PyTorchKR Papers

최신 논문

총 5,576편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2209.08699

An Adaptive Threshold for the Canny Edge Detection with Actor-Critic Algorithm

Visual surveillance aims to perform robust foreground object detection regardless of the time and place. Object detection shows good results using only spatial information, but foreground object detection in visual surveillance requires proper temporal and spatial information processing. In deep learning-based foreground object detection algorithms, the detection ability is superior to classical background subtraction (BGS) algorithms in an environment similar to training. However, the performance is lower than that of the classical BGS algorithm in the environment different from training. This paper proposes a spatio-temporal fusion network (STFN) that could extract temporal and spatial information using a temporal network and a spatial network. We suggest a method using a semi-foreground map for stable training of the proposed STFN. The proposed algorithm shows excellent performance in an environment different from training, and we show it through experiments with various public datasets. Also, STFN can generate a compliant background image in a semi-supervised method, and it can operate in real-time on a desktop with GPU. The proposed method shows 11.28% and 18.33% higher FM than the latest deep learning method in the LASIESTA and SBI dataset, respectively.

arXiv:2209.08435

Rethinking Personalized Ranking at Pinterest: An End-to-End Approach

In this work, we present our journey to revolutionize the personalized recommendation engine through end-to-end learning from raw user actions. We encode user's long-term interest in Pinner- Former, a user embedding optimized for long-term future actions via a new dense all-action loss, and capture user's short-term intention by directly learning from the real-time action sequences. We conducted both offline and online experiments to validate the performance of the new model architecture, and also address the challenge of serving such a complex model using mixed CPU/GPU setup in production. The proposed system has been deployed in production at Pinterest and has delivered significant online gains across organic and Ads applications.

arXiv:2209.07578공식 코드 · Papers with Code

Pixel-wise classification in graphene-detection with tree-based machine learning algorithms

Mechanical exfoliation of graphene and its identification by optical inspection is one of the milestones in condensed matter physics that sparked the field of 2D materials. Finding regions of interest from the entire sample space and identification of layer number is a routine task potentially amenable to automatization. We propose supervised pixel-wise classification methods showing a high performance even with a small number of training image datasets that require short computational time without GPU. We introduce four different tree-based machine learning algorithms -- decision tree, random forest, extreme gradient boost, and light gradient boosting machine. We train them with five optical microscopy images of graphene, and evaluate their performances with multiple metrics and indices. We also discuss combinatorial machine learning models between the three single classifiers and assess their performances in identification and reliability. The code developed in this paper is open to the public and will be released at github.com/gjung-group/Graphene_segmentation.

논문 ID: document/9590334

User Allocation in Mobile Edge Computing: A Deep Reinforcement Learning Approach

In recent times, the need for low latency has made it necessary to deploy application services physically and logically close to the users rather than using the cloud for hosting services. This paradigm of computing, known as edge or fog computing, is becoming increasingly popular. An edge user allocation policy determines how to allocate service requests from mobile users to MEC servers. Current state-of-the-art techniques assume that the total resource utilization on an edge server is equal to the sum of the individual resource utilizations of services provisioned from the edge server. However, the relationship between resources utilized on an edge server with the number of service requests served from there is usually highly non-linear, hence, mathematically modelling the resource utilization is challenging. This is especially true in case of an environment with CPU-GPU co-execution, as commonly observed in modern edge computing. In this work, we provide an on-device Deep Reinforcement Learning (DRL) framework to predict the resource utilization of incoming service requests from users, thereby estimating the number of users an edge server can accommodate for a given latency threshold. We further propose an algorithm to obtain the user allocation policy. We compare the performance of the proposed DRL framework with traditional allocation approaches and show that the DRL framework outperforms deterministic approaches by at least 10% in terms of the number of users allocated.

arXiv:2209.06979공식 코드 · Papers with Code

Efficient Quantized Sparse Matrix Operations on Tensor Cores

The exponentially growing model size drives the continued success of deep learning, but it brings prohibitive computation and memory cost. From the algorithm perspective, model sparsification and quantization have been studied to alleviate the problem. From the architecture perspective, hardware vendors provide Tensor cores for acceleration. However, it is very challenging to gain practical speedups from sparse, low-precision matrix operations on Tensor cores, because of the strict requirements for data layout and lack of support for efficiently manipulating the low-precision integers. We propose Magicube, a high-performance sparse-matrix library for low-precision integers on Tensor cores. Magicube supports SpMM and SDDMM, two major sparse operations in deep learning with mixed precision. Experimental results on an NVIDIA A100 GPU show that Magicube achieves on average 1.44x (up to 2.37x) speedup over the vendor-optimized library for sparse kernels, and 1.43x speedup over the state-of-the-art with a comparable accuracy for end-to-end sparse Transformer inference.

