PyTorchKR Papers

최신 논문

총 5,575편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1901.02217

Tree Tensor Networks for Generative Modeling

Matrix product states (MPS), a tensor network designed for one-dimensional quantum systems, has been recently proposed for generative modeling of natural data (such as images) in terms of `Born machine'. However, the exponential decay of correlation in MPS restricts its representation power heavily for modeling complex data such as natural images. In this work, we push forward the effort of applying tensor networks to machine learning by employing the Tree Tensor Network (TTN) which exhibits balanced performance in expressibility and efficient training and sampling. We design the tree tensor network to utilize the 2-dimensional prior of the natural images and develop sweeping learning and sampling algorithms which can be efficiently implemented utilizing Graphical Processing Units (GPU). We apply our model to random binary patterns and the binary MNIST datasets of handwritten digits. We show that TTN is superior to MPS for generative modeling in keeping correlation of pixels in natural images, as well as giving better log-likelihood scores in standard datasets of handwritten digits. We also compare its performance with state-of-the-art generative models such as the Variational AutoEncoders, Restricted Boltzmann machines, and PixelCNN. Finally, we discuss the future development of Tensor Network States in machine learning problems.

arXiv:1901.02144공식 코드 · Papers with Code

Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps

Deep learning solutions are being increasingly used in mobile applications. Although there are many open-source software tools for the development of deep learning solutions, there are no guidelines in one place in a unified manner for using these tools towards real-time deployment of these solutions on smartphones. From the variety of available deep learning tools, the most suited ones are used in this paper to enable real-time deployment of deep learning inference networks on smartphones. A uniform flow of implementation is devised for both Android and iOS smartphones. The advantage of using multi-threading to achieve or improve real-time throughputs is also showcased. A benchmarking framework consisting of accuracy, CPU/GPU consumption and real-time throughput is considered for validation purposes. The developed deployment approach allows deep learning models to be turned into real-time smartphone apps with ease based on publicly available deep learning and smartphone software tools. This approach is applied to six popular or representative convolutional neural network models and the validation results based on the benchmarking metrics are reported.

arXiv:1901.01007

FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters

Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is generally done by distributing tasks in batch mode using methods such as distributed synchronous SGD. Among the issues with this approach is that to make the distributed cluster work with high utilization, the workload distributed to each node must be large, which implies nontrivial growth in the SGD mini-batch size. In this paper, we propose a framework called FPDeep, which uses a hybrid of model and layer parallelism to configure distributed reconfigurable clusters to train DNNs. This approach has numerous benefits. First, the design does not suffer from batch size growth. Second, novel workload and weight partitioning leads to balanced loads of both among nodes. And third, the entire system is a fine-grained pipeline. This leads to high parallelism and utilization and also minimizes the time features need to be cached while waiting for back-propagation. As a result, storage demand is reduced to the point where only on-chip memory is used for the convolution layers. We evaluate FPDeep with the Alexnet, VGG-16, and VGG-19 benchmarks. Experimental results show that FPDeep has good scalability to a large number of FPGAs, with the limiting factor being the FPGA-to-FPGA bandwidth. With 6 transceivers per FPGA, FPDeep shows linearity up to 83 FPGAs. Energy efficiency is evaluated with respect to GOPs/J. FPDeep provides, on average, 6.36x higher energy efficiency than comparable GPU servers.

arXiv:1901.00858

HG-Caffe: Mobile and Embedded Neural Network GPU (OpenCL) Inference Engine with FP16 Supporting

Breakthroughs in the fields of deep learning and mobile system-on-chips are radically changing the way we use our smartphones. However, deep neural networks inference is still a challenging task for edge AI devices due to the computational overhead on mobile CPUs and a severe drain on the batteries. In this paper, we present a deep neural network inference engine named HG-Caffe, which supports GPUs with half precision. HG-Caffe provides up to 20 times speedup with GPUs compared to the original implementations. In addition to the speedup, the peak memory usage is also reduced to about 80%. With HG-Caffe, more innovative and fascinating mobile applications will be turned into reality.

arXiv:1812.11731

Batch Size Influence on Performance of Graphic and Tensor Processing Units during Training and Inference Phases

