PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1811.10649

Noisy Computations during Inference: Harmful or Helpful?

We study two aspects of noisy computations during inference. The first aspect is how to mitigate their side effects for naturally trained deep learning systems. One of the motivations for looking into this problem is to reduce the high power cost of conventional computing of neural networks through the use of analog neuromorphic circuits. Traditional GPU/CPU-centered deep learning architectures exhibit bottlenecks in power-restricted applications (e.g., embedded systems). The use of specialized neuromorphic circuits, where analog signals passed through memory-cell arrays are sensed to accomplish matrix-vector multiplications, promises large power savings and speed gains but brings with it the problems of limited precision of computations and unavoidable analog noise. We manage to improve inference accuracy from 21.1% to 99.5% for MNIST images, from 29.9% to 89.1% for CIFAR10, and from 15.5% to 89.6% for MNIST stroke sequences with the presence of strong noise (with signal-to-noise power ratio being 0 dB) by noise-injected training and a voting method. This observation promises neural networks that are insensitive to inference noise, which reduces the quality requirements on neuromorphic circuits and is crucial for their practical usage. The second aspect is how to utilize the noisy inference as a defensive architecture against black-box adversarial attacks. During inference, by injecting proper noise to signals in the neural networks, the robustness of adversarially-trained neural networks against black-box attacks has been further enhanced by 0.5% and 1.13% for two adversarially trained models for MNIST and CIFAR10, respectively.

arXiv:1811.09998

Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation

Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve higher speed and lower memory at the cost of minimal performance drop. Inspired by that, this paper proposes a learning approach to recognize low-resolution faces via selective knowledge distillation. In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively. The teacher stream is represented by a complex CNN for high-accuracy recognition, and the student stream is represented by a much simpler CNN for low-complexity recognition. To avoid significant performance drop at the student stream, we then selectively distil the most informative facial features from the teacher stream by solving a sparse graph optimization problem, which are then used to regularize the fine-tuning process of the student stream. In this way, the student stream is actually trained by simultaneously handling two tasks with limited computational resources: approximating the most informative facial cues via feature regression, and recovering the missing facial cues via low-resolution face classification. Experimental results show that the student stream performs impressively in recognizing low-resolution faces and costs only 0.15MB memory and runs at 418 faces per second on CPU and 9,433 faces per second on GPU.

arXiv:1811.08588

Real-Time 6D Object Pose Estimation on CPU

We propose a fast and accurate 6D object pose estimation from a RGB-D image. Our proposed method is template matching based and consists of three main technical components, PCOF-MOD (multimodal PCOF), balanced pose tree (BPT) and optimum memory rearrangement for a coarse-to-fine search. Our model templates on densely sampled viewpoints and PCOF-MOD which explicitly handles a certain range of 3D object pose improve the robustness against background clutters. BPT which is an efficient tree-based data structures for a large number of templates and template matching on rearranged feature maps where nearby features are linearly aligned accelerate the pose estimation. The experimental evaluation on tabletop and bin-picking dataset showed that our method achieved higher accuracy and faster speed in comparison with state-of-the-art techniques including recent CNN based approaches. Moreover, our model templates can be trained only from 3D CAD in a few minutes and the pose estimation run in near real-time (23 fps) on CPU. These features are suitable for any real applications.

arXiv:1811.07315

Learning to infer: RL-based search for DNN primitive selection on Heterogeneous Embedded Systems

Deep Learning is increasingly being adopted by industry for computer vision applications running on embedded devices. While Convolutional Neural Networks' accuracy has achieved a mature and remarkable state, inference latency and throughput are a major concern especially when targeting low-cost and low-power embedded platforms. CNNs' inference latency may become a bottleneck for Deep Learning adoption by industry, as it is a crucial specification for many real-time processes. Furthermore, deployment of CNNs across heterogeneous platforms presents major compatibility issues due to vendor-specific technology and acceleration libraries. In this work, we present QS-DNN, a fully automatic search based on Reinforcement Learning which, combined with an inference engine optimizer, efficiently explores through the design space and empirically finds the optimal combinations of libraries and primitives to speed up the inference of CNNs on heterogeneous embedded devices. We show that, an optimized combination can achieve 45x speedup in inference latency on CPU compared to a dependency-free baseline and 2x on average on GPGPU compared to the best vendor library. Further, we demonstrate that, the quality of results and time "to-solution" is much better than with Random Search and achieves up to 15x better results for a short-time search.

