PyTorchKR Papers

최신 논문

총 5,575편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2002.08258공식 코드 · Papers with Code

Knapsack Pruning with Inner Distillation

Neural network pruning reduces the computational cost of an over-parameterized network to improve its efficiency. Popular methods vary from $\ell_1$-norm sparsification to Neural Architecture Search (NAS). In this work, we propose a novel pruning method that optimizes the final accuracy of the pruned network and distills knowledge from the over-parameterized parent network's inner layers. To enable this approach, we formulate the network pruning as a Knapsack Problem which optimizes the trade-off between the importance of neurons and their associated computational cost. Then we prune the network channels while maintaining the high-level structure of the network. The pruned network is fine-tuned under the supervision of the parent network using its inner network knowledge, a technique we refer to as the Inner Knowledge Distillation. Our method leads to state-of-the-art pruning results on ImageNet, CIFAR-10 and CIFAR-100 using ResNet backbones. To prune complex network structures such as convolutions with skip-links and depth-wise convolutions, we propose a block grouping approach to cope with these structures. Through this we produce compact architectures with the same FLOPs as EfficientNet-B0 and MobileNetV3 but with higher accuracy, by $1\%$ and $0.3\%$ respectively on ImageNet, and faster runtime on GPU.

arXiv:2002.07613공식 코드 · Papers with Code

An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization

Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work well for natural images might not be applicable to medical image analysis. In this work, we extend the globally-aware multiple instance classifier, a framework we proposed to address these unique properties of medical images. This model first uses a low-capacity, yet memory-efficient, network on the whole image to identify the most informative regions. It then applies another higher-capacity network to collect details from chosen regions. Finally, it employs a fusion module that aggregates global and local information to make a final prediction. While existing methods often require lesion segmentation during training, our model is trained with only image-level labels and can generate pixel-level saliency maps indicating possible malignant findings. We apply the model to screening mammography interpretation: predicting the presence or absence of benign and malignant lesions. On the NYU Breast Cancer Screening Dataset, consisting of more than one million images, our model achieves an AUC of 0.93 in classifying breasts with malignant findings, outperforming ResNet-34 and Faster R-CNN. Compared to ResNet-34, our model is 4.1x faster for inference while using 78.4% less GPU memory. Furthermore, we demonstrate, in a reader study, that our model surpasses radiologist-level AUC by a margin of 0.11. The proposed model is available online: https://github.com/nyukat/GMIC.

arXiv:2002.07306

From English To Foreign Languages: Transferring Pre-trained Language Models

Pre-trained models have demonstrated their effectiveness in many downstream natural language processing (NLP) tasks. The availability of multilingual pre-trained models enables zero-shot transfer of NLP tasks from high resource languages to low resource ones. However, recent research in improving pre-trained models focuses heavily on English. While it is possible to train the latest neural architectures for other languages from scratch, it is undesirable due to the required amount of compute. In this work, we tackle the problem of transferring an existing pre-trained model from English to other languages under a limited computational budget. With a single GPU, our approach can obtain a foreign BERT base model within a day and a foreign BERT large within two days. Furthermore, evaluating our models on six languages, we demonstrate that our models are better than multilingual BERT on two zero-shot tasks: natural language inference and dependency parsing.

arXiv:2002.07754

Computational optimization of convolutional neural networks using separated filters architecture

This paper considers a convolutional neural network transformation that reduces computation complexity and thus speedups neural network processing. Usage of convolutional neural networks (CNN) is the standard approach to image recognition despite the fact they can be too computationally demanding, for example for recognition on mobile platforms or in embedded systems. In this paper we propose CNN structure transformation which expresses 2D convolution filters as a linear combination of separable filters. It allows to obtain separated convolutional filters by standard training algorithms. We study the computation efficiency of this structure transformation and suggest fast implementation easily handled by CPU or GPU. We demonstrate that CNNs designed for letter and digit recognition of proposed structure show 15% speedup without accuracy loss in industrial image recognition system. In conclusion, we discuss the question of possible accuracy decrease and the application of proposed transformation to different recognition problems. convolutional neural networks, computational optimization, separable filters, complexity reduction.

