This work presents CascadeCNN, an automated toolflow that pushes the
quantisation limits of any given CNN model, aiming to perform high-throughput
inference. A two-stage architecture tailored for any given CNN-FPGA pair is
generated, consisting of a low- and high-precision unit in a cascade. A
confidence evaluation unit is employed to identify misclassified cases from the
excessively low-precision unit and forward them to the high-precision unit for
re-processing. Experiments demonstrate that the proposed toolflow can achieve a
performance boost up to 55% for VGG-16 and 48% for AlexNet over the baseline
design for the same resource budget and accuracy, without the need of
retraining the model or accessing the training data.

CascadeCNN 是一个自动化工具流程，用于推动任何给定的 CNN 模型的量化极限，旨在进行高吞吐率推理。通过在级联中使用低 - 高精度单元以及置信度评估单元，实现对任何给定的 CNN-FPGA 配对的定制。实验证明，所提出的工具流程在相同的资源预算和准确性下，可以使 VGG-16 的性能提升高达 55％，AlexNet 的性能提升高达 48％，而无需重新训练模型或访问训练数据。