arXiv:2209.06800공식 코드 · Papers with Code

MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms

The increasing size of input graphs for graph neural networks (GNNs) highlights the demand for using multi-GPU platforms. However, existing multi-GPU GNN systems optimize the computation and communication individually based on the conventional practice of scaling dense DNNs. For irregularly sparse and fine-grained GNN workloads, such solutions miss the opportunity to jointly schedule/optimize the computation and communication operations for high-performance delivery. To this end, we propose MGG, a novel system design to accelerate full-graph GNNs on multi-GPU platforms. The core of MGG is its novel dynamic software pipeline to facilitate fine-grained computation-communication overlapping within a GPU kernel. Specifically, MGG introduces GNN-tailored pipeline construction and GPU-aware pipeline mapping to facilitate workload balancing and operation overlapping. MGG also incorporates an intelligent runtime design with analytical modeling and optimization heuristics to dynamically improve the execution performance. Extensive evaluation reveals that MGG outperforms state-of-the-art full-graph GNN systems across various settings: on average 4.41X, 4.81X, and 10.83X faster than DGL, MGG-UVM, and ROC, respectively.

arXiv:2209.06018

An Analysis of Collocation on GPUs for Deep Learning Training

Deep learning training is an expensive process that extensively uses GPUs, but not all model training saturates modern powerful GPUs. Multi-Instance GPU (MIG) is a new technology introduced by NVIDIA that can partition a GPU to better-fit workloads that do not require all the memory and compute resources of a full GPU. In this paper, we examine the performance of a MIG-enabled A100 GPU under deep learning workloads containing various sizes and combinations of models. We contrast the benefits of MIG to older workload collocation methods on GPUs: na\"ively submitting multiple processes on the same GPU and utilizing Multi-Process Service (MPS). Our results demonstrate that collocating multiple model training runs may yield significant benefits. In certain cases, it can lead up to four times training throughput despite increased epoch time. On the other hand, the aggregate memory footprint and compute needs of the models trained in parallel must fit the available memory and compute resources of the GPU. MIG can be beneficial thanks to its interference-free partitioning, especially when the sizes of the models align with the MIG partitioning options. MIG's rigid partitioning, however, may create sub-optimal GPU utilization for more dynamic mixed workloads. In general, we recommend MPS as the best performing and most flexible form of collocation for model training for a single user submitting training jobs.

arXiv:2209.04280공식 코드 · Papers with Code

F-coref: Fast, Accurate and Easy to Use Coreference Resolution

We introduce fastcoref, a python package for fast, accurate, and easy-to-use English coreference resolution. The package is pip-installable, and allows two modes: an accurate mode based on the LingMess architecture, providing state-of-the-art coreference accuracy, and a substantially faster model, F-coref, which is the focus of this work. F-coref allows to process 2.8K OntoNotes documents in 25 seconds on a V100 GPU (compared to 6 minutes for the LingMess model, and to 12 minutes of the popular AllenNLP coreference model) with only a modest drop in accuracy. The fast speed is achieved through a combination of distillation of a compact model from the LingMess model, and an efficient batching implementation using a technique we call leftover batching. Our code is available at https://github.com/shon-otmazgin/fastcoref

arXiv:2209.04042

Assessing Lower Limb Strength using Internet-of-Things Enabled Chair

This project describes the application of the technologies of Machine Learning and Internet-of-Things to assess the lower limb strength of individuals undergoing rehabilitation or therapy. Specifically, it seeks to measure and assess the progress of individuals by sensors attached to chairs and processing the data through Google GPU Tensorflow CoLab. Pressure sensors are attached to various locations on a chair, including but not limited to the seating area, backrest, hand rests, and legs. Sensor data from the individual performing both sit-to-stand transition and stand-to-sit transition provides a time series dataset regarding the pressure distribution and vibratory motion on the chair. The dataset and timing information can then be fed into a machine learning model to estimate the relative strength and weakness during various phases of the movement.

arXiv:2209.04161공식 코드 · Papers with Code

ApproxTrain: Fast Simulation of Approximate Multipliers for DNN Training and Inference

