Shubham Agarwal shubhamagarwal92

Here's a simple implementation of bilinear interpolation on tensors using PyTorch.

I wrote this up since I ended up learning a lot about options for interpolation in both the numpy and PyTorch ecosystems. More generally than just interpolation, too, it's also a nice case study in how PyTorch magically can put very numpy-like code on the GPU (and by the way, do autodiff for you too).

For interpolation in PyTorch, this open issue calls for more interpolation features. There is now a nn.functional.grid_sample() feature but at least at first this didn't look like what I needed (but we'll come back to this later).

In particular I wanted to take an image, W x H x C, and sample it many times at different random locations. Note also that this is different than upsampling which exhaustively samples and also doesn't give us fle

Enter this in the search box along with your search terms:

Get all gists from the user santisbon.
user:santisbon

Find all gists with a .yml extension.
extension:yml

Find all gists with HTML files.
language:html

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

	from collections import defaultdict

	# method 1
	my_dict = defaultdict(int)
	my_dict[key] += 1

	# method 2
	my_dict = {}
	my_dict[key] = my_dict.get(key, 0) + 1

	tail -f logs.txt
	watch -n1 nvidia-smi
	htop
	watch -n 1 free -h

	# Refer https://fizzylogic.nl/2017/11/06/edit-jupyter-notebooks-over-ssh/

	# On server
	jupyter notebook --no-browser --port=8080

	# On local machine
	ssh -N -L 8080:localhost:8080 <remote_user>@<remote_host>

	# https://stackoverflow.com/a/52076633/3776827
	# Run as download_drive_file.sh file_id

	# where file_id is google drive file id
	# https://drive.google.com/file/d/0B-u9nH58139bTy1XRFdqaVEzUGs/view
	# Eg. file_id here is 0B-u9nH58139bTy1XRFdqaVEzUGs
	curl gdrive.sh \| bash -s $1

	from wordcloud import WordCloud, STOPWORDS
	from PIL import Image
	import urllib
	import requests
	import numpy as np
	import matplotlib.pyplot as plt

	words = 'access guest guest apartment area area bathroom bed bed bed bed bed bedroom block coffee coffee coffee coffee entrance entry francisco free garden guest home house kettle kettle kitchen kitchen kitchen kitchen kitchen kitchenliving located microwave neighborhood new park parking place privacy private queen room san separate seperate shared space space space street suite time welcome'
	mask = np.array(Image.open(requests.get('http://www.clker.com/cliparts/O/i/x/Y/q/P/yellow-house-hi.png', stream=True).raw))