Introduction to PyTorch

Ketkar, Nikhil

doi:10.1007/978-1-4842-2766-4_12

Cited by 448 publications

(240 citation statements)

References 0 publications

Supporting

Mentioning

239

Contrasting

Unclassified

Order By: Relevance

“…We implement our model in python 3.4 and cuDNN 6.0 using pyTorch [16] and use NYU-Depth-v2 dataset to train our model. As for training, we use an NVIDIA TITAN xp with 12GB memory.…”

Section: Methodsmentioning

confidence: 99%

Depth Estimation from Monocular Image and Coarse Depth Points based on Conditional GAN

Qian

Zhou

2018

MATEC Web Conf.

View full text Add to dashboard Cite

Abstract. Depth estimation has achieved considerable success with the development of the depth sensor devices and deep learning method. However, depth estimation from monocular RGB-based image will increase ambiguity and is prone to error. In this paper, we present a novel approach to produce dense depth map from a single image coupled with coarse point-cloud samples. Our approach learns to fit the distribution of the depth map from source data using conditional adversarial networks and convert the sparse point clouds to dense maps. Our experiments show that the use of the conditional adversarial networks can add full image information to the predicted depth maps and the effectiveness of our approach to predict depth in NYU-Depthv2 indoor dataset.

show abstract

“…We implement our model in python 3.4 and cuDNN 6.0 using pyTorch [16] and use NYU-Depth-v2 dataset to train our model. As for training, we use an NVIDIA TITAN xp with 12GB memory.…”

Section: Methodsmentioning

confidence: 99%

Depth Estimation from Monocular Image and Coarse Depth Points based on Conditional GAN

Qian

Zhou

2018

MATEC Web Conf.

View full text Add to dashboard Cite

show abstract

“…Here, we will assume that the total variational energy of the system, E is such that there exists a unique solution of the problem defined in Eq. (6) and is the same as the solution of Eq. (1).…”

Section: Energy Approachmentioning

confidence: 99%

An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications

Samaniego

Anitescu

Goswami

et al. 2020

Computer Methods in Applied Mechanics and Engineering

1,161

281

View full text Add to dashboard Cite

Partial Differential Equations (PDE) are fundamental to model different phenomena in science and engineering mathematically. Solving them is a crucial step towards a precise knowledge of the behaviour of natural and engineered systems. In general, in order to solve PDEs that represent real systems to an acceptable degree, analytical methods are usually not enough. One has to resort to discretization methods. For engineering problems, probably the best known option is the finite element method (FEM). However, powerful alternatives such as mesh-free methods and Isogeometric Analysis (IGA) are also available. The fundamental idea is to approximate the solution of the PDE by means of functions specifically built to have some desirable properties. In this contribution, we explore Deep Neural Networks (DNNs) as an option for approximation. They have shown impressive results in areas such as visual recognition. DNNs are regarded here as function approximation machines. There is great flexibility to define their structure and important advances in the architecture and the efficiency of the algorithms to implement them make DNNs a very interesting alternative to approximate the solution of a PDE. We concentrate in applications that have an interest for Computational Mechanics. Most contributions that have decided to explore this possibility have adopted a collocation strategy. In this contribution, we concentrate in mechanical problems and analyze the energetic format of the PDE. The energy of a mechanical system seems to be the natural loss function for a machine learning method to approach a mechanical problem. As proofs of concept, we deal with several problems and explore the capabilities of the method for applications in engineering.

show abstract

“…The data sets are summarized in Table 4. All the experiments for LibriSpeech were performed using ESPnet, the End-to-End Speech Processing Toolkit [34], and the recipe for a baseline LibriSpeech setup with PyTorch backend [35]. According to the baseline recipe, we trained an 8-layer BLSTM encoder including 320 cells in each layer and direction, and the linear projection layer with 320 units followed by each BLSTM layer.…”

Section: Evaluation With Librispeechmentioning

confidence: 99%

End-to-end Speech Recognition With Word-Based Rnn Language Models

Hori

Cho

Watanabe

2018

2018 IEEE Spoken Language Technology Workshop (SLT)

109

View full text Add to dashboard Cite

This paper investigates the impact of word-based RNN language models (RNN-LMs) on the performance of end-to-end automatic speech recognition (ASR). In our prior work, we have proposed a multi-level LM, in which character-based and word-based RNN-LMs are combined in hybrid CTC/attention-based ASR. Although this multi-level approach achieves significant error reduction in the Wall Street Journal (WSJ) task, two different LMs need to be trained and used for decoding, which increase the computational cost and memory usage. In this paper, we further propose a novel wordbased RNN-LM, which allows us to decode with only the wordbased LM, where it provides look-ahead word probabilities to predict next characters instead of the character-based LM, leading competitive accuracy with less computation compared to the multi-level LM. We demonstrate the efficacy of the word-based RNN-LMs using a larger corpus, LibriSpeech, in addition to WSJ we used in the prior work. Furthermore, we show that the proposed model achieves 5.1 %WER for WSJ Eval'92 test set when the vocabulary size is increased, which is the best WER reported for end-to-end ASR systems on this benchmark.Index Terms-End-to-end speech recognition, language modeling, decoding, connectionist temporal classification, attention decoder 1. Character-based LM can help correct hypotheses survive until they are rescored at word boundaries during the beam search. Before the hypothesis reaches the boundary, the identity of the last word is unknown and its word probability cannot be applied. Hence, good character-level prediction is important to avoid pruning errors for hypotheses within a word.2. Character-based LM can predict character sequences even for OOV words not included in the vocabulary of the word-based LM. Since the word-based LM basically cannot predict unseen character sequences, good character-level prediction is important for open-vocabulary ASR.However, the multi-level LM approach has a problem that it requires two different RNN-LMs. To build the two LMs, we need to

show abstract

Introduction to PyTorch

Cited by 448 publications

References 0 publications

Depth Estimation from Monocular Image and Coarse Depth Points based on Conditional GAN

Depth Estimation from Monocular Image and Coarse Depth Points based on Conditional GAN

An energy approach to the solution of partial differential equations in computational mechanics via machine learning: Concepts, implementation and applications

End-to-end Speech Recognition With Word-Based Rnn Language Models

Contact Info

Product

Resources

About