Kulbear

import tensorflow as tf
import torch
import numpy as np

def gather_nd_torch(params, indices, batch_dim=1):
    """ A PyTorch porting of tensorflow.gather_nd
    This implementation can handle leading batch dimensions in params, see below for detailed explanation.

    The majority of this implementation is from Michael Jungo @ https://stackoverflow.com/a/61810047/6670143
    I just ported it compatible to leading batch dimension.

Kulbear

import torch
import tensorflow as tf

import time
import numpy as np

def gather_nd_torch(params, indices, batch_dim=1):
    """ A PyTorch porting of tensorflow.gather_nd
    This implementation can handle leading batch dimensions in params, see below for detailed explanation.

Kulbear

# Authors: Mathieu Blondel, Vlad Niculae
# License: BSD 3 clause

import numpy as np


def _gen_pairs(gen, max_iter, max_inner, random_state, verbose):
    rng = np.random.RandomState(random_state)

    # if tuple, interpret as randn

Kulbear

class FocalLoss(nn.Module):
    def __init__(self, gamma=2):
        super().__init__()
        self.gamma = gamma

    def forward(self, logit, target):
        target = target.float()
        max_val = (-logit).clamp(min=0)
        loss = logit - logit * target + max_val + \
               ((-max_val).exp() + (-logit - max_val).exp()).log()

Kulbear

def get_senet50(config):
    model = se_resnext50_32x4d(pretrained='imagenet')
#     print(model.last_linear)
#     print(model.dropout)
    model.layer0.conv1 = nn.Conv2d(config.channels, 64, 3, stride=2, padding=1, bias=False)
    model.avg_pool = nn.AdaptiveAvgPool2d(1)
    model.dropout = None
    model.last_linear = nn.Sequential(
        nn.BatchNorm1d(2048),
        nn.Dropout(0.5),

Kulbear

def multi_weighted_logloss(y_ohe, y_p):
    """
    @author olivier https://www.kaggle.com/ogrellier
    multi logloss for PLAsTiCC challenge
    """
    classes = [6, 15, 16, 42, 52, 53, 62, 64, 65, 67, 88, 90, 92, 95]
    class_weight = {6: 1, 15: 2, 16: 1, 42: 1, 52: 1, 53: 1, 62: 1, 64: 2, 65: 1, 67: 1, 88: 1, 90: 1, 92: 1, 95: 1}
    # Normalize rows and limit y_preds to 1e-15, 1-1e-15
    y_p = np.clip(a=y_p, a_min=1e-15, a_max=1-1e-15)
    # Transform to log

Kulbear

class Node:
    def __init__(self, val):
        self.val = val
        self.next = None


class MyLinkedList:
    def __init__(self):
        """
        Initialize your data structure here.

Kulbear

import tensorflow as tf
import numpy as np
import os

import zconfig
import utils

class DenoisingAutoencoder(object):

    """ Implementation of Denoising Autoencoders using TensorFlow.

Kulbear

from tensorflow.contrib.learn.python.learn.datasets.mnist import read_data_sets
import numpy as np
import timeit
import tensorflow as tf
from pprint import pformat

mnist = read_data_sets("data", one_hot=False)

NUM_CLASS = 10
STEP = 200

Kulbear

% Author: Ji Yang
%% Description
% A simple implementation of histogram equalization.
%

%% Note
% Histogram equalization is a technique for adjusting image intensities 
% to enhance contrast.
%