Tensor Yard: One-Shot Algorithm of Hardware-Friendly Tensor-Train Decomposition for Convolutional Neural Networks

2021-08-09 · Anuar Taskynov, Vladimir Korviakov, Ivan Mazurenko, Yepan Xiong

Nowadays Deep Learning became widely used in many economic, technical and scientific areas of human interest. It is clear that efficiency of solutions based on Deep Neural Networks should consider not only quality metric for the target task, but also latency and constraints of target platform design should be taken into account. In this paper we present novel hardware-friendly Tensor-Train decomposition implementation for Convolutional Neural Networks together with Tensor Yard - one-shot training algorithm which optimizes an order of decomposition of network layers. These ideas allow to accelerate ResNet models on Ascend 310 NPU devices without significant loss of accuracy. For example we accelerate ResNet-101 by 14.6% with drop by 0.5 of top-1 ImageNet accuracy.

📄 PDF Abstract BibTeX arXiv:2108.04029

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Batch Normalization 설명 없음

Residual Connection 설명 없음

Average Pooling 설명 없음

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Smart Pipe System for a Shipyard 4.0

2024-02-06 · Paula Fraga-Lamas, Diego Noceda-Davila, Tiago M. Fernández-Caramés, Manuel A. Díaz-Bouza 외

As a result of the progressive implantation of the Industry 4.0 paradigm, many industries are experimenting a revolution that shipyards cannot ignore. Therefore, the application of the principles of Industry 4.0 to shipy…

LLM-Aided Compilation for Tensor Accelerators

2024-08-06 · Charles Hong, Sahil Bhatia, Altan Haan, Shengjun Kris Dong 외

Hardware accelerators, in particular accelerators for tensor processing, have many potential application domains. However, they currently lack the software infrastructure to support the majority of domains outside of dee…

Data Generation for Hardware-Friendly Post-Training Quantization

2024-10-29 · Lior Dikstein, Ariel Lapid, Arnon Netzer, Hai Victor Habi

Zero-shot quantization (ZSQ) using synthetic data is a key approach for post-training quantization (PTQ) under privacy and security constraints. However, existing data generation methods often struggle to effectively gen…

Data Augmentation GPU object-detection Object Detection+1

FastMamba: A High-Speed and Efficient Mamba Accelerator on FPGA with Accurate Quantization

2025-05-25 · Aotao Wang, Haikuo Shao, Shaobo Ma, Zhongfeng Wang

State Space Models (SSMs), like recent Mamba2, have achieved remarkable performance and received extensive attention. However, deploying Mamba2 on resource-constrained edge devices encounters many problems: severe outlie…

Computational Efficiency CPU GPU Mamba+2

GrateTile: Efficient Sparse Tensor Tiling for CNN Processing

2020-09-18 · Yu-Sheng Lin, Hung Chang Lu, Yang-Bin Tsao, Yi-Min Chih 외

We propose GrateTile, an efficient, hardwarefriendly data storage scheme for sparse CNN feature maps (activations). It divides data into uneven-sized subtensors and, with small indexing overhead, stores them in a compres…