def home():
K.clear_session()
if request.method == 'POST':
# check if the post request has the file part
if 'file' not in request.files:
flash('No file part')
return redirect(request.url)
file = request.files['file']
if file.filename == '':
flash('No file selected for uploading')
return redirect(request.url)
if file and allowed_file(file.filename):
filename = secure_filename(file.filename)
filepath=os.path.join(UPLOAD_FOLDER, filename)
file.save(filepath)
flash('File successfully uploaded')
load_keras_model()
kq = hienthi_kq(filepath)
print(kq)
response = {}
response['path'] = 'static/images/'+filename
response['text'] = kq
return render_template('index.html', response=response)
else:
flash('Allowed file types are txt, pdf, png, jpg, jpeg, gif')
return redirect(request.url)
def __init__(self, model_filename, tokenizer, mle_model, bigramer,
max_len_questions, max_len_answers, strategy):
self._tokenizer = tokenizer
self._tokenizer_index_to_word = {
index: word
for (word, index) in self._tokenizer.word_index.items()
}
self._mle_model = mle_model
self._bigramer = bigramer
self._max_len_questions = max_len_questions
self._max_len_answers = max_len_answers
model_data = utils.load_keras_model(model_filename)
_, self._encoder_inputs, self._encoder_states, self._decoder_inputs, self._decoder_embedding, self._decoder_lstm, self._decoder_dense = model_data
self._enc_model, self._dec_model = utils.make_inference_models(
self._encoder_inputs, self._encoder_states, self._decoder_inputs,
self._decoder_embedding, self._decoder_lstm, self._decoder_dense)
self._strategy = strategy
def load_from_params(cls):
"""
Creates a chatbot from params.py.
Good for development, not for production.
:return: Chatbot initialized from params.py.
"""
import params
# load data
questions, answers = load_data(params.data_file_directory,
params.files, params.encoding)
bigramer = Bigramer(params.bigramer)
# prepare data manipulators
VOCAB_SIZE = params.vocab_size
tokenizer = create_tokenizer(questions + answers, VOCAB_SIZE,
params.unknown_token)
tokenized_questions, tokenized_answers = tokenize_q_a(
tokenizer, questions, answers)
# prepare data
prepared_data = prepare_data(tokenized_questions, tokenized_answers)
max_len_questions, max_len_answers, *_ = prepared_data
# mle_model
reversed_tokenizer_word_dict = {
index: word
for (word, index) in tokenizer.word_index.items()
}
mle_model = utils.fit_mle_model(tokenized_answers,
reversed_tokenizer_word_dict)
# load model
model_data = utils.load_keras_model(params.model)
_, encoder_inputs, encoder_states, decoder_inputs, decoder_embedding, decoder_lstm, decoder_dense = model_data
return cls(params.model, tokenizer, mle_model, bigramer,
max_len_questions, max_len_answers, params.strategy)
# This will be replaced with the test data when grading the assignment
data_path = '../data/data.npz'
x, y = load_data(data_path)
x_train, x_test, y_train, y_test = train_test_split(x,
y,
test_size=0.2,
random_state=0)
############################################################################
# EDITABLE SECTION OF THE SCRIPT: if you need to edit the script, do it here
############################################################################
# Load the Linear Regression model
linear_regressor = load_sklearn_model("./Linear_Regression.pickle")
# Load the Neural Network model
regressor = load_keras_model("./Neural_Network.pickle")
# Model from Task 1
# Number of data points
n = len(x)
# Initialize array
x3 = np.empty((0, n))
# Append x3
for x1, x2 in x:
temp = sin(x1) * x2
x3 = np.append(x3, temp)
# Build the X matrix
X = np.insert(x, 2, x3, axis=1)
# Make the predictions of the model
# Load the test CIFAR-10 data
(x_train, y_train), (x_test, y_test) = utils.load_cifar10()
# Pre-processing
# Normalize each pixel of each channel so that the range is [0, 1];
# each pixel is represented by an integer value in the 0-255 range.
x_train, x_test = x_train / 255., x_test / 255.
