39 citations · 84 across the 5 of their papers we have counts for
3 papers · 1 filter
Fast and Accurate 3D Medical Image Segmentation with Data-swapping Method
Haruki Imai, Samuel Matzek, Tung D. Le +2
Deep neural network models used for medical image segmentation are large because they are trained with high-resolution three-dimensional (3D) images. Graphics processing units (GPU…
TFLMS: Large Model Support in TensorFlow by Graph Rewriting
Tung D. Le, Haruki Imai, Yasushi Negishi +1
While accelerators such as GPUs have limited memory, deep neural networks are becoming larger and will not fit with the memory limitation of accelerators for training. We propose a…
Profile-guided memory optimization for deep neural networks
Taro Sekiyama, Takashi Imamichi, Haruki Imai +1
Recent years have seen deep neural networks (DNNs) becoming wider and deeper to achieve better performance in many applications of AI. Such DNNs however require huge amounts of mem…