Compiling ONNX Neural Network Models Using MLIR

1 code implementation • 19 Aug 2020 • Tian Jin, Gheorghe-Teodor Bercea, Tung D. Le, Tong Chen, Gong Su, Haruki Imai, Yasushi Negishi, Anh Leu, Kevin O'Brien, Kiyokuni Kawachiya, Alexandre E. Eichenberger

Deep neural network models are becoming increasingly popular and have been used in various tasks such as computer vision, speech recognition, and natural language processing.

speech-recognition Speech Recognition

Profiling based Out-of-core Hybrid Method for Large Neural Networks

no code implementations • 11 Jul 2019 • Yuki Ito, Haruki Imai, Tung Le Duc, Yasushi Negishi, Kiyokuni Kawachiya, Ryo Matsumiya, Toshio Endo

We implemented PoocH by extending a deep learning framework, Chainer, and we evaluated its performance.

Fast and Accurate 3D Medical Image Segmentation with Data-swapping Method

no code implementations • 19 Dec 2018 • Haruki Imai, Samuel Matzek, Tung D. Le, Yasushi Negishi, Kiyokuni Kawachiya

A popular approach to tackling this problem is patch-based method, which divides a large image into small patches and trains the models with these small patches.

Image Segmentation Medical Image Segmentation +2

TFLMS: Large Model Support in TensorFlow by Graph Rewriting

no code implementations • 5 Jul 2018 • Tung D. Le, Haruki Imai, Yasushi Negishi, Kiyokuni Kawachiya

We propose an approach to tackle this problem by rewriting the computational graph of a neural network, in which swap-out and swap-in operations are inserted to temporarily store intermediate results on CPU memory.

Image Segmentation Semantic Segmentation