Pinned Repositories
course
Course site
dam_detection
Dam detection using satellite imagery with Google Earth Engine and machine learning
deepops
Tools for building GPU clusters
ismi
intelligent systems in medical imaging
NN-hyperparameter
Natural computing assignment on tuning hyperparameters for neural networks
panda
Prostate cANcer graDe Assessment
pathology-streaming-pipeline
Use streaming to train whole-slides images with single image-level labels, by reducing GPU memory requirements with 99%.
speaker_estimation
Count the number of speakers in a conversation
stephandooper.github.io
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.
stephandooper's Repositories
stephandooper/dam_detection
Dam detection using satellite imagery with Google Earth Engine and machine learning
stephandooper/NN-hyperparameter
Natural computing assignment on tuning hyperparameters for neural networks
stephandooper/ismi
intelligent systems in medical imaging
stephandooper/course
Course site
stephandooper/deepops
Tools for building GPU clusters
stephandooper/panda
Prostate cANcer graDe Assessment
stephandooper/pathology-streaming-pipeline
Use streaming to train whole-slides images with single image-level labels, by reducing GPU memory requirements with 99%.
stephandooper/speaker_estimation
Count the number of speakers in a conversation
stephandooper/stephandooper.github.io
stephandooper/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.