The impact of the maximally possible batch size (for the better runtime) on performance of graphic processing units (GPU) and tensor processing units (TPU) during training and inference phases is investigated. The numerous runs of the selected deep neural network (DNN) were performed on the standard MNIST and Fashion-MNIST datasets. The significant speedup was obtained even for extremely low-scale usage of Google TPUv2 units (8 cores only) in comparison to the quite powerful GPU NVIDIA Tesla K80 card with the speedup up to 10x for training stage (without taking into account the overheads) and speedup up to 2x for prediction stage (with and without taking into account overheads). The precise speedup values depend on the utilization level of TPUv2 units and increase with the increase of the data volume under processing, but for the datasets used in this work (MNIST and Fashion-MNIST with images of sizes 28x28) the speedup was observed for batch sizes >512 images for training phase and >40 000 images for prediction phase. It should be noted that these results were obtained without detriment to the prediction accuracy and loss that were equal for both GPU and TPU runs up to the 3rd significant digit for MNIST dataset, and up to the 2nd significant digit for Fashion-MNIST dataset.

arXiv:1812.11473

ORIGAMI: A Heterogeneous Split Architecture for In-Memory Acceleration of Learning

Memory bandwidth bottleneck is a major challenges in processing machine learning (ML) algorithms. In-memory acceleration has potential to address this problem; however, it needs to address two challenges. First, in-memory accelerator should be general enough to support a large set of different ML algorithms. Second, it should be efficient enough to utilize bandwidth while meeting limited power and area budgets of logic layer of a 3D-stacked memory. We observe that previous work fails to simultaneously address both challenges. We propose ORIGAMI, a heterogeneous set of in-memory accelerators, to support compute demands of different ML algorithms, and also uses an off-the-shelf compute platform (e.g.,FPGA,GPU,TPU,etc.) to utilize bandwidth without violating strict area and power budgets. ORIGAMI offers a pattern-matching technique to identify similar computation patterns of ML algorithms and extracts a compute engine for each pattern. These compute engines constitute heterogeneous accelerators integrated on logic layer of a 3D-stacked memory. Combination of these compute engines can execute any type of ML algorithms. To utilize available bandwidth without violating area and power budgets of logic layer, ORIGAMI comes with a computation-splitting compiler that divides an ML algorithm between in-memory accelerators and an out-of-the-memory platform in a balanced way and with minimum inter-communications. Combination of pattern matching and split execution offers a new design point for acceleration of ML algorithms. Evaluation results across 12 popular ML algorithms show that ORIGAMI outperforms state-of-the-art accelerator with 3D-stacked memory in terms of performance and energy-delay product (EDP) by 1.5x and 29x (up to 1.6x and 31x), respectively. Furthermore, results are within a 1% margin of an ideal system that has unlimited compute resources on logic layer of a 3D-stacked memory.

arXiv:1812.11214공식 코드 · Papers with Code

Kymatio: Scattering Transforms in Python

The wavelet scattering transform is an invariant signal representation suitable for many signal processing and machine learning applications. We present the Kymatio software package, an easy-to-use, high-performance Python implementation of the scattering transform in 1D, 2D, and 3D that is compatible with modern deep learning frameworks. All transforms may be executed on a GPU (in addition to CPU), offering a considerable speed up over CPU implementations. The package also has a small memory footprint, resulting inefficient memory usage. The source code, documentation, and examples are available undera BSD license at https://www.kymat.io/

arXiv:1901.00444

BMF: Block matrix approach to factorization of large scale data

Matrix Factorization (MF) on large scale matrices is computationally as well as memory intensive task. Alternative convergence techniques are needed when the size of the input matrix is higher than the available memory on a Central Processing Unit (CPU) and Graphical Processing Unit (GPU). While alternating least squares (ALS) convergence on CPU could take forever, loading all the required matrices on to GPU memory may not be possible when the dimensions are significantly higher. Hence we introduce a novel technique that is based on considering the entire data into a block matrix and relies on factorization at a block level.