arXiv:1811.07184공식 코드 · Papers with Code

Stacking-Based Deep Neural Network: Deep Analytic Network for Pattern Classification

Stacking-based deep neural network (S-DNN) is aggregated with pluralities of basic learning modules, one after another, to synthesize a deep neural network (DNN) alternative for pattern classification. Contrary to the DNNs trained end to end by backpropagation (BP), each S-DNN layer, i.e., a self-learnable module, is to be trained decisively and independently without BP intervention. In this paper, a ridge regression-based S-DNN, dubbed deep analytic network (DAN), along with its kernelization (K-DAN), are devised for multilayer feature re-learning from the pre-extracted baseline features and the structured features. Our theoretical formulation demonstrates that DAN/K-DAN re-learn by perturbing the intra/inter-class variations, apart from diminishing the prediction errors. We scrutinize the DAN/K-DAN performance for pattern classification on datasets of varying domains - faces, handwritten digits, generic objects, to name a few. Unlike the typical BP-optimized DNNs to be trained from gigantic datasets by GPU, we disclose that DAN/K-DAN are trainable using only CPU even for small-scale training sets. Our experimental results disclose that DAN/K-DAN outperform the present S-DNNs and also the BP-trained DNNs, including multiplayer perceptron, deep belief network, etc., without data augmentation applied.

arXiv:1811.05894

Development of Real-time ADAS Object Detector for Deployment on CPU

In this work, we outline the set of problems, which any Object Detection CNN faces when its development comes to the deployment stage and propose methods to deal with such difficulties. We show that these practices allow one to get Object Detection network, which can recognize two classes: vehicles and pedestrians and achieves more than 60 frames per second inference speed on Core$^{TM}$ i5-6500 CPU. The proposed model is built on top of the popular Single Shot MultiBox Object Detection framework but with substantial improvements, which were inspired by the discovered problems. The network has just 1.96 GMAC complexity and less than 7 MB model size. It is publicly available as a part of Intel$\circledR$ OpenVINO$^{TM}$ Toolkit.

arXiv:1811.04624

Importance Weighted Evolution Strategies

Evolution Strategies (ES) emerged as a scalable alternative to popular Reinforcement Learning (RL) techniques, providing an almost perfect speedup when distributed across hundreds of CPU cores thanks to a reduced communication overhead. Despite providing large improvements in wall-clock time, ES is data inefficient when compared to competing RL methods. One of the main causes of such inefficiency is the collection of large batches of experience, which are discarded after each policy update. In this work, we study how to perform more than one update per batch of experience by means of Importance Sampling while preserving the scalability of the original method. The proposed method, Importance Weighted Evolution Strategies (IW-ES), shows promising results and is a first step towards designing efficient ES algorithms.

arXiv:1811.04047

A Microprocessor implemented in 65nm CMOS with Configurable and Bit-scalable Accelerator for Programmable In-memory Computing

This paper presents a programmable in-memory-computing processor, demonstrated in a 65nm CMOS technology. For data-centric workloads, such as deep neural networks, data movement often dominates when implemented with today's computing architectures. This has motivated spatial architectures, where the arrangement of data-storage and compute hardware is distributed and explicitly aligned to the computation dataflow, most notably for matrix-vector multiplication. In-memory computing is a spatial architecture where processing elements correspond to dense bit cells, providing local storage and compute, typically employing analog operation. Though this raises the potential for high energy efficiency and throughput, analog operation has significantly limited robustness, scale, and programmability. This paper describes a 590kb in-memory-computing accelerator integrated in a programmable processor architecture, by exploiting recent approaches to charge-domain in-memory computing. The architecture takes the approach of tight coupling with an embedded CPU, through accelerator interfaces enabling integration in the standard processor memory space. Additionally, a near-memory-computing datapath both enables diverse computations locally, to address operations required across applications, and enables bit-precision scalability for matrix/input-vector elements, through a bit-parallel/bit-serial (BP/BS) scheme. Chip measurements show an energy efficiency of 152/297 1b-TOPS/W and throughput of 4.7/1.9 1b-TOPS (scaling linearly with the matrix/input-vector element precisions) at VDD of 1.2/0.85V. Neural network demonstrations with 1-b/4-b weights and activations for CIFAR-10 classification consume 5.3/105.2 $\mu$J/image at 176/23 fps, with accuracy at the level of digital/software implementation (89.3/92.4 $\%$ accuracy).

