def recognize(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
warnings.filterwarnings("ignore", category=DeprecationWarning)
probabilities = []
guesses = ['' for i in range(len(test_set.get_all_Xlengths()))]
# TODO implement the recognizer
# return probabilities, guesses
for i in range(len(test_set.get_all_sequences())):
current_sequence = test_set.get_item_sequences(i)
current_X, current_lengths = test_set.get_item_Xlengths(i)
best_word = None
p = {}
best_score = float('-inf')
for word in models:
model = models[word]
try:
score = model.score(current_X, current_lengths)
p[word] = score
except:
p[word] = 0
if score > best_score:
best_score = score
best_word = word
probabilities.append(p)
guesses[i] = best_word
return probabilities, guesses
def recognize(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
warnings.filterwarnings("ignore", category=DeprecationWarning)
# TODO implement the recognizer
probabilities = []
guesses = []
for word_id in range(0, len(test_set.get_all_Xlengths())):
#for word_id in range(0,2):
current_sequence = test_set.get_item_sequences(word_id)
current_length = test_set.get_item_Xlengths(word_id)
probs = {}
for word, model in models.items():
try:
probs[word] = model.score(current_sequence[0],
current_length[1])
except:
print('failed for word_id {} and word: {}'.format(
word_id, word))
probs[word] = float('-inf')
guess = max(probs, key=probs.get)
probabilities.append(probs)
guesses.append(guess)
return probabilities, guesses
def recognize(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
warnings.filterwarnings("ignore", category=DeprecationWarning)
probabilities = []
guesses = []
# TODO implement the recognizer
# return probabilities, guesses
for item in range(test_set.num_items):
sequences = test_set.get_item_sequences(item)
X,lengths = test_set.get_item_Xlengths(item)
logLs = dict()
for w,m in models.items():
try:
score = m.score(X,lengths)
except:
# print('failed {}'.format(w))
continue
else:
logLs[w] = score
guess_word = max(logLs, key=logLs.get)
probabilities.append(logLs)
guesses.append(guess_word)
return probabilities,guesses
def recognize(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
warnings.filterwarnings("ignore", category=DeprecationWarning)
probabilities = []
guesses = []
# TODO implement the recognizer
# return probabilities, guesses
for word_id in range(0, len(test_set.get_all_Xlengths())):
cur_seq = test_set.get_item_sequences(word_id)
cur_x, cur_len = test_set.get_item_Xlengths(word_id)
best_score = -float('INF')
best_guess = None
prob_dict = {}
for word, model in models.items():
score = -float('INF')
try:
score = model.score(cur_x, cur_len)
except:
pass
prob_dict[word] = score
if score >= best_score:
best_score = score
best_guess = word
probabilities.append(prob_dict)
guesses.append(best_guess)
return (probabilities, guesses)
def recognize(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
warnings.filterwarnings("ignore", category=DeprecationWarning)
probabilities = []
guesses = []
for item in range(test_set.num_items):
probs = {}
best_prob = float("-inf")
best_guess = ""
for model_name in models:
try:
score = models[model_name].score(
*test_set.get_item_sequences(item))
probs[model_name] = score
if score > best_prob:
best_prob = score
best_guess = model_name
except:
probs[model_name] = float("-inf")
probabilities.append(probs)
guesses.append(best_guess)
return (probabilities, guesses)
def recognize(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
warnings.filterwarnings("ignore", category=DeprecationWarning)
probabilities = []
guesses = []
for i in range(test_set.num_items):
word = test_set.wordlist[i]
seqs = test_set.get_item_sequences(i)
X = test_set.get_item_Xlengths(i)
p_hash = {}
best_score = -1000000000
best_word = None
for m_key in models:
try:
model = models[m_key]
logL = model.score(X[0], X[1])
p_hash[m_key] = logL
if logL > best_score:
best_score = logL
best_word = m_key
except ValueError:
continue
probabilities.append(p_hash)
guesses.append(best_word)
return (probabilities, guesses)
def recognize_ngram(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
# This import is necessary to be able recognize language model in arpa files
# could be easily installed using the following command :
# pip install arpa
import arpa
import itertools
warnings.filterwarnings("ignore", category=DeprecationWarning)
# TODO implement the recognizer
probabilities = []
guesses = []
probabilities_dict = {}
guesses_dict = {}
#load the language model
lm_models = arpa.loadf('lm3_sri.lm')
lm = lm_models[0] # ARPA files may contain several models.