arXiv:1901.00275공식 코드 · Papers with Code

Vector and Line Quantization for Billion-scale Similarity Search on GPUs

Billion-scale high-dimensional approximate nearest neighbour (ANN) search has become an important problem for searching similar objects among the vast amount of images and videos available online. The existing ANN methods are usually characterized by their specific indexing structures, including the inverted index and the inverted multi-index structure. The inverted index structure is amenable to GPU-based implementations, and the state-of-the-art systems such as Faiss are able to exploit the massive parallelism offered by GPUs. However, the inverted index requires high memory overhead to index the dataset effectively. The inverted multi-index structure is difficult to implement for GPUs, and also ineffective in dealing with database with different data distributions. In this paper we propose a novel hierarchical inverted index structure generated by vector and line quantization methods. Our quantization method improves both search efficiency and accuracy, while maintaining comparable memory consumption. This is achieved by reducing search space and increasing the number of indexed regions. We introduce a new ANN search system, VLQ-ADC, that is based on the proposed inverted index, and perform extensive evaluation on two public billion-scale benchmark datasets SIFT1B and DEEP1B. Our evaluation shows that VLQ-ADC significantly outperforms the state-of-the-art GPU- and CPU-based systems in terms of both accuracy and search speed. The source code of VLQ-ADC is available at https://github.com/zjuchenwei/vector-line-quantization.

arXiv:1812.10624

Stanza: Layer Separation for Distributed Training in Deep Learning

The parameter server architecture is prevalently used for distributed deep learning. Each worker machine in a parameter server system trains the complete model, which leads to a hefty amount of network data transfer between workers and servers. We empirically observe that the data transfer has a non-negligible impact on training time. To tackle the problem, we design a new distributed training system called Stanza. Stanza exploits the fact that in many models such as convolution neural networks, most data exchange is attributed to the fully connected layers, while most computation is carried out in convolutional layers. Thus, we propose layer separation in distributed training: the majority of the nodes just train the convolutional layers, and the rest train the fully connected layers only. Gradients and parameters of the fully connected layers no longer need to be exchanged across the cluster, thereby substantially reducing the data transfer volume. We implement Stanza on PyTorch and evaluate its performance on Azure and EC2. Results show that Stanza accelerates training significantly over current parameter server systems: on EC2 instances with Tesla V100 GPU and 10Gb bandwidth for example, Stanza is 1.34x--13.9x faster for common deep learning models.

arXiv:1812.10889공식 코드 · Papers with Code

InstaGAN: Instance-aware Image-to-Image Translation

Unsupervised image-to-image translation has gained considerable attention due to the recent impressive progress based on generative adversarial networks (GANs). However, previous methods often fail in challenging cases, in particular, when an image has multiple target instances and a translation task involves significant changes in shape, e.g., translating pants to skirts in fashion images. To tackle the issues, we propose a novel method, coined instance-aware GAN (InstaGAN), that incorporates the instance information (e.g., object segmentation masks) and improves multi-instance transfiguration. The proposed method translates both an image and the corresponding set of instance attributes while maintaining the permutation invariance property of the instances. To this end, we introduce a context preserving loss that encourages the network to learn the identity function outside of target instances. We also propose a sequential mini-batch inference/training technique that handles multiple instances with a limited GPU memory and enhances the network to generalize better for multiple instances. Our comparative evaluation demonstrates the effectiveness of the proposed method on different image datasets, in particular, in the aforementioned challenging cases. Code and results are available in https://github.com/sangwoomo/instagan

arXiv:1812.09834

Holistic Decomposition Convolution for Effective Semantic Segmentation of 3D MR Images

Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many different 2D medical image analysis tasks. In clinical practice, however, a large part of the medical imaging data available is in 3D. This has motivated the development of 3D CNNs for volumetric image segmentation in order to benefit from more spatial context. Due to GPU memory restrictions caused by moving to fully 3D, state-of-the-art methods depend on subvolume/patch processing and the size of the input patch is usually small, limiting the incorporation of larger context information for a better performance. In this paper, we propose a novel Holistic Decomposition Convolution (HDC), for an effective and efficient semantic segmentation of volumetric images. HDC consists of a periodic down-shuffling operation followed by a conventional 3D convolution. HDC has the advantage of significantly reducing the size of the data for sub-sequential processing while using all the information available in the input irrespective of the down-shuffling factors. Results obtained from comprehensive experiments conducted on hip T1 MR images and intervertebral disc T2 MR images demonstrate the efficacy of the present approach.

