konverner

from gensim.parsing.preprocessing import preprocess_string
from gensim.utils import any2unicode

def preprocess(text: str) -> list:
  text = any2unicode(text).lower()
  text = preprocess_string(text)
  return text

konverner

arr = [2, 2, 1, 1, 1, -1, -1, 0]
sorted([(i,arr.count(i)) for i in set(arr)], key=lambda x: x[1], reverse=True)[0][0]

konverner

import numpy as np


class Conv1d:
    def __init__(self, in_channels: int, out_channels: int, kernel_size: int, stride: int = 1):
        self.stride = stride
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.kernel = np.random.uniform(0, 1, size=(out_channels, in_channels, kernel_size))

konverner

import numpy as np


class Corr1d:
    def __init__(self, in_channels, out_channels, kernel_size, stride=1):
        self.stride = stride
        self.in_channels = in_channels
        self.out_channels = out_channels
        self.kernel_size = kernel_size
        self.kernel = np.random.uniform(0, 1, size=(out_channels, in_channels, kernel_size))

konverner

from transformers import BertTokenizer, BertModel
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained("bert-base-uncased")
text = "Replace me by any text you'd like."
encoded_input = tokenizer(text, return_tensors='pt')
output = model(**encoded_input)
embs = output.last_hidden_state

konverner

"""
A O
spokesman O
for O
Israel B-ORG
civil I-ORG
administration I-ORG

Samuel B-PER
Graham I-PER

konverner

import numpy as np
import matplotlib

def colorGrdient(c1: str, c2: str, n: int):
    """
    c1 : color FROM (e.g. '#FFCDD2')
    c2 : color TO (e.g. '#BBDEFB')
    """
    c1=np.array(matplotlib.colors.to_rgb(c1))
    c2=np.array(matplotlib.colors.to_rgb(c2))

konverner

# 12 space symbols to left and 2 numbers after a decimal point
print("{:>12.2f}  {:>12.2f}".format(1.32342, 1.9121))

konverner

def imshow_tensor_batch(batch):
    """
    batch: torch.tesnor [batch_size, c, h, w]
    """
    batch_size = batch.shape[0]
    fig, axis = plt.subplots(1, batch_size)

    if batch_size == 1:
        axis.imshow((batch[0] * 255).permute(2, 1, 0).permute(1, 0, 2).detach().cpu().numpy().astype(np.uint8))
    else:

konverner

import numpy as np
import torch
from PIL import Image


def img2tensor(img_path: str):
  """
  img_path : path to the image to convert
  ---
  t : normalized tensor [1, c, h, w]