PyTorchKR Papers

최신 논문

총 2,153편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2105.15168공식 코드 · Papers with Code

MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens

Transformers have offered a new methodology of designing neural networks for visual recognition. Compared to convolutional networks, Transformers enjoy the ability of referring to global features at each stage, yet the attention module brings higher computational overhead that obstructs the application of Transformers to process high-resolution visual data. This paper aims to alleviate the conflict between efficiency and flexibility, for which we propose a specialized token for each region that serves as a messenger (MSG). Hence, by manipulating these MSG tokens, one can flexibly exchange visual information across regions and the computational complexity is reduced. We then integrate the MSG token into a multi-scale architecture named MSG-Transformer. In standard image classification and object detection, MSG-Transformer achieves competitive performance and the inference on both GPU and CPU is accelerated. Code is available at https://github.com/hustvl/MSG-Transformer.

arXiv:2105.14713공식 코드 · Papers with Code

1xN Pattern for Pruning Convolutional Neural Networks

Though network pruning receives popularity in reducing the complexity of convolutional neural networks (CNNs), it remains an open issue to concurrently maintain model accuracy as well as achieve significant speedups on general CPUs. In this paper, we propose a novel 1xN pruning pattern to break this limitation. In particular, consecutive N output kernels with the same input channel index are grouped into one block, which serves as a basic pruning granularity of our pruning pattern. Our 1xN pattern prunes these blocks considered unimportant. We also provide a workflow of filter rearrangement that first rearranges the weight matrix in the output channel dimension to derive more influential blocks for accuracy improvements and then applies similar rearrangement to the next-layer weights in the input channel dimension to ensure correct convolutional operations. Moreover, the output computation after our 1xN pruning can be realized via a parallelized block-wise vectorized operation, leading to significant speedups on general CPUs. The efficacy of our pruning pattern is proved with experiments on ILSVRC-2012. For example, given the pruning rate of 50% and N=4, our pattern obtains about 3.0% improvements over filter pruning in the top-1 accuracy of MobileNet-V2. Meanwhile, it obtains 56.04ms inference savings on Cortex-A7 CPU over weight pruning. Our project is made available at https://github.com/lmbxmu/1xN.

arXiv:2105.13904

An In-Memory Analog Computing Co-Processor for Energy-Efficient CNN Inference on Mobile Devices

In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays. Spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) devices are leveraged to realize sigmoidal neurons as well as binarized synapses. First, it is shown the proposed IMAC architecture can be utilized to realize a multilayer perceptron (MLP) classifier achieving orders of magnitude performance improvement compared to previous mixed-signal and digital implementations. Next, a heterogeneous mixed-signal and mixed-precision CPU-IMAC architecture is proposed for convolutional neural networks (CNNs) inference on mobile processors, in which IMAC is designed as a co-processor to realize fully-connected (FC) layers whereas convolution layers are executed in CPU. Architecture-level analytical models are developed to evaluate the performance and energy consumption of the CPU-IMAC architecture. Simulation results exhibit 6.5% and 10% energy savings for CPU-IMAC based realizations of LeNet and VGG CNN models, for MNIST and CIFAR-10 pattern recognition tasks, respectively.

arXiv:2105.12676

Low-Precision Hardware Architectures Meet Recommendation Model Inference at Scale

Tremendous success of machine learning (ML) and the unabated growth in ML model complexity motivated many ML-specific designs in both CPU and accelerator architectures to speed up the model inference. While these architectures are diverse, highly optimized low-precision arithmetic is a component shared by most. Impressive compute throughputs are indeed often exhibited by these architectures on benchmark ML models. Nevertheless, production models such as recommendation systems important to Facebook's personalization services are demanding and complex: These systems must serve billions of users per month responsively with low latency while maintaining high prediction accuracy, notwithstanding computations with many tens of billions parameters per inference. Do these low-precision architectures work well with our production recommendation systems? They do. But not without significant effort. We share in this paper our search strategies to adapt reference recommendation models to low-precision hardware, our optimization of low-precision compute kernels, and the design and development of tool chain so as to maintain our models' accuracy throughout their lifespan during which topic trends and users' interests inevitably evolve. Practicing these low-precision technologies helped us save datacenter capacities while deploying models with up to 5X complexity that would otherwise not be deployed on traditional general-purpose CPUs. We believe these lessons from the trenches promote better co-design between hardware architecture and software engineering and advance the state of the art of ML in industry.

