trainworker.sh

This shell script is an internal script called by runtraining.sh that calls caffetrain.sh on all three caffe models.

Usage

usage: trainworker.sh [-h] [--models MODELS]
                              [--numiterations NUMITERATIONS] 
                              [--gpu GPU] [--base_lr BASE_LR] [--power POWER] 
                              [--momentum MOMENTUM] 
                              [--weight_decay WEIGHT_DECAY] 
                              [--average_loss AVERAGE_LOSS] 
                              [--lr_policy POLICY] [--iter_size ITER_SIZE] 
                              [--snapshot_interval SNAPSHOT_INTERVAL]
                              trainoutdir
              Version: 1.6.0

              Runs caffe training on CDeep3M model in <trainoutdir>
              directory.

              For further information about parameters below please see: 
              https://github.com/BVLC/caffe/wiki/Solver-Prototxt 


optional arguments:
  -h, --help           show this help message and exit
  --models             Only train on models specified in comma 
                       delimited list. (default 1fm,3fm,5fm)
  --gpu                Which GPU to use, can be a number ie 0 or 1 or
                       all to use all GPUs (default all)
  --base_learn         Base learning rate (default 1e-02)
  --power              Used in poly and sigmoid lr_policies. (default 0.8)
  --momentum           Indicates how much of the previous weight will be 
                       retained in the new calculation. (default 0.9)
  --weight_decay       Factor of (regularization) penalization of large
                       weights (default 0.0005)
  --average_loss       Number of iterations to use to average loss
                       (default 16)
  --lr_policy          Learning rate policy (default poly)
  --iter_size          Accumulate gradients across batches through the 
                       iter_size solver field. (default 8)
  --snapshot_interval  How often caffe should output a model and solverstate.
                       (default 2000)
  --numiterations      Number of training iterations to run (default 30000)

Example:

trainworker.sh --numiterations 2000 ~/trainoutdir