In the recent years, artificial intelligence (AI) applies in various industries and has
changed around the world. Edge AI has became a virtual role when customers
spend more time and moved services on local devices to increase the privacy,
security and minimize the latency.
The Mustang-T100 integrated five Coral TPU modules in a real compact size PCIe
card with half-height and half-length, and offered well computing speed up to 20
TOPS and extremely low power consumption, only 15W. More, powered by
well-developed Tensorflow Lite community, it can smoothly and simply
implement the existing model to your edge inference project. The Mustang-T100
is an ideal AI PCIe accelerator card for image classification, object detection and
image segmentation.
How It Benifits
High Computing Capability
IEI Mustang-T100 leveraged the powerfull Coral edge TPU, a
complete and fast toolkit to build products with local AI, to
bring AI developers getting into a different AI inference
platform at the edge. The Mustang-T100 integrated five
Coral TPU modules to offered well computing speed up to
20 TOPS.
Low Power Consumption with Wide
Temperature Design
Approximating Energy Consumption : 15W
Operating Temperature : -20ºC~60ºC
Active Cooling
High Computing Capability
No need to build models from the ground up. TensorFlow
Lite models can be compiled to run on the Edge TPU.
Optimize Pre-trained Models at The Edge
Combined with AutoML VisionEdge, AI developers can use
Edge TPU to accelerate transfer-learning with a pre-trained
model at the edge devices directly.
Simply Create an AI Environment
Mustang-T100-T5 is able to easily apply in IEI AI-ready
systems, such as TANK series, FLEX series, and DRPC series
to creates an edge AI Inference Systems with high efficiency.
This site uses cookies in order to improve your user experience and to provide content tailored specifically to your interests. By continuing to browse our site you agree to our use of cookies, Data Privacy Notice and Terms of Use.
