sample code:   trained deep net

Training Data Files

Data must be organized into two CSV files: features; labels. They must not exceed 10 MiB and 3 MiB in size, respectively. They must consist of integer values only and not have column headings or missing values.

Each label must have its own column, e.g. two columns for a two-class problem.

Binary columns must be mapped to the set {-127, 127}. Continuous-valued columns must be mapped to the range [127, -127]. For example, if continuous values are in the range [0, 1], they are to be mapped using int(round(254 * value - 127))

Sample data:   features   labels