Edge training of Deep Neural Networks (DNNs) is a desirable goal for continuous learning; however, it is hindered by the enormous computational power required by training. Hardware approximate multipliers have shown their effectiveness for gaining resource-efficiency in DNN inference accelerators; however, training with approximate multipliers is largely unexplored. To build resource efficient accelerators with approximate multipliers supporting DNN training, a thorough evaluation of training convergence and accuracy for different DNN architectures and different approximate multipliers is needed. This paper presents ApproxTrain, an open-source framework that allows fast evaluation of DNN training and inference using simulated approximate multipliers. ApproxTrain is as user-friendly as TensorFlow (TF) and requires only a high-level description of a DNN architecture along with C/C++ functional models of the approximate multiplier. We improve the speed of the simulation at the multiplier level by using a novel LUT-based approximate floating-point (FP) multiplier simulator on GPU (AMSim). ApproxTrain leverages CUDA and efficiently integrates AMSim into the TensorFlow library, in order to overcome the absence of native hardware approximate multiplier in commercial GPUs. We use ApproxTrain to evaluate the convergence and accuracy of DNN training with approximate multipliers for small and large datasets (including ImageNet) using LeNets and ResNets architectures. The evaluations demonstrate similar convergence behavior and negligible change in test accuracy compared to FP32 and bfloat16 multipliers. Compared to CPU-based approximate multiplier simulations in training and inference, the GPU-accelerated ApproxTrain is more than 2500x faster. Based on highly optimized closed-source cuDNN/cuBLAS libraries with native hardware multipliers, the original TensorFlow is only 8x faster than ApproxTrain.

arXiv:2209.03353

Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimation

The application of the context-adaptive entropy model significantly improves the rate-distortion (R-D) performance, in which hyperpriors and autoregressive models are jointly utilized to effectively capture the spatial redundancy of the latent representations. However, the latent representations still contain some spatial correlations. In addition, these methods based on the context-adaptive entropy model cannot be accelerated in the decoding process by parallel computing devices, e.g. FPGA or GPU. To alleviate these limitations, we propose a learned multi-resolution image compression framework, which exploits the recently developed octave convolutions to factorize the latent representations into the high-resolution (HR) and low-resolution (LR) parts, similar to wavelet transform, which further improves the R-D performance. To speed up the decoding, our scheme does not use context-adaptive entropy model. Instead, we exploit an additional hyper layer including hyper encoder and hyper decoder to further remove the spatial redundancy of the latent representation. Moreover, the cross-resolution parameter estimation (CRPE) is introduced into the proposed framework to enhance the flow of information and further improve the rate-distortion performance. An additional information-fidelity loss is proposed to the total loss function to adjust the contribution of the LR part to the final bit stream. Experimental results show that our method separately reduces the decoding time by approximately 73.35 % and 93.44 % compared with that of state-of-the-art learned image compression methods, and the R-D performance is still better than H.266/VVC(4:2:0) and some learning-based methods on both PSNR and MS-SSIM metrics across a wide bit rates.

arXiv:2209.03704

Kernel-Segregated Transpose Convolution Operation

Transpose convolution has shown prominence in many deep learning applications. However, transpose convolution layers are computationally intensive due to the increased feature map size due to adding zeros after each element in each row and column. Thus, convolution operation on the expanded input feature map leads to poor utilization of hardware resources. The main reason for unnecessary multiplication operations is zeros at predefined positions in the input feature map. We propose an algorithmic-level optimization technique for the effective transpose convolution implementation to solve these problems. Based on kernel activations, we segregated the original kernel into four sub-kernels. This scheme could reduce memory requirements and unnecessary multiplications. Our proposed method was $3.09 (3.02) \times$ faster computation using the Titan X GPU (Intel Dual Core CPU) with a flower dataset from the Kaggle website. Furthermore, the proposed optimization method can be generalized to existing devices without additional hardware requirements. A simple deep learning model containing one transpose convolution layer was used to evaluate the optimization method. It showed $2.2 \times$ faster training using the MNIST dataset with an Intel Dual-core CPU than the conventional implementation.

arXiv:2209.03042

Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube

IceCube, a cubic-kilometer array of optical sensors built to detect atmospheric and astrophysical neutrinos between 1 GeV and 1 PeV, is deployed 1.45 km to 2.45 km below the surface of the ice sheet at the South Pole. The classification and reconstruction of events from the in-ice detectors play a central role in the analysis of data from IceCube. Reconstructing and classifying events is a challenge due to the irregular detector geometry, inhomogeneous scattering and absorption of light in the ice and, below 100 GeV, the relatively low number of signal photons produced per event. To address this challenge, it is possible to represent IceCube events as point cloud graphs and use a Graph Neural Network (GNN) as the classification and reconstruction method. The GNN is capable of distinguishing neutrino events from cosmic-ray backgrounds, classifying different neutrino event types, and reconstructing the deposited energy, direction and interaction vertex. Based on simulation, we provide a comparison in the 1-100 GeV energy range to the current state-of-the-art maximum likelihood techniques used in current IceCube analyses, including the effects of known systematic uncertainties. For neutrino event classification, the GNN increases the signal efficiency by 18% at a fixed false positive rate (FPR), compared to current IceCube methods. Alternatively, the GNN offers a reduction of the FPR by over a factor 8 (to below half a percent) at a fixed signal efficiency. For the reconstruction of energy, direction, and interaction vertex, the resolution improves by an average of 13%-20% compared to current maximum likelihood techniques in the energy range of 1-30 GeV. The GNN, when run on a GPU, is capable of processing IceCube events at a rate nearly double of the median IceCube trigger rate of 2.7 kHz, which opens the possibility of using low energy neutrinos in online searches for transient events.

