KBlansit

TECHNICAL DETAILS
The most important specification at this time is that COMET GPUs have the nvidia 367.48 driver installed.  As a result, we are
restricted to versions of CUDA <= 8.0.  In turn, we are restricted to using tensorflow <= 1.4.1 due to using CUDA 8.0.  These
drivers may change over time, but thankfully, adapting is as trivial as updating the Dockerfile and rebuilding the container.
It should be noted that since the cluster does not have Docker, we need to generate and push Docker images locally, then pull
them on the cluster.  A bit convoluted, but not too bad.

Also, tensorflow 1.4.1 requires cuDNN >= 6

HOW-TO

KBlansit

# i iterable are values of sigma to probe
template=$PWD"/settings/data_pipeline_settings_ns.yaml"
outputHeader=$PWD"/settings/sigma_"
outputEnder=".yaml"
aiSettings=$PWD"/settings/ai_settings.yaml"
for i in 10 20 30 40 50 60 70 80 90
do
  sigma=$i
  output=$outputHeader$sigma$outputEnder
  echo $output

KBlansit

# deep learning settings
WEIGHT_DECAY: 0.0005
LEARNING_RATE: 10e-4
MOMENTUM: 0.99
DOWNSIZE_FILTER_FACTOR: 1
EPOCHS: 1
KERNEL_SIZE: 3

# file settings
BATCH_SIZE: 10

KBlansit

anatomic_landmarks:
  "1": "AV"
  "2": "PV"
  "3": "MV"
  "4": "TV"
  "5": "Apex"

  "q": "MMA - 1"
  "w": "MMA - 2"
  "e": "MMA - 3"

KBlansit

# import libraries
require(data.table)
require(dplyr)

# define system variables
PROCEDURE <- '^proc_p$|^oproc[0-9]{1,2}'
DIAGNOSIS <- '^diag_p$|^odiag[0-9]{1,2}'

ROBOTIC_PROCEDURE <- '^174[^1]{1}'
MIN_VOL <- 25

KBlansit

We couldn’t find that file to show.