arXiv:1808.10678

Self-Attention Linguistic-Acoustic Decoder

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of such models (in terms of low distortion in the generated speech), their recursive structure tends to make them slow to train and to sample from. In this work, we try to overcome the limitations of recursive structure by using a module based on the transformer decoder network, designed without recurrent connections but emulating them with attention and positioning codes. Our results show that the proposed decoder network is competitive in terms of distortion when compared to a recurrent baseline, whilst being significantly faster in terms of CPU inference time. On average, it increases Mel cepstral distortion between 0.1 and 0.3 dB, but it is over an order of magnitude faster on average. Fast inference is important for the deployment of speech synthesis systems on devices with restricted resources, like mobile phones or embedded systems, where speaking virtual assistants are gaining importance.

arXiv:1811.01564

Parallel training of linear models without compromising convergence

In this paper we analyze, evaluate, and improve the performance of training generalized linear models on modern CPUs. We start with a state-of-the-art asynchronous parallel training algorithm, identify system-level performance bottlenecks, and apply optimizations that improve data parallelism, cache line locality, and cache line prefetching of the algorithm. These modifications reduce the per-epoch run-time significantly, but take a toll on algorithm convergence in terms of the required number of epochs. To alleviate these shortcomings of our systems-optimized version, we propose a novel, dynamic data partitioning scheme across threads which allows us to approach the convergence of the sequential version. The combined set of optimizations result in a consistent bottom line speedup in convergence of up to 12x compared to the initial asynchronous parallel training algorithm and up to 42x, compared to state of the art implementations (scikit-learn and h2o) on a range of multi-core CPU architectures.

arXiv:1810.12514공식 코드 · Papers with Code

DeepGRU: Deep Gesture Recognition Utility

We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic. DeepGRU, which uses only raw skeleton, pose or vector data is quickly understood, implemented, and trained, and yet achieves state-of-the-art results on challenging datasets. At the heart of our method lies a set of stacked gated recurrent units (GRU), two fully-connected layers and a novel global attention model. We evaluate our method on seven publicly available datasets, containing various number of samples and spanning over a broad range of interactions (full-body, multi-actor, hand gestures, etc.). In all but one case we outperform the state-of-the-art pose-based methods. For instance, we achieve a recognition accuracy of 84.9% and 92.3% on cross-subject and cross-view tests of the NTU RGB+D dataset respectively, and also 100% recognition accuracy on the UT-Kinect dataset. While DeepGRU works well on large datasets with many training samples, we show that even in the absence of a large number of training data, and with as little as four samples per class, DeepGRU can beat traditional methods specifically designed for small training sets. Lastly, we demonstrate that even without powerful hardware, and using only the CPU, our method can still be trained in under 10 minutes on small-scale datasets, making it an enticing choice for rapid application prototyping and development.

arXiv:1810.12210공식 코드 · Papers with Code

A Comparative Measurement Study of Deep Learning as a Service Framework

Big data powered Deep Learning (DL) and its applications have blossomed in recent years, fueled by three technological trends: a large amount of digitized data openly accessible, a growing number of DL software frameworks in open source and commercial markets, and a selection of affordable parallel computing hardware devices. However, no single DL framework, to date, dominates in terms of performance and accuracy even for baseline classification tasks on standard datasets, making the selection of a DL framework an overwhelming task. This paper takes a holistic approach to conduct empirical comparison and analysis of four representative DL frameworks with three unique contributions. First, given a selection of CPU-GPU configurations, we show that for a specific DL framework, different configurations of its hyper-parameters may have a significant impact on both performance and accuracy of DL applications. Second, to the best of our knowledge, this study is the first to identify the opportunities for improving the training time performance and the accuracy of DL frameworks by configuring parallel computing libraries and tuning individual and multiple hyper-parameters. Third, we also conduct a comparative measurement study on the resource consumption patterns of four DL frameworks and their performance and accuracy implications, including CPU and memory usage, and their correlations to varying settings of hyper-parameters under different configuration combinations of hardware, parallel computing libraries. We argue that this measurement study provides in-depth empirical comparison and analysis of four representative DL frameworks, and offers practical guidance for service providers to deploying and delivering DL as a Service (DLaaS) and for application developers and DLaaS consumers to select the right DL frameworks for the right DL workloads.