arXiv:2002.06736공식 코드 · Papers with Code

Directional Deep Embedding and Appearance Learning for Fast Video Object Segmentation

Most recent semi-supervised video object segmentation (VOS) methods rely on fine-tuning deep convolutional neural networks online using the given mask of the first frame or predicted masks of subsequent frames. However, the online fine-tuning process is usually time-consuming, limiting the practical use of such methods. We propose a directional deep embedding and appearance learning (DDEAL) method, which is free of the online fine-tuning process, for fast VOS. First, a global directional matching module, which can be efficiently implemented by parallel convolutional operations, is proposed to learn a semantic pixel-wise embedding as an internal guidance. Second, an effective directional appearance model based statistics is proposed to represent the target and background on a spherical embedding space for VOS. Equipped with the global directional matching module and the directional appearance model learning module, DDEAL learns static cues from the labeled first frame and dynamically updates cues of the subsequent frames for object segmentation. Our method exhibits state-of-the-art VOS performance without using online fine-tuning. Specifically, it achieves a J & F mean score of 74.8% on DAVIS 2017 dataset and an overall score G of 71.3% on the large-scale YouTube-VOS dataset, while retaining a speed of 25 fps with a single NVIDIA TITAN Xp GPU. Furthermore, our faster version runs 31 fps with only a little accuracy loss. Our code and trained networks are available at https://github.com/YingjieYin/Directional-Deep-Embedding-and-Appearance-Learning-for-Fast-Video-Object-Segmentation.

arXiv:2002.05292

NN-PARS: A Parallelized Neural Network Based Circuit Simulation Framework

The shrinking of transistor geometries as well as the increasing complexity of integrated circuits, significantly aggravate nonlinear design behavior. This demands accurate and fast circuit simulation to meet the design quality and time-to-market constraints. The existing circuit simulators which utilize lookup tables and/or closed-form expressions are either slow or inaccurate in analyzing the nonlinear behavior of designs with billions of transistors. To address these shortcomings, we present NN-PARS, a neural network (NN) based and parallelized circuit simulation framework with optimized event-driven scheduling of simulation tasks to maximize concurrency, according to the underlying GPU parallel processing capabilities. NN-PARS replaces the required memory queries in traditional techniques with parallelized NN-based computation tasks. Experimental results show that compared to a state-of-the-art current-based simulation method, NN-PARS reduces the simulation time by over two orders of magnitude in large circuits. NN-PARS also provides high accuracy levels in signal waveform calculations, with less than $2\%$ error compared to HSPICE.

arXiv:2002.05291

CSM-NN: Current Source Model Based Logic Circuit Simulation -- A Neural Network Approach

The miniaturization of transistors down to 5nm and beyond, plus the increasing complexity of integrated circuits, significantly aggravate short channel effects, and demand analysis and optimization of more design corners and modes. Simulators need to model output variables related to circuit timing, power, noise, etc., which exhibit nonlinear behavior. The existing simulation and sign-off tools, based on a combination of closed-form expressions and lookup tables are either inaccurate or slow, when dealing with circuits with more than billions of transistors. In this work, we present CSM-NN, a scalable simulation framework with optimized neural network structures and processing algorithms. CSM-NN is aimed at optimizing the simulation time by accounting for the latency of the required memory query and computation, given the underlying CPU and GPU parallel processing capabilities. Experimental results show that CSM-NN reduces the simulation time by up to $6\times$ compared to a state-of-the-art current source model based simulator running on a CPU. This speedup improves by up to $15\times$ when running on a GPU. CSM-NN also provides high accuracy levels, with less than $2\%$ error, compared to HSPICE.