arXiv:1812.09584공식 코드 · Papers with Code

Meta Architecture Search

Neural Architecture Search (NAS) has been quite successful in constructing state-of-the-art models on a variety of tasks. Unfortunately, the computational cost can make it difficult to scale. In this paper, we make the first attempt to study Meta Architecture Search which aims at learning a task-agnostic representation that can be used to speed up the process of architecture search on a large number of tasks. We propose the Bayesian Meta Architecture SEarch (BASE) framework which takes advantage of a Bayesian formulation of the architecture search problem to learn over an entire set of tasks simultaneously. We show that on Imagenet classification, we can find a model that achieves 25.7% top-1 error and 8.1% top-5 error by adapting the architecture in less than an hour from an 8 GPU days pretrained meta-network. By learning a good prior for NAS, our method dramatically decreases the required computation cost while achieving comparable performance to current state-of-the-art methods - even finding competitive models for unseen datasets with very quick adaptation. We believe our framework will open up new possibilities for efficient and massively scalable architecture search research across multiple tasks.

arXiv:1812.08934

ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation

This paper proposes an efficient neural network (NN) architecture design methodology called Chameleon that honors given resource constraints. Instead of developing new building blocks or using computationally-intensive reinforcement learning algorithms, our approach leverages existing efficient network building blocks and focuses on exploiting hardware traits and adapting computation resources to fit target latency and/or energy constraints. We formulate platform-aware NN architecture search in an optimization framework and propose a novel algorithm to search for optimal architectures aided by efficient accuracy and resource (latency and/or energy) predictors. At the core of our algorithm lies an accuracy predictor built atop Gaussian Process with Bayesian optimization for iterative sampling. With a one-time building cost for the predictors, our algorithm produces state-of-the-art model architectures on different platforms under given constraints in just minutes. Our results show that adapting computation resources to building blocks is critical to model performance. Without the addition of any bells and whistles, our models achieve significant accuracy improvements against state-of-the-art hand-crafted and automatically designed architectures. We achieve 73.8% and 75.3% top-1 accuracy on ImageNet at 20ms latency on a mobile CPU and DSP. At reduced latency, our models achieve up to 8.5% (4.8%) and 6.6% (9.3%) absolute top-1 accuracy improvements compared to MobileNetV2 and MnasNet, respectively, on a mobile CPU (DSP), and 2.7% (4.6%) and 5.6% (2.6%) accuracy gains over ResNet-101 and ResNet-152, respectively, on an Nvidia GPU (Intel CPU).

arXiv:1812.08491공식 코드 · Papers with Code

cuPC: CUDA-based Parallel PC Algorithm for Causal Structure Learning on GPU

The main goal in many fields in the empirical sciences is to discover causal relationships among a set of variables from observational data. PC algorithm is one of the promising solutions to learn underlying causal structure by performing a number of conditional independence tests. In this paper, we propose a novel GPU-based parallel algorithm, called cuPC, to execute an order-independent version of PC. The proposed solution has two variants, cuPC-E and cuPC-S, which parallelize PC in two different ways for multivariate normal distribution. Experimental results show the scalability of the proposed algorithms with respect to the number of variables, the number of samples, and different graph densities. For instance, in one of the most challenging datasets, the runtime is reduced from more than 11 hours to about 4 seconds. On average, cuPC-E and cuPC-S achieve 500 X and 1300 X speedup, respectively, compared to serial implementation on CPU. The source code of cuPC is available online [1].

arXiv:1812.08402공식 코드 · Papers with Code

SFA: Small Faces Attention Face Detector

In recent year, tremendous strides have been made in face detection thanks to deep learning. However, most published face detectors deteriorate dramatically as the faces become smaller. In this paper, we present the Small Faces Attention (SFA) face detector to better detect faces with small scale. First, we propose a new scale-invariant face detection architecture which pays more attention to small faces, including 4-branch detection architecture and small faces sensitive anchor design. Second, feature maps fusion strategy is applied in SFA by partially combining high-level features into low-level features to further improve the ability of finding hard faces. Third, we use multi-scale training and testing strategy to enhance face detection performance in practice. Comprehensive experiments show that SFA significantly improves face detection performance, especially on small faces. Our real-time SFA face detector can run at 5 FPS on a single GPU as well as maintain high performance. Besides, our final SFA face detector achieves state-of-the-art detection performance on challenging face detection benchmarks, including WIDER FACE and FDDB datasets, with competitive runtime speed. Both our code and models will be available to the research community.

arXiv:1812.08295

Efficient logic architecture in training gradient boosting decision tree for high-performance and edge computing

This study proposes a logic architecture for the high-speed and power efficiently training of a gradient boosting decision tree model of binary classification. We implemented the proposed logic architecture on an FPGA and compared training time and power efficiency with three general GBDT software libraries using CPU and GPU. The training speed of the logic architecture on the FPGA was 26-259 times faster than the software libraries. The power efficiency of the logic architecture was 90-1,104 times higher than the software libraries. The results show that the logic architecture suits for high-performance and edge computing.

arXiv:1812.07816

Fast and Accurate 3D Medical Image Segmentation with Data-swapping Method

Deep neural network models used for medical image segmentation are large because they are trained with high-resolution three-dimensional (3D) images. Graphics processing units (GPUs) are widely used to accelerate the trainings. However, the memory on a GPU is not large enough to train the models. A popular approach to tackling this problem is patch-based method, which divides a large image into small patches and trains the models with these small patches. However, this method would degrade the segmentation quality if a target object spans multiple patches. In this paper, we propose a novel approach for 3D medical image segmentation that utilizes the data-swapping, which swaps out intermediate data from GPU memory to CPU memory to enlarge the effective GPU memory size, for training high-resolution 3D medical images without patching. We carefully tuned parameters in the data-swapping method to obtain the best training performance for 3D U-Net, a widely used deep neural network model for medical image segmentation. We applied our tuning to train 3D U-Net with full-size images of 192 x 192 x 192 voxels in brain tumor dataset. As a result, communication overhead, which is the most important issue, was reduced by 17.1%. Compared with the patch-based method for patches of 128 x 128 x 128 voxels, our training for full-size images achieved improvement on the mean Dice score by 4.48% and 5.32 % for detecting whole tumor sub-region and tumor core sub-region, respectively. The total training time was reduced from 164 hours to 47 hours, resulting in 3.53 times of acceleration.

arXiv:1812.06765

Fully-deformable 3D image registration in two seconds

We present a highly parallel method for accurate and efficient variational deformable 3D image registration on a consumer-grade graphics processing unit (GPU). We build on recent matrix-free variational approaches and specialize the concepts to the massively-parallel manycore architecture provided by the GPU. Compared to a parallel and optimized CPU implementation, this allows us to achieve an average speedup of 32.53 on 986 real-world CT thorax-abdomen follow-up scans. At a resolution of approximately $256^3$ voxels, the average runtime is 1.99 seconds for the full registration. On the publicly available DIR-lab benchmark, our method ranks third with respect to average landmark error at an average runtime of 0.32 seconds.

arXiv:1812.06371공식 코드 · Papers with Code

Trust Region Based Adversarial Attack on Neural Networks

Deep Neural Networks are quite vulnerable to adversarial perturbations. Current state-of-the-art adversarial attack methods typically require very time consuming hyper-parameter tuning, or require many iterations to solve an optimization based adversarial attack. To address this problem, we present a new family of trust region based adversarial attacks, with the goal of computing adversarial perturbations efficiently. We propose several attacks based on variants of the trust region optimization method. We test the proposed methods on Cifar-10 and ImageNet datasets using several different models including AlexNet, ResNet-50, VGG-16, and DenseNet-121 models. Our methods achieve comparable results with the Carlini-Wagner (CW) attack, but with significant speed up of up to $37\times$, for the VGG-16 model on a Titan Xp GPU. For the case of ResNet-50 on ImageNet, we can bring down its classification accuracy to less than 0.1\% with at most $1.5\%$ relative $L_\infty$ (or $L_2$) perturbation requiring only $1.02$ seconds as compared to $27.04$ seconds for the CW attack. We have open sourced our method which can be accessed at [1].