DIAGNijmegen/StreamingCNN
To train deep convolutional neural networks, the input data and the activations need to be kept in memory. Given the limited memory available in current GPUs, this limits the maximum dimensions of the input data. Here we demonstrate a method to train convolutional neural networks while holding only parts of the image in memory.
Jupyter NotebookMIT
Stargazers
- abursucvaleo.ai
- avijit9Hyderabad, India
- basveelingAI4Science @ Microsoft Research
- dnlcrl@dvisionlab
- DrSleepAdelaide, AU
- fly51flyPRIS
- ggsonic
- jdc08161063
- JonathanFlyiforcedabot.com
- KlaymenGC
- kli-casiaCASIA
- kloumpt
- kmaderZurich, Switzerland
- lxtGHBytedance
- mechatron1991Saarland, Germany
- mrajchlImperial College London
- MSC19950601
- nathaninSingular Genomics
- nijianmo
- nom
- omorillo
- PhilipChiccoHarvard Medical School
- radao@scythe-robotics
- renmengyeNYU
- silvandeleemput
- skripov-ds-aiRussia, Omsk
- smrjansTalentica
- supernesSofia, Bulgaria
- tonysyShanghai AI Lab
- udionDowntown Toronto
- vaxherra7N
- weiji14@developmentseed
- weixia1Anhui University
- wouterbulten@Aiosyn
- xuanhan863Los Angeles, USA
- yaramohamadiUniversity of Tehran