paper-with-me

Papers

ShapeFlow: Dynamic Shape Interpreter for TensorFlow

2020-11-26 · Sahil Verma, Zhendong Su

We present ShapeFlow, a dynamic abstract interpreter for TensorFlow which quickly catches tensor shape incompatibility errors, one of the most common bugs in deep learning code. ShapeFlow shares the same APIs as TensorFlow but only captures and emits tensor shapes, its abstract domain. ShapeFlow constructs a custom shape computational graph, similar to the computational graph used by TensorFlow. ShapeFlow requires no code annotation or code modification by the programmer, and therefore is convenient to use. We evaluate ShapeFlow on 52 programs collected by prior empirical studies to show how fast and accurately it can catch shape incompatibility errors compared to TensorFlow. We use two baselines: a worst-case training dataset size and a more realistic dataset size. ShapeFlow detects shape incompatibility errors highly accurately -- with no false positives and a single false negative -- and highly efficiently -- with an average speed-up of 499X and 24X for the first and second baseline, respectively. We believe ShapeFlow is a practical tool that benefits machine learning developers. We will open-source ShapeFlow on GitHub to make it publicly available to both the developer and research communities.

📄 PDF Abstract BibTeX arXiv:2011.13452

Code (1)

vsahil/Static-Analyser_ML 공식 구현 tf

Similar Papers 제목 키워드 기반

ShapeFlow: Learnable Deformations Among 3D Shapes

2020-06-14 · Chiyu "Max" Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas Guibas

We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations. ShapeFlow allows learning a multi-template deformation space that is agnostic t…

DisentanglementStyle Transfer

ShapeFlow: Learnable Deformation Flows Among 3D Shapes

2020-12-01 · NeurIPS 2020 12 · Chiyu Jiang, Jingwei Huang, Andrea Tagliasacchi, Leonidas J. Guibas

We present ShapeFlow, a flow-based model for learning a deformation space for entire classes of 3D shapes with large intra-class variations. ShapeFlow allows learning a multi-template deformation space that is agnostic t…

DisentanglementStyle Transfer

TensorFlow Agents: Efficient Batched Reinforcement Learning in TensorFlow

2017-09-08 · Danijar Hafner, James Davidson, Vincent Vanhoucke

We introduce TensorFlow Agents, an efficient infrastructure paradigm for building parallel reinforcement learning algorithms in TensorFlow. We simulate multiple environments in parallel, and group them to perform the neu…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Using Python for Model Inference in Deep Learning

2021-04-01 · Zachary DeVito, Jason Ansel, Will Constable, Michael Suo 외

Python has become the de-facto language for training deep neural networks, coupling a large suite of scientific computing libraries with efficient libraries for tensor computation such as PyTorch or TensorFlow. However, …

Deep LearningmodelModel extraction

Fast Linear Interpolation for Piecewise-Linear Functions, GAMs, and Deep Lattice Networks

2019-09-25 · Nathan Zhang, Kevin Canini, Sean Silva, and Maya R. Gupta

We present fast implementations of linear interpolation operators for both piecewise linear functions and multi-dimensional look-up tables. We use a compiler-based solution (using MLIR) for accelerating this family of wo…

CPU