arXiv:2002.04971

FastWave: Accelerating Autoregressive Convolutional Neural Networks on FPGA

Autoregressive convolutional neural networks (CNNs) have been widely exploited for sequence generation tasks such as audio synthesis, language modeling and neural machine translation. WaveNet is a deep autoregressive CNN composed of several stacked layers of dilated convolution that is used for sequence generation. While WaveNet produces state-of-the art audio generation results, the naive inference implementation is quite slow; it takes a few minutes to generate just one second of audio on a high-end GPU. In this work, we develop the first accelerator platform~\textit{FastWave} for autoregressive convolutional neural networks, and address the associated design challenges. We design the Fast-Wavenet inference model in Vivado HLS and perform a wide range of optimizations including fixed-point implementation, array partitioning and pipelining. Our model uses a fully parameterized parallel architecture for fast matrix-vector multiplication that enables per-layer customized latency fine-tuning for further throughput improvement. Our experiments comparatively assess the trade-off between throughput and resource utilization for various optimizations. Our best WaveNet design on the Xilinx XCVU13P FPGA that uses only on-chip memory, achieves 66 faster generation speed compared to CPU implementation and 11 faster generation speed than GPU implementation.

arXiv:2002.05022

Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator

Neural architecture search (NAS) has been very successful at outperforming human-designed convolutional neural networks (CNN) in accuracy, and when hardware information is present, latency as well. However, NAS-designed CNNs typically have a complicated topology, therefore, it may be difficult to design a custom hardware (HW) accelerator for such CNNs. We automate HW-CNN codesign using NAS by including parameters from both the CNN model and the HW accelerator, and we jointly search for the best model-accelerator pair that boosts accuracy and efficiency. We call this Codesign-NAS. In this paper we focus on defining the Codesign-NAS multiobjective optimization problem, demonstrating its effectiveness, and exploring different ways of navigating the codesign search space. For CIFAR-10 image classification, we enumerate close to 4 billion model-accelerator pairs, and find the Pareto frontier within that large search space. This allows us to evaluate three different reinforcement-learning-based search strategies. Finally, compared to ResNet on its most optimal HW accelerator from within our HW design space, we improve on CIFAR-100 classification accuracy by 1.3% while simultaneously increasing performance/area by 41% in just~1000 GPU-hours of running Codesign-NAS.

arXiv:2002.04803공식 코드 · Papers with Code

Machine Learning in Python: Main developments and technology trends in data science, machine learning, and artificial intelligence

Smarter applications are making better use of the insights gleaned from data, having an impact on every industry and research discipline. At the core of this revolution lies the tools and the methods that are driving it, from processing the massive piles of data generated each day to learning from and taking useful action. Deep neural networks, along with advancements in classical ML and scalable general-purpose GPU computing, have become critical components of artificial intelligence, enabling many of these astounding breakthroughs and lowering the barrier to adoption. Python continues to be the most preferred language for scientific computing, data science, and machine learning, boosting both performance and productivity by enabling the use of low-level libraries and clean high-level APIs. This survey offers insight into the field of machine learning with Python, taking a tour through important topics to identify some of the core hardware and software paradigms that have enabled it. We cover widely-used libraries and concepts, collected together for holistic comparison, with the goal of educating the reader and driving the field of Python machine learning forward.

arXiv:2002.04742

Fast Geometric Projections for Local Robustness Certification

Local robustness ensures that a model classifies all inputs within an $\ell_2$-ball consistently, which precludes various forms of adversarial inputs. In this paper, we present a fast procedure for checking local robustness in feed-forward neural networks with piecewise-linear activation functions. Such networks partition the input space into a set of convex polyhedral regions in which the network's behavior is linear; hence, a systematic search for decision boundaries within the regions around a given input is sufficient for assessing robustness. Crucially, we show how the regions around a point can be analyzed using simple geometric projections, thus admitting an efficient, highly-parallel GPU implementation that excels particularly for the $\ell_2$ norm, where previous work has been less effective. Empirically we find this approach to be far more precise than many approximate verification approaches, while at the same time performing multiple orders of magnitude faster than complete verifiers, and scaling to much deeper networks.