arXiv:1810.11363공식 코드 · Papers with Code

CatBoost: gradient boosting with categorical features support

In this paper we present CatBoost, a new open-sourced gradient boosting library that successfully handles categorical features and outperforms existing publicly available implementations of gradient boosting in terms of quality on a set of popular publicly available datasets. The library has a GPU implementation of learning algorithm and a CPU implementation of scoring algorithm, which are significantly faster than other gradient boosting libraries on ensembles of similar sizes.

arXiv:1810.11359공식 코드 · Papers with Code

gpuRIR: A python library for Room Impulse Response simulation with GPU acceleration

The Image Source Method (ISM) is one of the most employed techniques to calculate acoustic Room Impulse Responses (RIRs), however, its computational complexity grows fast with the reverberation time of the room and its computation time can be prohibitive for some applications where a huge number of RIRs are needed. In this paper, we present a new implementation that dramatically improves the computation speed of the ISM by using Graphic Processing Units (GPUs) to parallelize both the simulation of multiple RIRs and the computation of the images inside each RIR. We provide a Python library under GNU license that can be easily used without any knowledge about GPU programming and we show that it is about 100 times faster than other state of the art CPU libraries.

arXiv:1810.11066

Automating Generation of Low Precision Deep Learning Operators

State of the art deep learning models have made steady progress in the fields of computer vision and natural language processing, at the expense of growing model sizes and computational complexity. Deploying these models on low power and mobile devices poses a challenge due to their limited compute capabilities and strict energy budgets. One solution that has generated significant research interest is deploying highly quantized models that operate on low precision inputs and weights less than eight bits, trading off accuracy for performance. These models have a significantly reduced memory footprint (up to 32x reduction) and can replace multiply-accumulates with bitwise operations during compute intensive convolution and fully connected layers. Most deep learning frameworks rely on highly engineered linear algebra libraries such as ATLAS or Intel's MKL to implement efficient deep learning operators. To date, none of the popular deep learning directly support low precision operators, partly due to a lack of optimized low precision libraries. In this paper we introduce a work flow to quickly generate high performance low precision deep learning operators for arbitrary precision that target multiple CPU architectures and include optimizations such as memory tiling and vectorization. We present an extensive case study on low power ARM Cortex-A53 CPU, and show how we can generate 1-bit, 2-bit convolutions with speedups up to 16x over an optimized 16-bit integer baseline and 2.3x better than handwritten implementations.

arXiv:1810.10110

Resource-Constrained Simultaneous Detection and Labeling of Objects in High-Resolution Satellite Images

We describe a strategy for detection and classification of man-made objects in large high-resolution satellite photos under computational resource constraints. We detect and classify candidate objects by using five pipelines of convolutional neural network processing (CNN), run in parallel. Each pipeline has its own unique strategy for fine tunning parameters, proposal region filtering, and dealing with image scales. The conflicting region proposals are merged based on region confidence and not just based on overlap areas, which improves the quality of the final bounding-box regions selected. We demonstrate this strategy using the recent xView challenge, which is a complex benchmark with more than 1,100 high-resolution images, spanning 800,000 aerial objects around the world covering a total area of 1,400 square kilometers at 0.3 meter ground sample distance. To tackle the resource-constrained problem posed by the xView challenge, where inferences are restricted to be on CPU with 8GB memory limit, we used lightweight CNN's trained with the single shot detector algorithm. Our approach was competitive on sequestered sets; it was ranked third.

