Evaluation and Development Kit - メーカー・企業と製品の一覧 | イプロス

Evaluation and Development Kitの製品一覧

1~2 件を表示 / 全 2 件

表示件数

Hailo-8 Evaluation Development Kit

Affordable and easy access to the development environment of the Hailo-8 AI Processor.

We have packaged a development environment to easily start developing AI applications using the Hailo-8 AI Processor. The evaluation development kit includes PC hardware equipped with the Hailo-8 Mini-PCIe module (with a performance value of 13 TOPS) as the execution environment for running Hailo-8. ■ Deployment toolchain compatible with industry-standard frameworks Supports model conversion from industry-standard frameworks to Hailo format, converting the bit configuration of models using the latest quantization algorithms to Hailo's configuration. Allocates hardware resources and user network resources to the physical resources of the Hailo device. Compiles the model into Hailo binary, loads the binary, and executes inference on the Hailo target device. The SDK supports both standalone inference that allows direct access to the device and TensorFlow integrated inference that facilitates integration with existing environments.

  • Other PCs and OA equipment
  • IoT
  • Measurement and Analysis Equipment
  • Evaluation and Development Kit

ブックマークに追加いたしました

ブックマーク一覧

ブックマークを削除いたしました

ブックマーク一覧

これ以上ブックマークできません

会員登録すると、ブックマークできる件数が増えて、ラベルをつけて整理することもできます

無料会員登録

Hailo-8 Evaluation Development Kit 2 "AT-Hailo8-Multi"

A development environment equipped with four Hailo-8 AI Processors for implementing parallel high-speed processing and multi-AI algorithms.

1. Support for Multi-AI Algorithms In deep learning, various algorithms have been developed, and depending on the 'type of data source being handled' such as images, audio, time series, and the intended application like 'classification', 'depth estimation', 'object recognition', 'face detection', and 'pose estimation', the optimal algorithm is selected and applied accordingly. Generally, in edge inference, a single learning model is executed for one image source. With AT-Hailo8-Multi, by equipping multiple Hailo-8 AI chips, it has become possible to 'apply multiple algorithms simultaneously to a single source'. 2. Linear Expansion of Inference Performance by Parallel Processing of Four Chips By parallel processing four chips, it supports a maximum processing capability of 104 TOPS, approaching that of data center-class GPUs. The power consumption of the chip processing this 104 TOPS performance is only 25W.

  • Other PCs and OA equipment
  • IoT
  • Measurement and Analysis Equipment
  • Evaluation and Development Kit

ブックマークに追加いたしました

ブックマーク一覧

ブックマークを削除いたしました

ブックマーク一覧

これ以上ブックマークできません

会員登録すると、ブックマークできる件数が増えて、ラベルをつけて整理することもできます

無料会員登録