arXiv:2002.04688공식 코드 · Papers with Code

fastai: A Layered API for Deep Learning

fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed and matched to build new approaches. It aims to do both things without substantial compromises in ease of use, flexibility, or performance. This is possible thanks to a carefully layered architecture, which expresses common underlying patterns of many deep learning and data processing techniques in terms of decoupled abstractions. These abstractions can be expressed concisely and clearly by leveraging the dynamism of the underlying Python language and the flexibility of the PyTorch library. fastai includes: a new type dispatch system for Python along with a semantic type hierarchy for tensors; a GPU-optimized computer vision library which can be extended in pure Python; an optimizer which refactors out the common functionality of modern optimizers into two basic pieces, allowing optimization algorithms to be implemented in 4-5 lines of code; a novel 2-way callback system that can access any part of the data, model, or optimizer and change it at any point during training; a new data block API; and much more. We have used this library to successfully create a complete deep learning course, which we were able to write more quickly than using previous approaches, and the code was more clear. The library is already in wide use in research, industry, and teaching. NB: This paper covers fastai v2, which is currently in pre-release at http://dev.fast.ai/

arXiv:2002.04993공식 코드 · Papers with Code

Real-Time Semantic Background Subtraction

Semantic background subtraction SBS has been shown to improve the performance of most background subtraction algorithms by combining them with semantic information, derived from a semantic segmentation network. However, SBS requires high-quality semantic segmentation masks for all frames, which are slow to compute. In addition, most state-of-the-art background subtraction algorithms are not real-time, which makes them unsuitable for real-world applications. In this paper, we present a novel background subtraction algorithm called Real-Time Semantic Background Subtraction (denoted RT-SBS) which extends SBS for real-time constrained applications while keeping similar performances. RT-SBS effectively combines a real-time background subtraction algorithm with high-quality semantic information which can be provided at a slower pace, independently for each pixel. We show that RT-SBS coupled with ViBe sets a new state of the art for real-time background subtraction algorithms and even competes with the non real-time state-of-the-art ones. Note that we provide python CPU and GPU implementations of RT-SBS at https://github.com/cioppaanthony/rt-sbs.

arXiv:2002.03729

A lightweight target detection algorithm based on Mobilenet Convolution

Target detection algorithm based on deep learning needs high computer GPU configuration, even need to use high performance deep learning workstation, this not only makes the cost increase, also greatly limits the realizability of the ground, this paper introduces a kind of lightweight algorithm for target detection under the condition of the balance accuracy and computational efficiency, MobileNet as Backbone performs parameter The processing speed is 30fps on the RTX2060 card for images with the CNN separator layer. The processing speed is 30fps on the RTX2060 card for images with a resolution of 320*320.

arXiv:2002.03471공식 코드 · Papers with Code

MOGPTK: The Multi-Output Gaussian Process Toolkit

We present MOGPTK, a Python package for multi-channel data modelling using Gaussian processes (GP). The aim of this toolkit is to make multi-output GP (MOGP) models accessible to researchers, data scientists, and practitioners alike. MOGPTK uses a Python front-end, relies on the GPflow suite and is built on a TensorFlow back-end, thus enabling GPU-accelerated training. The toolkit facilitates implementing the entire pipeline of GP modelling, including data loading, parameter initialization, model learning, parameter interpretation, up to data imputation and extrapolation. MOGPTK implements the main multi-output covariance kernels from literature, as well as spectral-based parameter initialization strategies. The source code, tutorials and examples in the form of Jupyter notebooks, together with the API documentation, can be found at http://github.com/GAMES-UChile/mogptk

arXiv:2002.02885

Understanding and Optimizing Packed Neural Network Training for Hyper-Parameter Tuning

As neural networks are increasingly employed in machine learning practice, how to efficiently share limited training resources among a diverse set of model training tasks becomes a crucial issue. To achieve better utilization of the shared resources, we explore the idea of jointly training multiple neural network models on a single GPU in this paper. We realize this idea by proposing a primitive, called pack. We further present a comprehensive empirical study of pack and end-to-end experiments that suggest significant improvements for hyperparameter tuning. The results suggest: (1) packing two models can bring up to 40% performance improvement over unpacked setups for a single training step and the improvement increases when packing more models; (2) the benefit of the pack primitive largely depends on a number of factors including memory capacity, chip architecture, neural network structure, and batch size; (3) there exists a trade-off between packing and unpacking when training multiple neural network models on limited resources; (4) a pack-aware Hyperband is up to 2.7x faster than the original Hyperband, with this improvement growing as memory size increases and subsequently the density of models packed.

