Yu-Te Cheng – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2023-02-13T17:04:00Z http://www.open-lab.net/blog/feed/ Yu-Te Cheng <![CDATA[Speeding Up Deep Learning Inference Using TensorFlow, ONNX, and NVIDIA TensorRT]]> http://www.open-lab.net/blog/?p=16755 2022-08-21T23:39:52Z 2021-07-20T13:00:00Z This post was updated July 20, 2021 to reflect NVIDIA TensorRT 8.0 updates. In this post, you learn how to deploy TensorFlow trained deep learning models using...]]>

Source

]]>
19
Yu-Te Cheng <![CDATA[Discovering GPU-friendly Deep Neural Networks with Unified Neural Architecture Search]]> http://www.open-lab.net/blog/?p=21847 2022-08-21T23:40:45Z 2020-11-05T21:29:02Z After the first successes of deep learning, designing neural network architectures with desirable performance criteria for a given task (for example, high...]]>

After the first successes of deep learning, designing neural network architectures with desirable performance criteria for a given task (for example, high accuracy or low latency) has been a challenging problem. Some call it alchemy and some intuition, but the task of discovering a novel architecture often involves a tedious and costly trial-and-error process of searching in an exponentially large…

Source

]]>
0
Yu-Te Cheng <![CDATA[Object Detection and Lane Segmentation Using Multiple Accelerators with DRIVE AGX]]> http://www.open-lab.net/blog/?p=14880 2023-02-13T17:04:00Z 2019-06-20T13:00:32Z [caption id="attachment_14898" align="alignright" width="610"] DRIVE AGX is NVIDIA's platform for autonomous driving[/caption] Autonomous vehicles require fast...]]>

Autonomous vehicles require fast and accurate perception of the surrounding environment in order to accomplish a wide set of tasks concurrently in real time. Systems need to handle the detection of obstacles, determine the boundaries of lanes, intersection detection, and sign recognition among many more functions over a large variety of environments, conditions, and situations and do this work…

Source

]]>
0
���˳���97caoporen����