| 1. |
- Wess, M., et al.
(författare)
-
ANNETTE : Accurate Neural Network Execution Time Estimation with Stacked Models
- 2021
-
Ingår i: IEEE Access. - : Institute of Electrical and Electronics Engineers Inc.. - 2169-3536. ; 9, s. 3545-3556
-
Tidskriftsartikel (refereegranskat)abstract
- With new accelerator hardware for Deep Neural Networks (DNNs), the computing power for Artificial Intelligence (AI) applications has increased rapidly. However, as DNN algorithms become more complex and optimized for specific applications, latency requirements remain challenging, and it is critical to find the optimal points in the design space. To decouple the architectural search from the target hardware, we propose a time estimation framework that allows for modeling the inference latency of DNNs on hardware accelerators based on mapping and layer-wise estimation models. The proposed methodology extracts a set of models from micro-kernel and multi-layer benchmarks and generates a stacked model for mapping and network execution time estimation. We compare estimation accuracy and fidelity of the generated mixed models, statistical models with the roofline model, and a refined roofline model for evaluation. We test the mixed models on the ZCU102 SoC board with Xilinx Deep Neural Network Development Kit (DNNDK) and Intel Neural Compute Stick 2 (NCS2) on a set of 12 state-of-the-art neural networks. It shows an average estimation error of 3.47% for the DNNDK and 7.44% for the NCS2, outperforming the statistical and analytical layer models for almost all selected networks. For a randomly selected subset of 34 networks of the NASBench dataset, the mixed model reaches fidelity of 0.988 in Spearman's $\rho $ rank correlation coefficient metric. © 2013 IEEE.
|
|
| 2. |
- Haas, B., et al.
(författare)
-
Neural Network Compression Through Shunt Connections and Knowledge Distillation for Semantic Segmentation Problems
- 2021
-
Ingår i: IFIP Advances in Information and Communication Technology. - Cham : Springer Science and Business Media Deutschland GmbH. - 9783030791490 ; , s. 349-361
-
Konferensbidrag (refereegranskat)abstract
- Employing convolutional neural network models for large scale datasets represents a big challenge. Especially embedded devices with limited resources cannot run most state-of-the-art model architectures in real-time, necessary for many applications. This paper proves the applicability of shunt connections on large scale datasets and narrows this computational gap. Shunt connections is a proposed method for MobileNet compression. We are the first to provide results of shunt connections for the MobileNetV3 model and for segmentation tasks on the Cityscapes dataset, using the DeeplabV3 architecture, on which we achieve compression by 28%, while observing a 3.52 drop in mIoU. The training of shunt-inserted models are optimized through knowledge distillation. The full code used for this work will be available online. © 2021, IFIP International Federation for Information Processing.
|
|
