Florin Gogianu floringogianu

Preparation of ImageNet (ILSVRC2012)

The dataset can be found on the official website if you are affiliated with a research organization. It is also available on Academic torrents.

This script extracts all the images and group them so that folders contain images that belong to the same class.

Download the ILSVRC2012_img_train.tar and ILSVRC2012_img_val.tar
Download the script wget https://gist.githubusercontent.com/antoinebrl/7d00d5cb6c95ef194c737392ef7e476a/raw/dc53ad5fcb69dcde2b3e0b9d6f8f99d000ead696/prepare.sh
Run it ./prepare.sh

	import optuna
	from optuna.trial import TrialState
	import numpy as np
	from typing import Dict, List, Optional
	from collections import defaultdict


	class ParamRepeatPruner:
	"""Prunes reapeated trials, which means trials with the same paramters won't waste time/resources."""

	import jax
	import jax.numpy as np
	from jax import grad, jit
	from jax.scipy.special import logsumexp


	def dadashi_fig2d():
	""" Figure 2 d) of
	''The Value Function Polytope in Reinforcement Learning''
	by Dadashi et al. (2019) https://arxiv.org/abs/1901.11524

	# null.py

	import numpy as np
	from scipy.linalg import qr

	def qr_null(A, tol=None):
	Q, R, P = qr(A.T, mode='full', pivoting=True)
	tol = np.max(A) * np.finfo(R.dtype).eps if tol is None else tol
	rnk = min(A.shape) - np.abs(np.diag(R))[::-1].searchsorted(tol)
	return Q[:, rnk:].conj()

	Pretty print tables summarizing properties of tensor arrays in numpy, pytorch, jax, etc.

	Now on pip! `pip install arrgh` https://github.com/nmwsharp/arrgh