arXiv:2105.12026

Providing Meaningful Data Summarizations Using Exemplar-based Clustering in Industry 4.0

Data summarizations are a valuable tool to derive knowledge from large data streams and have proven their usefulness in a great number of applications. Summaries can be found by optimizing submodular functions. These functions map subsets of data to real values, which indicate their "representativeness" and which should be maximized to find a diverse summary of the underlying data. In this paper, we studied Exemplar-based clustering as a submodular function and provide a GPU algorithm to cope with its high computational complexity. We show, that our GPU implementation provides speedups of up to 72x using single-precision and up to 452x using half-precision computation compared to conventional CPU algorithms. We also show, that the GPU algorithm not only provides remarkable runtime benefits with workstation-grade GPUs but also with low-power embedded computation units for which speedups of up to 35x are possible. Furthermore, we apply our algorithm to real-world data from injection molding manufacturing processes and discuss how found summaries help with steering this specific process to cut costs and reduce the manufacturing of bad parts. Beyond pure speedup considerations, we show, that our approach can provide summaries within reasonable time frames for this kind of industrial, real-world data.

arXiv:2105.11118공식 코드 · Papers with Code

Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads

A graph neural network (GNN) enables deep learning on structured graph data. There are two major GNN training obstacles: 1) it relies on high-end servers with many GPUs which are expensive to purchase and maintain, and 2) limited memory on GPUs cannot scale to today's billion-edge graphs. This paper presents Dorylus: a distributed system for training GNNs. Uniquely, Dorylus can take advantage of serverless computing to increase scalability at a low cost. The key insight guiding our design is computation separation. Computation separation makes it possible to construct a deep, bounded-asynchronous pipeline where graph and tensor parallel tasks can fully overlap, effectively hiding the network latency incurred by Lambdas. With the help of thousands of Lambda threads, Dorylus scales GNN training to billion-edge graphs. Currently, for large graphs, CPU servers offer the best performance-per-dollar over GPU servers. Just using Lambdas on top of CPU servers offers up to 2.75x more performance-per-dollar than training only with CPU servers. Concretely, Dorylus is 1.22x faster and 4.83x cheaper than GPU servers for massive sparse graphs. Dorylus is up to 3.8x faster and 10.7x cheaper compared to existing sampling-based systems.

arXiv:2105.10554

GNNIE: GNN Inference Engine with Load-balancing and Graph-Specific Caching

Graph neural networks (GNN) analysis engines are vital for real-world problems that use large graph models. Challenges for a GNN hardware platform include the ability to (a) host a variety of GNNs, (b) handle high sparsity in input vertex feature vectors and the graph adjacency matrix and the accompanying random memory access patterns, and (c) maintain load-balanced computation in the face of uneven workloads, induced by high sparsity and power-law vertex degree distributions. This paper proposes GNNIE, an accelerator designed to run a broad range of GNNs. It tackles workload imbalance by (i)~splitting vertex feature operands into blocks, (ii)~reordering and redistributing computations, (iii)~using a novel flexible MAC architecture. It adopts a graph-specific, degree-aware caching policy that is well suited to real-world graph characteristics. The policy enhances on-chip data reuse and avoids random memory access to DRAM. GNNIE achieves average speedups of 21233x over a CPU and 699x over a GPU over multiple datasets on graph attention networks (GATs), graph convolutional networks (GCNs), GraphSAGE, GINConv, and DiffPool. Compared to prior approaches, GNNIE achieves an average speedup of 35x over HyGCN (which cannot implement GATs) for GCN, GraphSAGE, and GINConv, and, using 3.4x fewer processing units, an average speedup of 2.1x over AWB-GCN (which runs only GCNs).

