PrototypeCommon
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…
- Owner
- DIAGNijmegen (organization)
- Stars
- Stars: 101
- Forks
- Forks: 26
- Language
- Jupyter Notebook
- License
- MIT
- Created
- 2018
- Tier
- Prototype (100 to 249 ★) What this tier means
More repos by DIAGNijmegen
All 4 repos by DIAGNijmegen- DIAGNijmegen/rse-grand-challengeStars: 194PythonPrototype
- DIAGNijmegen/pathology-whole-slide-dataStars: 119PythonPrototype
- DIAGNijmegen/neural-odes-segmentationStars: 111PythonPrototype
Nearby in Jupyter Notebook
All Jupyter Notebook repos- alvaroprat97/sigmadockStars: 101Jupyter NotebookPrototype
- Isso-W/RDPRO-SS26-ProjectStars: 101Jupyter NotebookPrototype
- cair-vinuni/CLP_VLAStars: 101Jupyter NotebookPrototype
- kylemcdonald/LightLeaksStars: 101Jupyter NotebookPrototype
- kyuni22/pybbgStars: 101Jupyter NotebookPrototype
- dpsanders/scipy_2014_juliaStars: 101Jupyter NotebookPrototype