PyTorch: An Imperative Style, High-Performance Deep Learning Library

Paszke, Adam; Gross, Sam; Massa, Francisco; Lerer, Adam; Bradbury, James T.; Chanan, Gregory; Killeen, Trevor; Lin, Zhongqin; Gimelshein, Natalia; Antiga, Luca; Desmaison, Alban; Köpf, Andreas; Yang, E.S.; DeVito, Zach; Raison, Martin; Tejani, Alykhan; Chilamkurthy, Sasank; Steiner, Benoit; Liu, Feng; Bai, Junjie; Chintala, Soumith

doi:10.48550/arxiv.1912.01703

Cited by 1,075 publications

(1,019 citation statements)

References 9 publications

(9 reference statements)

Supporting

Mentioning

882

Contrasting

Unclassified

Order By: Relevance

“…Libraries Neural networks were implemented in PyTorch (Paszke et al, 2019). The RL algorithms were implemented using Tonic (Pardo, 2021).…”

Section: A Experimental Detailsmentioning

confidence: 99%

Neural Circuit Architectural Priors for Embodied Control

Bhattasali¹,

Zador²,

Engel³

2022

Preprint

View full text Add to dashboard Cite

Artificial neural networks for simulated motor control and robotics often adopt generic architectures like fully connected MLPs. While general, these tabula rasa architectures rely on large amounts of experience to learn, are not easily transferable to new bodies, and have internal dynamics that are difficult to interpret. In nature, animals are born with highly structured connectivity in their nervous systems shaped by evolution; this innate circuitry acts synergistically with learning mechanisms to provide inductive biases that enable most animals to function well soon after birth and improve abilities efficiently. Convolutional networks inspired by visual circuitry have encoded useful biases for vision. However, it is unknown the extent to which ANN architectures inspired by neural circuitry can yield useful biases for other domains. In this work, we ask what advantages biologically inspired network architecture can provide in the context of motor control. Specifically, we translate C. elegans circuits for locomotion into an ANN model controlling a simulated Swimmer agent. On a locomotion task, our architecture achieves good initial performance and asymptotic performance comparable with MLPs, while dramatically improving data efficiency and requiring orders of magnitude fewer parameters. Our architecture is more interpretable and transfers to new body designs. An ablation analysis shows that principled excitation/inhibition is crucial for learning, while weight initialization contributes to good initial performance. Our work demonstrates several advantages of ANN architectures inspired by systems neuroscience and suggests a path towards modeling more complex behavior.

show abstract

“…Libraries Neural networks were implemented in PyTorch (Paszke et al, 2019). The RL algorithms were implemented using Tonic (Pardo, 2021).…”

Section: A Experimental Detailsmentioning

confidence: 99%

Neural Circuit Architectural Priors for Embodied Control

Bhattasali¹,

Zador²,

Engel³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…It takes approximately 3 days to train the full model on one GTX2080 Ti. We train our network with PyTorch [48], using the Adam [33] optimizer with a cyclic learning rate schedule [57] with a base learning rate of 10 −4 and a max learning rate of 5 × 10 −4 . We provide training hyperparameters for each dataset in Section B.…”

Section: Trainingmentioning

confidence: 99%

“…To help understand the flexibility of our self-supervised model, we trained a variation of our model on images with large, simulated brightness and hue variations, inspired by the challenges of rapid exposure changes (e.g., in HDR photography). During training and testing, we randomly jitter the brightness and hue of the second image in KITTI by a factor of up to 0.6 and 0.3 respectively, using PyTorch's [48] built-in augmentation. We finetuned the variation of our model that combines our learned features with Census features (Tab.…”

Section: Motion Estimation Ablationsmentioning

confidence: 99%

See 1 more Smart Citation

Learning Pixel Trajectories with Multiscale Contrastive Random Walks

Bian¹,

Jabri²,

Efros³

et al. 2022

Preprint

View full text Add to dashboard Cite

A range of video modeling tasks, from optical flow to multiple object tracking, share the same fundamental challenge: establishing space-time correspondence. Yet, approaches that dominate each space differ. We take a step towards bridging this gap by extending the recent contrastive random walk formulation to much denser, pixel-level spacetime graphs. The main contribution is introducing hierarchy into the search problem by computing the transition matrix between two frames in a coarse-to-fine manner, forming a multiscale contrastive random walk when extended in time. This establishes a unified technique for selfsupervised learning of optical flow, keypoint tracking, and video object segmentation. Experiments demonstrate that, for each of these tasks, the unified model achieves performance competitive with strong self-supervised approaches specific to that task.

show abstract

“…44 In this work, we demonstrate the integration of NNP in molecular dynamics simulations by implementing NNP/MM in ACEMD 2 using OpenMM 6 and PyTorch. 46 The implementation is validated by performing MD simulations of four protein-ligand complexes. We have made the set up of NNP/MM as simple as possible to facilitate adaption.…”

Section: Introductionmentioning

confidence: 99%