arXiv:2105.10154공식 코드 · Papers with Code

ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search

Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-time efficiency. To achieve a better trade-off between accuracy and efficiency, we propose a novel neural architecture search (NAS) method, termed ViPNAS, to search networks in both spatial and temporal levels for fast online video pose estimation. In the spatial level, we carefully design the search space with five different dimensions including network depth, width, kernel size, group number, and attentions. In the temporal level, we search from a series of temporal feature fusions to optimize the total accuracy and speed across multiple video frames. To the best of our knowledge, we are the first to search for the temporal feature fusion and automatic computation allocation in videos. Extensive experiments demonstrate the effectiveness of our approach on the challenging COCO2017 and PoseTrack2018 datasets. Our discovered model family, S-ViPNAS and T-ViPNAS, achieve significantly higher inference speed (CPU real-time) without sacrificing the accuracy compared to the previous state-of-the-art methods.

arXiv:2105.09858공식 코드 · Papers with Code

Low-Latency Real-Time Non-Parallel Voice Conversion based on Cyclic Variational Autoencoder and Multiband WaveRNN with Data-Driven Linear Prediction

This paper presents a low-latency real-time (LLRT) non-parallel voice conversion (VC) framework based on cyclic variational autoencoder (CycleVAE) and multiband WaveRNN with data-driven linear prediction (MWDLP). CycleVAE is a robust non-parallel multispeaker spectral model, which utilizes a speaker-independent latent space and a speaker-dependent code to generate reconstructed/converted spectral features given the spectral features of an input speaker. On the other hand, MWDLP is an efficient and a high-quality neural vocoder that can handle multispeaker data and generate speech waveform for LLRT applications with CPU. To accommodate LLRT constraint with CPU, we propose a novel CycleVAE framework that utilizes mel-spectrogram as spectral features and is built with a sparse network architecture. Further, to improve the modeling performance, we also propose a novel fine-tuning procedure that refines the frame-rate CycleVAE network by utilizing the waveform loss from the MWDLP network. The experimental results demonstrate that the proposed framework achieves high-performance VC, while allowing for LLRT usage with a single-core of $2.1$--$2.7$ GHz CPU on a real-time factor of $0.87$--$0.95$, including input/output, feature extraction, on a frame shift of $10$ ms, a window length of $27.5$ ms, and $2$ lookup frames.

arXiv:2105.09856공식 코드 · Papers with Code

High-Fidelity and Low-Latency Universal Neural Vocoder based on Multiband WaveRNN with Data-Driven Linear Prediction for Discrete Waveform Modeling

This paper presents a novel high-fidelity and low-latency universal neural vocoder framework based on multiband WaveRNN with data-driven linear prediction for discrete waveform modeling (MWDLP). MWDLP employs a coarse-fine bit WaveRNN architecture for 10-bit mu-law waveform modeling. A sparse gated recurrent unit with a relatively large size of hidden units is utilized, while the multiband modeling is deployed to achieve real-time low-latency usage. A novel technique for data-driven linear prediction (LP) with discrete waveform modeling is proposed, where the LP coefficients are estimated in a data-driven manner. Moreover, a novel loss function using short-time Fourier transform (STFT) for discrete waveform modeling with Gumbel approximation is also proposed. The experimental results demonstrate that the proposed MWDLP framework generates high-fidelity synthetic speech for seen and unseen speakers and/or language on 300 speakers training data including clean and noisy/reverberant conditions, where the number of training utterances is limited to 60 per speaker, while allowing for real-time low-latency processing using a single core of $\sim\!$ 2.1--2.7 GHz CPU with $\sim\!$ 0.57--0.64 real-time factor including input/output and feature extraction.

arXiv:2105.06183

Adaptive Test-Time Augmentation for Low-Power CPU

Convolutional Neural Networks (ConvNets) are trained offline using the few available data and may therefore suffer from substantial accuracy loss when ported on the field, where unseen input patterns received under unpredictable external conditions can mislead the model. Test-Time Augmentation (TTA) techniques aim to alleviate such common side effect at inference-time, first running multiple feed-forward passes on a set of altered versions of the same input sample, and then computing the main outcome through a consensus of the aggregated predictions. Unfortunately, the implementation of TTA on embedded CPUs introduces latency penalties that limit its adoption on edge applications. To tackle this issue, we propose AdapTTA, an adaptive implementation of TTA that controls the number of feed-forward passes dynamically, depending on the complexity of the input. Experimental results on state-of-the-art ConvNets for image classification deployed on a commercial ARM Cortex-A CPU demonstrate AdapTTA reaches remarkable latency savings, from 1.49X to 2.21X, and hence a higher frame rate compared to static TTA, still preserving the same accuracy gain.

