-n 1 -c 64
Slurm settingsmachine | author | commit | commit date | platform | loss | time | check | rel time | points |
---|
Your job is to improve the performance of the existing code, by altering the code in sol/dcnnsol.hpp
.
(You may also write some code in sol/dcnnsol.cpp
;
however, all the existing code is templated and must remain in the header file.)
The folder containing input data is set by the command-line parameter --data-folder
.
The input data are already available at parlab, in the folder /home/_teaching/hiperf/dcnndata
.
Therefore, the program shall be invoked as:
srun -p mpi-homo-short -n 1 -c 64 ./dcnn --data-folder=/home/_teaching/hiperf/dcnndata
The input data may be downloaded from parlab via scp or compressed from here:
data-folder - the folder containing the input data files (default: data
).
minibatch - the number of images in a testing minibatch
(processed in one call to the forward
functions).
Default: 16.
superbatch - the number of minibatches in a testing batch (each minibatch is assigned to a different thread). Default: 8 (1 in Debug mode).
total - the total number of images submitted into testing
(shall be divisible by minibatch*superbatch
).
Default: 2048 (16 in Debug mode).
The DCNN architecture was taken from [Hasanpour 2016]. The original implementation used the Caffe framework and was later converted to Pytorch.
Both the pretrained weights and the test images were converted from publicly available data: