thomwolf

class DeepMojiDataset(Dataset):
    """ A simple Dataset class.
    # Arguments:
        X_in: Inputs of the given dataset.
        y_in: Outputs of the given dataset.
    
    # __getitem__ output:
        (torch.LongTensor, torch.LongTensor)
    """
    def __init__(self, X_in, y_in):

thomwolf

class DeepMojiBatchSampler(object):
    """A Batch sampler that enables larger epochs on small datasets and
        has upsampling functionality.
    # Arguments:
        y_in: Labels of the dataset.
        batch_size: Batch size.
        epoch_size: Number of samples in an epoch.
        upsample: Whether upsampling should be done. This flag should only be
            set on binary class problems.
        seed: Random number generator seed.

thomwolf

class Model(nn.Module):
  def __init__(self, vocab_size, embed_dim, H1, H2, H3, pairs_in, single_in, drop=0.5):
    super(Model, self).__init__()
    self.embed = nn.Embedding(vocab_size, embedding_dim)
    self.drop = nn.Dropout(drop)
    self.pairs = nn.Sequential(nn.Linear(pairs_in, H1), nn.ReLU(), nn.Dropout(drop),
                               nn.Linear(H1, H2), nn.ReLU(), nn.Dropout(drop),
                               nn.Linear(H2, H3), nn.ReLU(), nn.Dropout(drop),
                               nn.Linear(H3, 1),
                               nn.Linear(1, 1))

thomwolf

def get_params(module, memo=None, pointers=None):
    """ Returns an iterator over PyTorch module parameters that allows to update parameters
        (and not only the data).
    ! Side effect: update shared parameters to point to the first yield instance
        (i.e. you can update shared parameters and keep them shared)
    Yields:
        (Module, string, Parameter): Tuple containing the parameter's module, name and pointer
    """
    if memo is None:
        memo = set()

thomwolf

class Rectangle:
    def __init__(self, w, h):
        self.w = w
        self.h = h
    def area(self):
        return self.w * self.h

thomwolf

cdef struct Rectangle:
    float w
    float h

thomwolf

def slow_loop(doc_list, word, tag):
    n_out = 0
    for doc in doc_list:
        for tok in doc:
            if tok.lower_ == word and tok.tag_ == tag:
                n_out += 1
    return n_out

def main_nlp_slow(doc_list):
    n_out = slow_loop(doc_list, 'run', 'NN')

thomwolf

import urllib.request
import spacy

with urllib.request.urlopen('https://raw.githubusercontent.com/pytorch/examples/master/word_language_model/data/wikitext-2/valid.txt') as response:
   text = response.read()
nlp = spacy.load('en')
doc_list = list(nlp(text[:800000].decode('utf8')) for i in range(10))

thomwolf

from random import random

class Rectangle:
    def __init__(self, w, h):
        self.w = w
        self.h = h
    def area(self):
        return self.w * self.h

def check_rectangles(rectangles, threshold):

thomwolf

%%cython -+
import numpy # Sometime we have a fail to import numpy compilation error if we don't import numpy
from cymem.cymem cimport Pool
from spacy.tokens.doc cimport Doc
from spacy.typedefs cimport hash_t
from spacy.structs cimport TokenC

cdef struct DocElement:
    TokenC* c
    int length