arXiv:2105.03949공식 코드 · Papers with Code

High-performance symbolic-numerics via multiple dispatch

As mathematical computing becomes more democratized in high-level languages, high-performance symbolic-numeric systems are necessary for domain scientists and engineers to get the best performance out of their machine without deep knowledge of code optimization. Naturally, users need different term types either to have different algebraic properties for them, or to use efficient data structures. To this end, we developed Symbolics.jl, an extendable symbolic system which uses dynamic multiple dispatch to change behavior depending on the domain needs. In this work we detail an underlying abstract term interface which allows for speed without sacrificing generality. We show that by formalizing a generic API on actions independent of implementation, we can retroactively add optimized data structures to our system without changing the pre-existing term rewriters. We showcase how this can be used to optimize term construction and give a 113x acceleration on general symbolic transformations. Further, we show that such a generic API allows for complementary term-rewriting implementations. We demonstrate the ability to swap between classical term-rewriting simplifiers and e-graph-based term-rewriting simplifiers. We showcase an e-graph ruleset which minimizes the number of CPU cycles during expression evaluation, and demonstrate how it simplifies a real-world reaction-network simulation to halve the runtime. Additionally, we show a reaction-diffusion partial differential equation solver which is able to be automatically converted into symbolic expressions via multiple dispatch tracing, which is subsequently accelerated and parallelized to give a 157x simulation speedup. Together, this presents Symbolics.jl as a next-generation symbolic-numeric computing environment geared towards modeling and simulation.

arXiv:2105.04528공식 코드 · Papers with Code

Accelerating Large Scale Real-Time GNN Inference using Channel Pruning

Graph Neural Networks (GNNs) are proven to be powerful models to generate node embedding for downstream applications. However, due to the high computation complexity of GNN inference, it is hard to deploy GNNs for large-scale or real-time applications. In this paper, we propose to accelerate GNN inference by pruning the dimensions in each layer with negligible accuracy loss. Our pruning framework uses a novel LASSO regression formulation for GNNs to identify feature dimensions (channels) that have high influence on the output activation. We identify two inference scenarios and design pruning schemes based on their computation and memory usage for each. To further reduce the inference complexity, we effectively store and reuse hidden features of visited nodes, which significantly reduces the number of supporting nodes needed to compute the target embedding. We evaluate the proposed method with the node classification problem on five popular datasets and a real-time spam detection application. We demonstrate that the pruned GNN models greatly reduce computation and memory usage with little accuracy loss. For full inference, the proposed method achieves an average of 3.27x speedup with only 0.002 drop in F1-Micro on GPU. For batched inference, the proposed method achieves an average of 6.67x speedup with only 0.003 drop in F1-Micro on CPU. To the best of our knowledge, we are the first to accelerate large scale real-time GNN inference through channel pruning.

arXiv:2105.03600

Incremental Training and Group Convolution Pruning for Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different and dynamic workloads concurrently, it is challenging to consistently meet inference time/energy budget at runtime because of the local computing resources available to the DNNs vary considerably. To address this challenge, a variety of dynamic DNNs were proposed. However, these works have significant memory overhead, limited runtime recoverable compression rate and narrow dynamic ranges of performance scaling. In this paper, we present a dynamic DNN using incremental training and group convolution pruning. The channels of the DNN convolution layer are divided into groups, which are then trained incrementally. At runtime, following groups can be pruned for inference time/energy reduction or added back for accuracy recovery without model retraining. In addition, we combine task mapping and Dynamic Voltage Frequency Scaling (DVFS) with our dynamic DNN to deliver finer trade-off between accuracy and time/power/energy over a wider dynamic range. We illustrate the approach by modifying AlexNet for the CIFAR10 image dataset and evaluate our work on two heterogeneous hardware platforms: Odroid XU3 (ARM big.LITTLE CPUs) and Nvidia Jetson Nano (CPU and GPU). Compared to the existing works, our approach can provide up to 2.36x (energy) and 2.73x (time) wider dynamic range with a 2.4x smaller memory footprint at the same compression rate. It achieved 10.6x (energy) and 41.6x (time) wider dynamic range by combining with task mapping and DVFS.