#for word_id in range(0, len(test_set.get_all_Xlengths())):
# probabilities_dict[word_id] = 'None'
# guesses_dict[word_id] = 'None'
for video_index in test_set._load_sentence_word_indices():
word_ids = test_set._load_sentence_word_indices()[video_index]
video_probs = collections.OrderedDict()
for word_id in word_ids:
current_sequence = test_set.get_item_sequences(word_id)
current_length = test_set.get_item_Xlengths(word_id)
probs = {}
for word, model in models.items():
try:
probs[word] = model.score(current_sequence[0],
current_length[1])
except:
print('failed for word_id {} and word: {}'.format(
word_id, word))
probs[word] = float('-inf')
if len(word_ids) > 5:
top_words = sorted(probs, key=probs.get, reverse=True)[:3]
elif len(word_ids) == 5:
top_words = sorted(probs, key=probs.get, reverse=True)[:4]
elif len(word_ids) < 5:
top_words = sorted(probs, key=probs.get, reverse=True)[:6]
probabilities_dict[word_id] = probs
video_probs[word_id] = {x: probs[x] for x in top_words}
sentences = list(itertools.product(*video_probs.values()))
sentences_prob = []
for sentence_index in range(len(sentences)):
sentence = sentences[sentence_index]
visual_prob = 0
word_index = 0
for word_id in word_ids:
word_id_probs = video_probs[word_id]
visual_prob = visual_prob + word_id_probs[sentence[word_index]]
word_index = word_index + 1
sentence_string = ''
for word in sentence:
sentence_string = sentence_string + ' ' + word
try:
language_prob = lm.log_s(sentence_string.strip())
alpha = 1
beta = 25
sentence_prob = alpha * visual_prob + beta * language_prob
sentences_prob.append(sentence_prob)
print(language_prob)
except:
print('no language for sor sentence: {}',
sentence_string.strip())
sentences_prob.append(float('-inf'))
#find the sentence with the highest prob then extract word_ids
max_sentence = sentences[sentences_prob.index(max(sentences_prob))]
word_index = 0
for word_id in word_ids:
guesses_dict[word_id] = max_sentence[word_index]
word_index = word_index + 1
for key in sorted(guesses_dict):
probabilities.append(probabilities_dict[key])
guesses.append(guesses_dict[key])
return probabilities, guesses
def recognize(models: dict, test_set: SinglesData):
""" Recognize test word sequences from word models set
:param models: dict of trained models
{'SOMEWORD': GaussianHMM model object, 'SOMEOTHERWORD': GaussianHMM model object, ...}
:param test_set: SinglesData object
:return: (list, list) as probabilities, guesses
both lists are ordered by the test set word_id
probabilities is a list of dictionaries where each key a word and value is Log Liklihood
[{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
{SOMEWORD': LogLvalue, 'SOMEOTHERWORD' LogLvalue, ... },
]
guesses is a list of the best guess words ordered by the test set word_id
['WORDGUESS0', 'WORDGUESS1', 'WORDGUESS2',...]
"""
warnings.filterwarnings("ignore", category=DeprecationWarning)
probabilities = []
guesses = []
for s in range(0,test_set.num_items):
X,lengths = test_set.get_item_Xlengths(s)
sequences = test_set.get_item_sequences(s)
gword,blogL = None,float('-inf')
# word = test_set.df.iloc[s].word
probs_dict={}
for word,model in models.items():
probs_dict[word] = float('-inf')
try:
probs_dict[word] = model.score(X,lengths)
if probs_dict[word] > blogL:
gword = word
blogL = probs_dict[word]
except Exception as e:
# print(str(e))
pass
probabilities.append(probs_dict)
guesses.append(gword)
# guesses.append(word)
# probabilities.append(logL)
# except:
# pass
# def run_through_test_set(x):
# # print(x)
# pass
# # test_set.get_word_Xlengths(x.word)
# model = models[x.word]
# logL = model.score(x.get_item_sequences,x.get_item_Xlengths)
# probabilities.append(logL)
# guesses.append(x.word)
# video speaker start_frame end_frame word
# get_item_Xlengths
# get_item_sequences
# test_set.df.apply(run_through_test_set,axis=0)
# TODO implement the recognizer
return probabilities, guesses
raise NotImplementedError
