elisehuard

# fixed version of http://altons.github.io/python/2012/12/01/converting-northing-and-easting-to-latitude-and-longitude/
# - filenames
# - data type (pyproj transform doesn't like pandas series) 
import os
import pandas as pd
import pyproj
import re

listfiles = os.listdir("codepo/Data/CSV")
pieces = []

kevinzakka

"""
Create train, valid, test iterators for CIFAR-10 [1].
Easily extended to MNIST, CIFAR-100 and Imagenet.

[1]: https://discuss.pytorch.org/t/feedback-on-pytorch-for-kaggle-competitions/2252/4
"""

import torch
import numpy as np

marcolivierarsenault

def lossless_triplet_loss(y_true, y_pred, N = 3, beta=N, epsilon=1e-8):
    """
    Implementation of the triplet loss function
    
    Arguments:
    y_true -- true labels, required when you define a loss in Keras, you don't need it in this function.
    y_pred -- python list containing three objects:
            anchor -- the encodings for the anchor data
            positive -- the encodings for the positive data (similar to anchor)
            negative -- the encodings for the negative data (different from anchor)

xuf12

def get_texts(path):
    rows_list = []   
    for idx, label in enumerate(CLASSES):
        print(f'working on {path}/{label}')
        for fname in (path/f'{label}').glob('*.*'):
            dict1 = {}
            text = fname.open('r').read()
            dict1.update({
                'text':text,
                'label':idx

talperetz

rxwei

See the official Differentiable Programming Manifesto instead.

crowsonkb

import torch
from torch import nn, optim


class Constraint(nn.Module):
    def __init__(self, fn, maximum, damping=1e-2):
        super().__init__()
        self.fn = fn
        self.register_buffer('maximum', torch.as_tensor(maximum))
        self.register_buffer('damping', torch.as_tensor(damping))

crowsonkb

"""Trains IMLE on the MNIST dataset."""

import torch
from torch import optim, nn
from torch.nn import functional as F
from torch.utils import data
from torchvision import datasets, transforms, utils
from torchvision.transforms import functional as TF
from tqdm import tqdm

crowsonkb

#!/usr/bin/env python3

import argparse
from collections import defaultdict
import csv
import math

import torch
from torch import nn, optim
from torch.nn import functional as F

pbaylies

# Modified StyleGAN2 Projector with CLIP, addl. losses, kmeans, etc.
# by Peter Baylies, 2021 -- @pbaylies on Twitter

# Copyright (c) 2021, NVIDIA CORPORATION.  All rights reserved.
#
# NVIDIA CORPORATION and its licensors retain all intellectual property
# and proprietary rights in and to this software, related documentation
# and any modifications thereto.  Any use, reproduction, disclosure or
# distribution of this software and related documentation without an express
# license agreement from NVIDIA CORPORATION is strictly prohibited.