arXiv:2209.02976공식 코드 · Papers with Code

YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications

For years, the YOLO series has been the de facto industry-level standard for efficient object detection. The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios. In this technical report, we strive to push its limits to the next level, stepping forward with an unwavering mindset for industry application. Considering the diverse requirements for speed and accuracy in the real environment, we extensively examine the up-to-date object detection advancements either from industry or academia. Specifically, we heavily assimilate ideas from recent network design, training strategies, testing techniques, quantization, and optimization methods. On top of this, we integrate our thoughts and practice to build a suite of deployment-ready networks at various scales to accommodate diversified use cases. With the generous permission of YOLO authors, we name it YOLOv6. We also express our warm welcome to users and contributors for further enhancement. For a glimpse of performance, our YOLOv6-N hits 35.9% AP on the COCO dataset at a throughput of 1234 FPS on an NVIDIA Tesla T4 GPU. YOLOv6-S strikes 43.5% AP at 495 FPS, outperforming other mainstream detectors at the same scale~(YOLOv5-S, YOLOX-S, and PPYOLOE-S). Our quantized version of YOLOv6-S even brings a new state-of-the-art 43.3% AP at 869 FPS. Furthermore, YOLOv6-M/L also achieves better accuracy performance (i.e., 49.5%/52.3%) than other detectors with a similar inference speed. We carefully conducted experiments to validate the effectiveness of each component. Our code is made available at https://github.com/meituan/YOLOv6.

arXiv:2209.03157

FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications

Real-time object detection on Unmanned Aerial Vehicles (UAVs) is a challenging issue due to the limited computing resources of edge GPU devices as Internet of Things (IoT) nodes. To solve this problem, in this paper, we propose a novel lightweight deep learning architectures named FasterX based on YOLOX model for real-time object detection on edge GPU. First, we design an effective and lightweight PixSF head to replace the original head of YOLOX to better detect small objects, which can be further embedded in the depthwise separable convolution (DS Conv) to achieve a lighter head. Then, a slimmer structure in the Neck layer termed as SlimFPN is developed to reduce parameters of the network, which is a trade-off between accuracy and speed. Furthermore, we embed attention module in the Head layer to improve the feature extraction effect of the prediction head. Meanwhile, we also improve the label assignment strategy and loss function to alleviate category imbalance and box optimization problems of the UAV dataset. Finally, auxiliary heads are presented for online distillation to improve the ability of position embedding and feature extraction in PixSF head. The performance of our lightweight models are validated experimentally on the NVIDIA Jetson NX and Jetson Nano GPU embedded platforms.Extensive experiments show that FasterX models achieve better trade-off between accuracy and latency on VisDrone2021 dataset compared to state-of-the-art models.

arXiv:2209.02341

EnergonAI: An Inference System for 10-100 Billion Parameter Transformer Models

Large transformer models display promising performance on a wide range of natural language processing (NLP) tasks. Although the AI community has expanded the model scale to the trillion parameter level, the practical deployment of 10-100 billion parameter models is still uncertain due to the latency, throughput, and memory constraints. In this paper, we proposed EnergonAI to solve the challenges of the efficient deployment of 10-100 billion parameter transformer models on single- or multi-GPU systems. EnergonAI adopts a hierarchy-controller system architecture to coordinate multiple devices and efficiently support different parallel patterns. It delegates the execution of sub-models to multiple workers in the single-controller style and applies tensor parallelism and pipeline parallelism among the workers in a multi-controller style. Upon the novel architecture, we propose three techniques, i.e. non-blocking pipeline parallelism, distributed redundant computation elimination, and peer memory pooling. EnergonAI enables the users to program complex parallel code the same as a serial one. Compared with the FasterTransformer, we have proven that EnergonAI has superior performance on latency and throughput. In our experiments, EnergonAI can achieve 37% latency reduction in tensor parallelism, 10% scalability improvement in pipeline parallelism, and it improves the model scale inferred on a single GPU by using a larger heterogeneous memory space at cost of limited performance reduction.