arXiv:2002.01981

Parallel 3DPIFCM Algorithm for Noisy Brain MRI Images

In this paper we implemented the algorithm we developed in [1] called 3DPIFCM in a parallel environment by using CUDA on a GPU. In our previous work we introduced 3DPIFCM which performs segmentation of images in noisy conditions and uses particle swarm optimization for finding the optimal algorithm parameters to account for noise. This algorithm achieved state of the art segmentation accuracy when compared to FCM (Fuzzy C-Means), IFCMPSO (Improved Fuzzy C-Means with Particle Swarm Optimization), GAIFCM (Genetic Algorithm Improved Fuzzy C-Means) on noisy MRI images of an adult Brain. When using a genetic algorithm or PSO (Particle Swarm Optimization) on a single machine for optimization we witnessed long execution times for practical clinical usage. Therefore, in the current paper our goal was to speed up the execution of 3DPIFCM by taking out parts of the algorithm and executing them as kernels on a GPU. The algorithm was implemented using the CUDA [13] framework from NVIDIA and experiments where performed on a server containing 64GB RAM , 8 cores and a TITAN X GPU with 3072 SP cores and 12GB of GPU memory. Our results show that the parallel version of the algorithm performs up to 27x faster than the original sequential version and 68x faster than GAIFCM algorithm. We show that the speedup of the parallel version increases as we increase the size of the image due to better utilization of cores in the GPU. Also, we show a speedup of up to 5x in our Brainweb experiment compared to other generic variants such as IFCMPSO and GAIFCM.

arXiv:2002.01427공식 코드 · Papers with Code

On the impact of selected modern deep-learning techniques to the performance and celerity of classification models in an experimental high-energy physics use case

Beginning from a basic neural-network architecture, we test the potential benefits offered by a range of advanced techniques for machine learning, in particular deep learning, in the context of a typical classification problem encountered in the domain of high-energy physics, using a well-studied dataset: the 2014 Higgs ML Kaggle dataset. The advantages are evaluated in terms of both performance metrics and the time required to train and apply the resulting models. Techniques examined include domain-specific data-augmentation, learning rate and momentum scheduling, (advanced) ensembling in both model-space and weight-space, and alternative architectures and connection methods. Following the investigation, we arrive at a model which achieves equal performance to the winning solution of the original Kaggle challenge, whilst being significantly quicker to train and apply, and being suitable for use with both GPU and CPU hardware setups. These reductions in timing and hardware requirements potentially allow the use of more powerful algorithms in HEP analyses, where models must be retrained frequently, sometimes at short notice, by small groups of researchers with limited hardware resources. Additionally, a new wrapper library for PyTorch called LUMIN is presented, which incorporates all of the techniques studied.

arXiv:2002.00250

Foreground object segmentation in RGB-D data implemented on GPU

This paper presents a GPU implementation of two foreground object segmentation algorithms: Gaussian Mixture Model (GMM) and Pixel Based Adaptive Segmenter (PBAS) modified for RGB-D data support. The simultaneous use of colour (RGB) and depth (D) data allows to improve segmentation accuracy, especially in case of colour camouflage, illumination changes and occurrence of shadows. Three GPUs were used to accelerate calculations: embedded NVIDIA Jetson TX2 (Maxwell architecture), mobile NVIDIA GeForce GTX 1050m (Pascal architecture) and efficient NVIDIA RTX 2070 (Turing architecture). Segmentation accuracy comparable to previously published works was obtained. Moreover, the use of a GPU platform allowed to get real-time image processing. In addition, the system has been adapted to work with two RGB-D sensors: RealSense D415 and D435 from Intel.

arXiv:2001.11396

Non-Determinism in TensorFlow ResNets

We show that the stochasticity in training ResNets for image classification on GPUs in TensorFlow is dominated by the non-determinism from GPUs, rather than by the initialisation of the weights and biases of the network or by the sequence of minibatches given. The standard deviation of test set accuracy is 0.02 with fixed seeds, compared to 0.027 with different seeds---nearly 74\% of the standard deviation of a ResNet model is non-deterministic. For test set loss the ratio of standard deviations is more than 80\%. These results call for more robust evaluation strategies of deep learning models, as a significant amount of the variation in results across runs can arise simply from GPU randomness.