Machine/Deep Learning

ML_DL_DS.md

Torch

Describe Torch Tensors

def describe(x):     
  print("Type: {}".format(x.type()))     
  print("Shape/size: {}".format(x.shape))     
  print("Values: \n{}".format(x))

GPU vs CPU Models

C++

torch::DeviceType device_type;
if (torch::cuda::is_available()) {
    std::cout << "Cuda available, running on GPU" << "\n";
    device_type = torch::kCUDA;
} else {
    std::cout << "Cuda NOT available, running on CPU" << "\n";
    device_type = torch::kCPU;
}
torch::Device device(device_type);
module->to(torch::Device(device));

Python

if torch.cuda.is_available(): 
 dev = "cuda:0" 
else: 
 dev = "cpu" 
device = torch.device(dev)
model.to(device)

NLP

N-gram

def n_grams(text, n):     
   '''     takes tokens or text, returns a list of ngrams     '''
   return [text[i:i+n] for i in range(len(text)-n+1)]

Tokenization

Sentence Tokenization

from nltk.tokenize import sent_tokenize

data = "Sentence one. Sentence two."
sent_tokenize(data)

Word Tokenization

from nltk.tokenize import word_tokenize

data = "word one two three, four."
word_tokenize(data)

Lemmatization

• Add lemma for Turkish