Skip to content

Instantly share code, notes, and snippets.


AruniRC AruniRC

View GitHub Profile
AruniRC /
Created Jun 19, 2020
Histogram specification demo code
import os
import sys
import pickle
import json
import numpy as np
import sys
import matplotlib
from matplotlib import pyplot as plt
import os.path as osp
AruniRC / bashrc_renyi
Last active Apr 19, 2020
Bashrc renyi server
View bashrc_renyi
if [ -n "$force_color_prompt" ]; then
if [ -x /usr/bin/tput ] && tput setaf 1 >&/dev/null; then
# We have color support; assume it's compliant with Ecma-48
# (ISO/IEC-6429). (Lack of such support is extremely rare, and such
# a case would tend to support setf rather than setaf.)
AruniRC / bash_profile
Last active Aug 14, 2020
Bashrc macbook home
View bash_profile
export PS1="\[\033[36m\]\u\[\033[m\]@\[\033[32m\]\h:\[\033[33;1m\]\w\[\033[m\]\n\$ "
export CLICOLOR=1
export LSCOLORS=ExFxBxDxCxegedabagacad
# User defined aliases
alias ls='ls -GFh'
# Mounting remote drives (create folder manually first under ~/Mount/remote-name)
alias mount-fisher='sshfs ~/Mount/fisher -o volname=fisher'
AruniRC /
Created Jul 30, 2019
Adding edge thickness and node colors in NetworkX graph plotting
# saliency
sal = cluster_saliency[cluster_label] # [ (grad-norm, grad-max)
grad_max = sal[1] / max(sal[1])
feat_vertices = features[cluster_ids, :]
adj_mat = get_adjmat(feat_vertices, is_norm_adj=False)
adj_mat_normed = get_adjmat(feat_vertices, is_norm_adj=True)
# create networkx graph from adjacency matrix
AruniRC /
Last active Apr 24, 2019
Allow shifts and scales of Poincare distance which usually lies on the unit disc
import numpy as np
import itertools
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.nn.init as init
from torch.autograd import Variable
from torch.autograd import Function
from scipy.spatial.distance import pdist
def forward(self, x):
x = self.features(x)
[bs, ch, h, w] = x.shape
x = x.view(bs, ch, -1).transpose(2, 1)
# x.register_hook(self.save_grad('x'))
# Gram Matrix NxN for the N input features "x"
K = x.bmm(x.transpose(2, 1))
K = x * x; # < --- IS THIS CORRECT for 1st order features????
AruniRC /
Last active Feb 27, 2019
HOWTO and quick links to help me learn (and remember) Vim and Netrw as part of my workflow
AruniRC / netrw.txt
Created Feb 27, 2019 — forked from danidiaz/netrw.txt
Vim's netrw commands.
View netrw.txt
--- ----------------- ----
Map Quick Explanation Link
--- ----------------- ----
< <F1> Causes Netrw to issue help
<cr> Netrw will enter the directory or read the file |netrw-cr|
<del> Netrw will attempt to remove the file/directory |netrw-del|
<c-h> Edit file hiding list |netrw-ctrl-h|
<c-l> Causes Netrw to refresh the directory listing |netrw-ctrl-l|
<c-r> Browse using a gvim server |netrw-ctrl-r|
<c-tab> Shrink/expand a netrw/explore window |netrw-c-tab|
AruniRC /
Last active Jul 4, 2019
Setup conda environment for Detectron with PyTorch on Gypsum

This walkthrough describes setting up Detectron (3rd party pytorch implementation) and Graph Conv Net (GCN) repos on the UMass cluster Gypsum. Most commands are specific to that setting.

Gypsum environment

$ module list
Currently Loaded Modulefiles:
  1) slurm/16.05.8                         3) hdf5/1.6.10                           5) gcc5/5.4.0                            7) cudnn/5.1
  2) openmpi/gcc/64/1.10.1                 4) fftw2/openmpi/open64/64/float/2.1.5   6) cuda80/toolkit/8.0.61                 8) hdf5_18/1.8.17
AruniRC /
Created Sep 13, 2018
Pytorch distillation soft targets
if self.distill:
soft_target = Variable(data[2].cuda())
distill_loss = torch.mean(torch.sum(- nn.Softmax(dim=1)(soft_target/self.T) * nn.LogSoftmax(dim=1)(out_data/self.T), 1))
loss += self.lbda*distill_loss
self.writer.add_scalar('train/distill_loss', distill_loss, i_acc+i+1)