arXiv:1810.09868

Automatic Full Compilation of Julia Programs and ML Models to Cloud TPUs

Google's Cloud TPUs are a promising new hardware architecture for machine learning workloads. They have powered many of Google's milestone machine learning achievements in recent years. Google has now made TPUs available for general use on their cloud platform and as of very recently has opened them up further to allow use by non-TensorFlow frontends. We describe a method and implementation for offloading suitable sections of Julia programs to TPUs via this new API and the Google XLA compiler. Our method is able to completely fuse the forward pass of a VGG19 model expressed as a Julia program into a single TPU executable to be offloaded to the device. Our method composes well with existing compiler-based automatic differentiation techniques on Julia code, and we are thus able to also automatically obtain the VGG19 backwards pass and similarly offload it to the TPU. Targeting TPUs using our compiler, we are able to evaluate the VGG19 forward pass on a batch of 100 images in 0.23s which compares favorably to the 52.4s required for the original model on the CPU. Our implementation is less than 1000 lines of Julia, with no TPU specific changes made to the core Julia compiler or any other Julia packages.

arXiv:1810.09309

Real-time Neural-based Input Method

The input method is an essential service on every mobile and desktop devices that provides text suggestions. It converts sequential keyboard inputs to the characters in its target language, which is indispensable for Japanese and Chinese users. Due to critical resource constraints and limited network bandwidth of the target devices, applying neural models to input method is not well explored. In this work, we apply a LSTM-based language model to input method and evaluate its performance for both prediction and conversion tasks with Japanese BCCWJ corpus. We articulate the bottleneck to be the slow softmax computation during conversion. To solve the issue, we propose incremental softmax approximation approach, which computes softmax with a selected subset vocabulary and fix the stale probabilities when the vocabulary is updated in future steps. We refer to this method as incremental selective softmax. The results show a two order speedup for the softmax computation when converting Japanese input sequences with a large vocabulary, reaching real-time speed on commodity CPU. We also exploit the model compressing potential to achieve a 92% model size reduction without losing accuracy.

arXiv:1810.08869공식 코드 · Papers with Code

Learning-based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems

The rising use of deep learning and other big-data algorithms has led to an increasing demand for hardware platforms that are computationally powerful, yet energy-efficient. Due to the amount of data parallelism in these algorithms, high-performance 3D manycore platforms that incorporate both CPUs and GPUs present a promising direction. However, as systems use heterogeneity (e.g., a combination of CPUs, GPUs, and accelerators) to improve performance and efficiency, it becomes more pertinent to address the distinct and likely conflicting communication requirements (e.g., CPU memory access latency or GPU network throughput) that arise from such heterogeneity. Unfortunately, it is difficult to quickly explore the hardware design space and choose appropriate tradeoffs between these heterogeneous requirements. To address these challenges, we propose the design of a 3D Network-on-Chip (NoC) for heterogeneous manycore platforms that considers the appropriate design objectives for a 3D heterogeneous system and explores various tradeoffs using an efficient ML-based multi-objective optimization technique. The proposed design space exploration considers the various requirements of its heterogeneous components and generates a set of 3D NoC architectures that efficiently trades off these design objectives. Our findings show that by jointly considering these requirements (latency, throughput, temperature, and energy), we can achieve 9.6% better Energy-Delay Product on average at nearly iso-temperature conditions when compared to a thermally-optimized design for 3D heterogeneous NoCs. More importantly, our results suggest that our 3D NoCs optimized for a few applications can be generalized for unknown applications as well. Our results show that these generalized 3D NoCs only incur a 1.8% (36-tile system) and 1.1% (64-tile system) average performance loss compared to application-specific NoCs.

arXiv:1810.08723공식 코드 · Papers with Code

The Ocean Tensor Package

Matrix and tensor operations form the basis of a wide range of fields and applications, and in many cases constitute a substantial part of the overall computational complexity. The ability of general-purpose GPUs to speed up many of these operations and enable others has resulted in a widespread adaptation of these devices. In order for tensor operations to take full advantage of the computational power, specialized software is required, and currently there exist several packages (predominantly in the area of deep learning) that incorporate tensor operations on both CPU and GPU. Nevertheless, a stand-alone framework that supports general tensor operations is still missing. In this paper we fill this gap and propose the Ocean Tensor Library: a modular tensor-support package that is designed to serve as a foundational layer for applications that require dense tensor operations on a variety of device types. The API is carefully designed to be powerful, extensible, and at the same time easy to use. The package is available as open source.