Live Demonstration: CNN Inference on the Focal Plane with a Pixel Processor Array

Live Demonstration: CNN Inference on the Focal Plane with a Pixel Processor Array
复制标题

现场演示:使用像素处理器阵列在焦平面上进行 CNN 推理

DOI:
10.1109/iscas45731.2020.9180959
复制
发表时间:
2020
期刊:
--
影响因子:
--
通讯作者:
Carey S
Carey S
中科院分区:
--
文献类型:
--
作者:
Carey S

文献摘要

相似文献

我们在像素处理器阵列设备上提出了一种新的CNN推理方法,使用手写数字(数字0-9)分类任务进行演示,神经网络计算的所有步骤都在焦平面上执行。我们部署的视觉芯片(SCAMP-7)在图像传感器中集成了一个256×256处理器元件阵列(PE)。算法运行速度超过3000帧/秒,分类准确率超过90%,传感器芯片只输出10个与分类分数对应的标量值。
We present a novel method of CNN inference on a pixel processor array device, demonstrating it using a handwritten digit (digits 0–9) classification task, with all steps of the neural network computation performed on the focal plane. The vision chip that we deploy (SCAMP-7) has a 256×256 array of processor elements (PE) integrated within the image sensor. The algorithm runs at over 3000 frames per second (FPS) and over 90% classification accuracy, with the sensor chip only outputting ten scalar values corresponding to the classification scores.