Image recognition tasks typically use deep learning and require enormous processing power, thus relying on hardware accelerators like GPUs and FPGAs for fast, timely processing. Failure in real-time image recognition tasks can occur due to incorrect mapping on hardware accelerators, which may lead to timing uncertainty and incorrect behavior. Owing to the increased use of image recognition tasks in safety-critical applications like autonomous driving and medical imaging, it is imperative to assess their robustness to changes in the computational environment as parameters like deep learning frameworks, compiler optimizations for code generation, and hardware devices are not regulated with varying impact on model performance and correctness. In this paper we conduct robustness analysis of four popular image recognition models (MobileNetV2, ResNet101V2, DenseNet121 and InceptionV3) with the ImageNet dataset, assessing the impact of the following parameters in the model's computational environment: (1) deep learning frameworks; (2) compiler optimizations; and (3) hardware devices. We report sensitivity of model performance in terms of output label and inference time for changes in each of these environment parameters. We find that output label predictions for all four models are sensitive to choice of deep learning framework (by up to 57%) and insensitive to other parameters. On the other hand, model inference time was affected by all environment parameters with changes in hardware device having the most effect. The extent of effect was not uniform across models.

翻译：图像识别任务通常采用深度学习技术，需要巨大的处理能力，因此依赖GPU和FPGA等硬件加速器来实现快速、及时的处理。由于硬件加速器上的错误映射可能导致时序不确定性和错误行为，实时图像识别任务可能出现故障。随着图像识别任务在自动驾驶、医学影像等安全关键型应用中的广泛使用，评估其对计算环境变化的鲁棒性至关重要——因为深度学习框架、代码生成的编译器优化和硬件设备等参数缺乏规范，对模型性能和正确性有不同影响。本文基于ImageNet数据集，对四种主流图像识别模型（MobileNetV2、ResNet101V2、DenseNet121和InceptionV3）进行了鲁棒性分析，评估模型计算环境中以下参数的影响：(1)深度学习框架；(2)编译器优化；(3)硬件设备。我们分别报告了这些环境参数变化时模型在输出标签和推理时间方面的敏感性。研究发现，所有四种模型的输出标签预测均对深度学习框架的选择敏感（差异高达57%），而对其他参数不敏感。另一方面，模型推理时间受所有环境参数影响，其中硬件设备变化影响最大，且影响程度因模型而异。