stes

:bowtie:

😄 :smile:

😆 :laughing:

😊 :blush:

😃 :smiley:

stes

""" Adapting ImageNet-scale models to complex distribution shifts with self-learning

Run with:

    ❯ docker pull pytorch/pytorch
    ❯ DATADIR="/path/to/imagenetc"
    ❯ curl -s https://stes.io/gce.py > gce.py
    ❯ docker run --gpus 1 -v ${DATADIR}:/data/imagenetc:ro \
        -v $(pwd):/app -w /app -u $(id -u) \
        --tmpfs /.cache --tmpfs /.local \

stes

#!/bin/bash
# Download gitignore files from https://github.com/github/gitignore
# Example Usage: ./gitignore.sh Python Java > .gitignore

invalid_language() {
    >&2 echo "No gitignore found for $1."
    return 1
}

echo_header() {

stes

#!/bin/bash

# Seen on https://coderwall.com/p/pfm8qg/counting-lines-of-code-in-a-python-project
# execute with file extension as argument, e.g.: 
# $ ./loc.sh py

find . -name "*.${1}" -type f -exec grep . {} \; | wc -l

stes

""" Convert weights from matconvnet model to an hdf5 dataset loadable into Lasagne models.

Call with ./matconv2hdf5.py [basename]
"""

import sys, os
from urllib.request import urlretrieve
import scipy.io
import collections
import h5py

stes

#define NB_STEPS (1000)

byte sine[] = {
  127,127,128,129,130,131,131,132,133,134,135,135,136,137,138,139,139,140,141,142,143,143,144,145,146,147,147,148,149,150,151,151,152,153,154,154,155,156,157,158,158,159,160,161,161,162,163,164,165,165,166,167,168,168,169,170,171,171,172,173,174,174,175,176,177,177,178,179,180,180,181,182,183,183,184,185,185,186,187,188,188,189,190,190,191,192,192,193,194,194,195,196,197,197,198,199,199,200,200,201,202,202,203,204,204,205,206,206,207,208,208,209,209,210,211,211,212,212,213,214,214,215,215,216,217,217,218,218,219,219,220,220,221,222,222,223,223,224,224,225,225,226,226,227,227,228,228,229,229,230,230,231,231,232,232,232,233,233,234,234,235,235,235,236,236,237,237,238,238,238,239,239,239,240,240,241,241,241,242,242,242,243,243,243,244,244,244,245,245,245,246,246,246,246,247,247,247,248,248,248,248,249,249,249,249,249,250,250,250,250,251,251,251,251,251,251,252,252,252,252,252,252,253,253,253,253,253,253,253,253,254,254,254,254,254,254,254,254,254,254,254,254,254,254,254,2

stes

import theano
import lasagne
import numpy as np

def upsample(layer, nb_kernels):

    def build_bilinear_kernel(ratio):
        half_kern = np.arange(1, ratio + 1)
        kern = np.concatenate([half_kern, half_kern[-2::-1]])

stes

from sklearn.manifold import TSNE
from sklearn.decomposition import PCA
from collections import OrderedDict

def cluster(X, pca_components=100, min_explained_variance=0.5, tsne_dimensions=2, nb_centroids=[4, 8, 16],\
           X_=None, embedding=None):
    """ Simple K-Means Clustering Pipeline for high dimensional data
    
    Perform the following steps for robust clustering:
    - Zero mean, unit variance normalization over all feature dimensions

stes

git log --date=short --pretty=format:'"%an","%cd","%s"'

stes

/*
 * A simple learning vector quantization (LVQ) neural network used to map datasets
 * (right now, however, without a normalization of the input data)
 *
 * Copyright (c) stes 2011
 */
import java.io.IOException;
import java.util.ArrayList;
import java.util.Random;