arXiv:2209.00860공식 코드 · Papers with Code

Real-time 3D Single Object Tracking with Transformer

LiDAR-based 3D single object tracking is a challenging issue in robotics and autonomous driving. Currently, existing approaches usually suffer from the problem that objects at long distance often have very sparse or partially-occluded point clouds, which makes the features extracted by the model ambiguous. Ambiguous features will make it hard to locate the target object and finally lead to bad tracking results. To solve this problem, we utilize the powerful Transformer architecture and propose a Point-Track-Transformer (PTT) module for point cloud-based 3D single object tracking task. Specifically, PTT module generates fine-tuned attention features by computing attention weights, which guides the tracker focusing on the important features of the target and improves the tracking ability in complex scenarios. To evaluate our PTT module, we embed PTT into the dominant method and construct a novel 3D SOT tracker named PTT-Net. In PTT-Net, we embed PTT into the voting stage and proposal generation stage, respectively. PTT module in the voting stage could model the interactions among point patches, which learns context-dependent features. Meanwhile, PTT module in the proposal generation stage could capture the contextual information between object and background. We evaluate our PTT-Net on KITTI and NuScenes datasets. Experimental results demonstrate the effectiveness of PTT module and the superiority of PTT-Net, which surpasses the baseline by a noticeable margin, ~10% in the Car category. Meanwhile, our method also has a significant performance improvement in sparse scenarios. In general, the combination of transformer and tracking pipeline enables our PTT-Net to achieve state-of-the-art performance on both two datasets. Additionally, PTT-Net could run in real-time at 40FPS on NVIDIA 1080Ti GPU. Our code is open-sourced for the research community at https://github.com/shanjiayao/PTT.

arXiv:2208.14818공식 코드 · Papers with Code

PyTorch Image Quality: Metrics for Image Quality Assessment

Image Quality Assessment (IQA) metrics are widely used to quantitatively estimate the extent of image degradation following some forming, restoring, transforming, or enhancing algorithms. We present PyTorch Image Quality (PIQ), a usability-centric library that contains the most popular modern IQA algorithms, guaranteed to be correctly implemented according to their original propositions and thoroughly verified. In this paper, we detail the principles behind the foundation of the library, describe the evaluation strategy that makes it reliable, provide the benchmarks that showcase the performance-time trade-offs, and underline the benefits of GPU acceleration given the library is used within the PyTorch backend. PyTorch Image Quality is an open source software: https://github.com/photosynthesis-team/piq/.

arXiv:2208.14655

XCAT -- Lightweight Quantized Single Image Super-Resolution using Heterogeneous Group Convolutions and Cross Concatenation

We propose a lightweight, single image super-resolution network for mobile devices, named XCAT. XCAT introduces Heterogeneous Group Convolution Blocks with Cross Concatenations (HXBlock). The heterogeneous split of the input channels to the group convolution blocks reduces the number of operations, and cross concatenation allows for information flow between the intermediate input tensors of cascaded HXBlocks. Cross concatenations inside HXBlocks can also avoid using more expensive operations like 1x1 convolutions. To further prev ent expensive tensor copy operations, XCAT utilizes non-trainable convolution kernels to apply up sampling operations. Designed with integer quantization in mind, XCAT also utilizes several techniques on training, like intensity-based data augmentation. Integer quantized XCAT operates in real time on Mali-G71 MP2 GPU with 320ms, and on Synaptics Dolphin NPU with 30ms (NCHW) and 8.8ms (NHWC), suitable for real-time applications.

arXiv:2208.14600

ELSR: Extreme Low-Power Super Resolution Network For Mobile Devices

With the popularity of mobile devices, e.g., smartphone and wearable devices, lighter and faster model is crucial for the application of video super resolution. However, most previous lightweight models tend to concentrate on reducing lantency of model inference on desktop GPU, which may be not energy efficient in current mobile devices. In this paper, we proposed Extreme Low-Power Super Resolution (ELSR) network which only consumes a small amount of energy in mobile devices. Pretraining and finetuning methods are applied to boost the performance of the extremely tiny model. Extensive experiments show that our method achieves a excellent balance between restoration quality and power consumption. Finally, we achieve a competitive score of 90.9 with PSNR 27.34 dB and power 0.09 W/30FPS on the target MediaTek Dimensity 9000 plantform, ranking 1st place in the Mobile AI & AIM 2022 Real-Time Video Super-Resolution Challenge.