arXiv:2105.03596

Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms

Mobile and embedded platforms are increasingly required to efficiently execute computationally demanding DNNs across heterogeneous processing elements. At runtime, the available hardware resources to DNNs can vary considerably due to other concurrently running applications. The performance requirements of the applications could also change under different scenarios. To achieve the desired performance, dynamic DNNs have been proposed in which the number of channels/layers can be scaled in real time to meet different requirements under varying resource constraints. However, the training process of such dynamic DNNs can be costly, since platform-aware models of different deployment scenarios must be retrained to become dynamic. This paper proposes Dynamic-OFA, a novel dynamic DNN approach for state-of-the-art platform-aware NAS models (i.e. Once-for-all network (OFA)). Dynamic-OFA pre-samples a family of sub-networks from a static OFA backbone model, and contains a runtime manager to choose different sub-networks under different runtime environments. As such, Dynamic-OFA does not need the traditional dynamic DNN training pipeline. Compared to the state-of-the-art, our experimental results using ImageNet on a Jetson Xavier NX show that the approach is up to 3.5x (CPU), 2.4x (GPU) faster for similar ImageNet Top-1 accuracy, or 3.8% (CPU), 5.1% (GPU) higher accuracy at similar latency.

arXiv:2105.03332

Finite volume method network for acceleration of unsteady computational fluid dynamics: non-reacting and reacting flows

Despite rapid improvements in the performance of central processing unit (CPU), the calculation cost of simulating chemically reacting flow using CFD remains infeasible in many cases. The application of the convolutional neural networks (CNNs) specialized in image processing in flow field prediction has been studied, but the need to develop a neural netweork design fitted for CFD is recently emerged. In this study, a neural network model introducing the finite volume method (FVM) with a unique network architecture and physics-informed loss function was developed to accelerate CFD simulations. The developed network model, considering the nature of the CFD flow field where the identical governing equations are applied to all grids, can predict the future fields with only two previous fields unlike the CNNs requiring many field images (>10,000). The performance of this baseline model was evaluated using CFD time series data from non-reacting flow and reacting flow simulation; counterflow and hydrogen flame with 20 detailed chemistries. Consequently, we demonstrated that (1) the FVM-based network architecture provided improved accuracy of multistep time series prediction compared to the previous MLP model (2) the physic-informed loss function prevented non-physical overfitting problem and ultimately reduced the error in time series prediction (3) observing the calculated residuals in an unsupervised manner could indirectly estimate the network accuracy. Additionally, under the reacting flow dataset, the computational speed of this network model was measured to be about 10 times faster than that of the CFD solver.

arXiv:2105.01280

VersaGNN: a Versatile accelerator for Graph neural networks

\textit{Graph Neural Network} (GNN) is a promising approach for analyzing graph-structured data that tactfully captures their dependency information via node-level message passing. It has achieved state-of-the-art performances in many tasks, such as node classification, graph matching, clustering, and graph generation. As GNNs operate on non-Euclidean data, their irregular data access patterns cause considerable computational costs and overhead on conventional architectures, such as GPU and CPU. Our analysis shows that GNN adopts a hybrid computing model. The \textit{Aggregation} (or \textit{Message Passing}) phase performs vector additions where vectors are fetched with irregular strides. The \textit{Transformation} (or \textit{Node Embedding}) phase can be either dense or sparse-dense matrix multiplication. In this work, We propose \textit{VersaGNN}, an ultra-efficient, systolic-array-based versatile hardware accelerator that unifies dense and sparse matrix multiplication. By applying this single optimized systolic array to both aggregation and transformation phases, we have significantly reduced chip sizes and energy consumption. We then divide the computing engine into blocked systolic arrays to support the \textit{Strassen}'s algorithm for dense matrix multiplication, dramatically scaling down the number of multiplications and enabling high-throughput computation of GNNs. To balance the workload of sparse-dense matrix multiplication, we also introduced a greedy algorithm to combine sparse sub-matrices of compressed format into condensed ones to reduce computational cycles. Compared with current state-of-the-art GNN software frameworks, \textit{VersaGNN} achieves on average 3712$\times$ speedup with 1301.25$\times$ energy reduction on CPU, and 35.4$\times$ speedup with 17.66$\times$ energy reduction on GPU.

