EdisonLeeeee

EdisonLeeeee

import os
import sys
import functools
import logging
from termcolor import colored
from typing import Optional

__all__ = ["setup_logger", "get_logger"]

EdisonLeeeee

import numpy as np
from collections import namedtuple

topk_namedtuple = namedtuple('topk_namedtuple', ['values', 'indices'])


def topk(array: np.ndarray, k: int, largest: bool = True) -> topk_namedtuple:
    """Returns the k largest/smallest elements and corresponding indices 
    from an array-like input.

EdisonLeeeee

People

:bowtie:	😄 :smile:	😆 :laughing:
😊 :blush:	😃 :smiley:	☺️ :relaxed:
😏 :smirk:	😍 :heart_eyes:	😘 :kissing_heart:
😚 :kissing_closed_eyes:	😳 :flushed:	😌 :relieved:
😆 :satisfied:	😁 :grin:	😉 :wink:
😜 :stuck_out_tongue_winking_eye:	😝 :stuck_out_tongue_closed_eyes:	😀 :grinning:
😗 :kissing:	😙 :kissing_smiling_eyes:	😛 :stuck_out_tongue:

EdisonLeeeee

import numpy as np
import torch
import tensorflow as tf
import numpy as np
import torch
import tensorflow as tf

# Numpy
np.random.seed(42)
x = np.random.randn(10, 10)

EdisonLeeeee

def f1_loss(y_true:torch.Tensor, y_pred:torch.Tensor, is_training=False) -> torch.Tensor:
    '''Calculate F1 score. Can work with gpu tensors
    
    The original implmentation is written by Michal Haltuf on Kaggle.
    
    Returns
    -------
    torch.Tensor
        `ndim` == 1. 0 <= val <= 1
    

EdisonLeeeee

import json
import requests

def translate(word):
    url = 'http://fanyi.youdao.com/translate?smartresult=dict&smartresult=rule&smartresult=ugc&sessionFrom=null'
    key = {
        'type': "AUTO",
        'i': word,
        "doctype": "json",
        "version": "2.1",

EdisonLeeeee

import torch
import tensorflow as tf

########## PyTorch Version 1 ################
x = torch.randn(5, 6)
norm_th = x/torch.norm(x, p=2, dim=1, keepdim=True)
norm_th[torch.isnan(norm_th)] = 0 # to avoid nan

########## PyTorch Version 2 ################
norm_th = torch.nn.functional.normalize(x, p=2, dim=1)

EdisonLeeeee

import torch
import tensorflow as tf

def softmax_cross_entropy_with_logits(labels, logits, dim=-1):
    return (-labels * F.log_softmax(logits, dim=dim)).sum(dim=dim)    


logits = [[4.0, 2.0, 1.0], [0.0, 5.0, 1.0]]
labels = [[1.0, 0.0, 0.0], [0.0, 0.8, 0.2]]