Fabrice Sodogandji fsodogandji

Sequential model in Keras -> ASCII

EDIT: Now at: https://github.com/stared/keras-sequential-ascii, pip-installable.

Usage

from keras_ascii_sequential import sequential_model_to_ascii_printout

A Tour of PyTorch Internals (Part I)

The fundamental unit in PyTorch is the Tensor. This post will serve as an overview for how we implement Tensors in PyTorch, such that the user can interact with it from the Python shell. In particular, we want to answer four main questions:

How does PyTorch extend the Python interpreter to define a Tensor type that can be manipulated from Python code?
How does PyTorch wrap the C libraries that actually define the Tensor's properties and methods?
How does PyTorch cwrap work to generate code for Tensor methods?
How does PyTorch's build system take all of these components to compile and generate a workable application?

Extending the Python Interpreter

PyTorch defines a new package torch. In this post we will consider the ._C module. This module is known as an "extension module" - a Python module written in C. Such modules allow us to define new built-in object types (e.g. the Tensor) and to call C/C++ functions.

How to set up DNS records on gandi.net to use a custom domain on Github Pages

You would think it would be easy to find this information, but none of the Github or Gandi documentation is clear so I have recorded the required steps here.

Create the following A records:

@ 1800 IN A 185.199.108.153
@ 1800 IN A 185.199.109.153
@ 1800 IN A 185.199.110.153

TL;DR

Guide from https://glitchwitch.io/blog/2018-09/windows-10-on-digitalocean/
Download Windows ISO from https://www.microsoft.com/en-us/software-download/windows10ISO

Steps

Create a build droplet with 4GB RAM
Install QEMU and run the Windows 10 installation ISO

$ apt-get update && apt-get install qemu -y
$ qemu-img create -f raw windows10.img 16G

	from functools import wraps
	from types import FunctionType, GeneratorType
	import logging
	import time

	def coroutine(f):
	@wraps(f)
	def wrapper(args, *kwargs):
	logging.debug('coroutine starting: {}'.format(f.__name__))
	return f(args, *kwargs)

	from tf_logger import TFLogger


	""" Example of using TFLogger to save train & dev statistics. To visualize
	in tensorboard simply do:

	tensorboard --logdir /path/to/summaries

	This code does depend on Tensorflow, but does not require that your model
	is built using Tensorflow. For instance, could build a model in Chainer, then

	# References:
	# [1] Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding, Fukui et al., https://arxiv.org/abs/1606.01847
	# [2] Compact Bilinear Pooling, Gao et al., https://arxiv.org/abs/1511.06062
	# [3] Fast and Scalable Polynomial Kernels via Explicit Feature Maps, Pham and Pagh, https://chbrown.github.io/kdd-2013-usb/kdd/p239.pdf
	# [4] Fastfood — Approximating Kernel Expansions in Loglinear Time, Le et al., https://arxiv.org/abs/1408.3060
	# [5] Original implementation in Caffe: https://github.com/gy20073/compact_bilinear_pooling

	# TODO: migrate to use of new native complex64 types
	# TODO: change strided x coo matmul to torch.matmul(): M[sparse_coo] @ M[strided] -> M[strided]