bkj

function download_google_drive {
    SRC=$1
    DST=$2
    echo "$SRC -> $DST"
    
    curl -c /tmp/cookies "https://drive.google.com/uc?export=download&id=$SRC" > /tmp/intermezzo.html
    DL_LINK=$(cat /tmp/intermezzo.html |\
        grep -Po 'uc-download-link" [^>]* href="\K[^"]*' |\
        sed 's/\&/\&/g'
    )

bkj

import numpy as np
from numba import njit, parallel

@njit(parallel=True)
def cross_exchange(route1, route2, dist):
    best_savings = -np.inf
    for offset11 in prange(len(route1) - 3):
        i1, i2 = route1[offset11], route1[offset11 + 1]
        dii = dist[i1, i2]
        

bkj

import ee
import urllib
import numpy as np
from skimage import io
from PIL import Image
from zipfile import ZipFile
from matplotlib import pyplot as plt

ee.Initialize()

bkj

#!/usr/bin/env python

"""
  fast_argmax.py
"""

import numpy as np
from time import time
from numba import jit, prange

bkj

#!/usr/bin/env python

"""
    prep-CUB200.py
"""

import os
import shutil
import pandas as pd
from tqdm import tqdm

bkj

def rle2mask(rle, height, width):
    rle        = [int(xx) for xx in rle.split(' ')]
    offsets, runs = rle[0::2], rle[1::2]
    
    tmp = np.zeros(height * width, dtype=np.uint8)
    for offset, run in zip(offsets, runs):
        tmp[offset:offset + run] = 1
    
    return tmp.reshape(width, height).T

bkj

// Note: `@` refers to matrix-matrix or matrix-vector multiplication.  `*` refers to elementwise multiplication.

degrees = // vector s.t. degree[i] is the degree of the i'th node in graph G
D       = // diagonal matrix s.t. D[i, i] = degrees[i]
D_inv   = // diagonal matrix s.t. D_inv[i, i] = 1 / sqrt(degrees[i])
q       = // zero matrix of shape (max_iters, num_nodes)

grad = -alpha * D_inv @ s

while k < max_iters do

bkj

#!/usr/bin/env python

"""
    simple_batchnorm.py
"""

class SimpleBatchNorm1d(nn.Module):
    def __init__(self, dim, momentum=0.5, eps=1e-5, affine=True, track_running_stats=True):
        self.eps      = eps
        self.momentum = momentum

bkj

#!/usr/bin/env python

"""
    sgd_optimizers.py
    
    Pseudocode for optimizers
    
    These _should be_ identical to Pytorch implementation of the optimizers
"""

bkj

#!/usr/bin/env python

"""
    simple-random-nasbench.py
"""

import numpy as np
import pandas as pd
from tqdm import tqdm, trange
from matplotlib import pyplot as plt