arXiv:2105.00728

Spectral Machine Learning for Pancreatic Mass Imaging Classification

We present a novel spectral machine learning (SML) method in screening for pancreatic mass using CT imaging. Our algorithm is trained with approximately 30,000 images from 250 patients (50 patients with normal pancreas and 200 patients with abnormal pancreas findings) based on public data sources. A test accuracy of 94.6 percents was achieved in the out-of-sample diagnosis classification based on a total of approximately 15,000 images from 113 patients, whereby 26 out of 32 patients with normal pancreas and all 81 patients with abnormal pancreas findings were correctly diagnosed. SML is able to automatically choose fundamental images (on average 5 or 9 images for each patient) in the diagnosis classification and achieve the above mentioned accuracy. The computational time is 75 seconds for diagnosing 113 patients in a laptop with standard CPU running environment. Factors that influenced high performance of a well-designed integration of spectral learning and machine learning included: 1) use of eigenvectors corresponding to several of the largest eigenvalues of sample covariance matrix (spike eigenvectors) to choose input attributes in classification training, taking into account only the fundamental information of the raw images with less noise; 2) removal of irrelevant pixels based on mean-level spectral test to lower the challenges of memory capacity and enhance computational efficiency while maintaining superior classification accuracy; 3) adoption of state-of-the-art machine learning classification, gradient boosting and random forest. Our methodology showcases practical utility and improved accuracy of image diagnosis in pancreatic mass screening in the era of AI.

arXiv:2105.00114

Improved Real-Time Monocular SLAM Using Semantic Segmentation on Selective Frames

Monocular simultaneous localization and mapping (SLAM) is emerging in advanced driver assistance systems and autonomous driving, because a single camera is cheap and easy to install. Conventional monocular SLAM has two major challenges leading inaccurate localization and mapping. First, it is challenging to estimate scales in localization and mapping. Second, conventional monocular SLAM uses inappropriate mapping factors such as dynamic objects and low-parallax areas in mapping. This paper proposes an improved real-time monocular SLAM that resolves the aforementioned challenges by efficiently using deep learning-based semantic segmentation. To achieve the real-time execution of the proposed method, we apply semantic segmentation only to downsampled keyframes in parallel with mapping processes. In addition, the proposed method corrects scales of camera poses and three-dimensional (3D) points, using estimated ground plane from road-labeled 3D points and the real camera height. The proposed method also removes inappropriate corner features labeled as moving objects and low parallax areas. Experiments with eight video sequences demonstrate that the proposed monocular SLAM system achieves significantly improved and comparable trajectory tracking accuracy, compared to existing state-of-the-art monocular and stereo SLAM systems, respectively. The proposed system can achieve real-time tracking on a standard CPU potentially with a standard GPU support, whereas existing segmentation-aided monocular SLAM does not.

arXiv:2104.15114공식 코드 · Papers with Code

Paraphrastic Representations at Scale

We present a system that allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. We also release trained models for English, Arabic, German, French, Spanish, Russian, Turkish, and Chinese. We train these models on large amounts of data, achieving significantly improved performance from the original papers proposing the methods on a suite of monolingual semantic similarity, cross-lingual semantic similarity, and bitext mining tasks. Moreover, the resulting models surpass all prior work on unsupervised semantic textual similarity, significantly outperforming even BERT-based models like Sentence-BERT (Reimers and Gurevych, 2019). Additionally, our models are orders of magnitude faster than prior work and can be used on CPU with little difference in inference speed (even improved speed over GPU when using more CPU cores), making these models an attractive choice for users without access to GPUs or for use on embedded devices. Finally, we add significantly increased functionality to the code bases for training paraphrastic sentence models, easing their use for both inference and for training them for any desired language with parallel data. We also include code to automatically download and preprocess training data.