# Create one-hot encoding of the labels;
# pre-process targets in order to perform multi-class classification.
n_classes = 3
y_train = tf_utils.to_categorical(y_train, n_classes)
y_test = tf_utils.to_categorical(y_test, n_classes)
# Load the trained models
model_task2 = utils.load_keras_model('../deliverable/nn_task2.h5')
model_task1 = utils.load_keras_model('../deliverable/nn_task1.h5')
# Predict on the given samples
y_pred_task1 = model_task1.predict(x_test)
y_pred_task2 = model_task2.predict(x_test)
# prepare data for f1 score:
y_test_f1 = np.argmax(y_test, axis=1).astype(int)
y_pred_task1_f1 = np.argmax(y_pred_task1, axis=1).astype(int)
y_pred_task2_f1 = np.argmax(y_pred_task2, axis=1).astype(int)
""" Accuracy comparison between model T1 and model T2 """
# data check
assert y_test.shape == y_pred_task1.shape
def analyze_checkpoints():
questions, answers = load_data(params.data_file_directory, params.files,
None)
VOCAB_SIZE = 15001
tokenizer = create_tokenizer(questions + answers, VOCAB_SIZE, 'UNK')
# tokenizer = utils.load_and_unpickle("test_models/tokenizer")
tokenized_questions, tokenized_answers = tokenize_q_a(
tokenizer, questions, answers)
reversed_tokenizer_word_dict = {
index: text
for text, index in tokenizer.word_index.items()
}
mle_model = utils.fit_mle_model(tokenized_answers,
reversed_tokenizer_word_dict)
max_len_questions, max_len_answers, encoder_input_data, decoder_input_data, decoder_output_data = \
prepare_data(tokenized_questions, tokenized_answers)
checkpoints = [
params.dir_name + file for file in os.listdir(params.dir_name)
if file.endswith("hdf5")
]
print(f"{len(checkpoints)} checkpoints")
results = defaultdict(list)
model_score = []
# model evaluations section
questions, answers = load_data(params.data_file_directory,
params.test_files)
enc_in_data, dec_in_data, dec_out_data = generate_test_values(
questions[:1000], answers[:1000], tokenizer)
# generating answer and perplexity section
texts = questions[:5]
for checkpoint in checkpoints:
net_model, encoder_inputs, encoder_states, decoder_inputs, \
decoder_embedding, decoder_lstm, decoder_dense = utils.load_keras_model(checkpoint)
enc_model, dec_model = conversation.make_inference_models(
encoder_inputs, encoder_states, decoder_inputs, decoder_embedding,
decoder_lstm, decoder_dense)
score = net_model.evaluate([enc_in_data, dec_in_data], dec_out_data)
model_score.append(score)
print(score)
for text in texts:
print(text)
states_values = enc_model.predict(
conversation.str_to_tokens(tokenizer, text, max_len_questions))
empty_target_seq = np.zeros((1, 1))
empty_target_seq[0, 0] = tokenizer.word_index['start']
end_index = tokenizer.word_index['end']
predictions, _ = beam_search(states_values, empty_target_seq,
dec_model, end_index)
decoded_texts = []
for prediction in predictions:
decoded_text = ['start']
for word_index in prediction[1:]:
decoded_text.append(
reversed_tokenizer_word_dict.get(word_index, 'UNK'))
decoded_texts.append(decoded_text)
result = choose_best_fit(decoded_texts, mle_model)
results[text].append(result)
utils.pickle_and_save(results, params.perplexity_file)
utils.pickle_and_save(model_score, params.model_summary_file)
def test():
questions, answers = load_data("prepare_data/output_files",
"preprocessed_cornell", None)
VOCAB_SIZE = 15001
tokenizer = create_tokenizer(questions + answers, VOCAB_SIZE, 'UNK')
tokenized_questions, tokenized_answers = tokenize_q_a(
tokenizer, questions, answers)
reversed_tokenizer_word_dict = {
index: text
for text, index in tokenizer.word_index.items()
}
mle_model = utils.fit_mle_model(tokenized_answers,
reversed_tokenizer_word_dict)
max_len_questions, max_len_answers, encoder_input_data, decoder_input_data, decoder_output_data = \
prepare_data(tokenized_questions, tokenized_answers)
_, encoder_inputs, encoder_states, decoder_inputs, \
decoder_embedding, decoder_lstm, decoder_dense = utils.load_keras_model('cornell.hdf5')
enc_model, dec_model = conversation.make_inference_models(
encoder_inputs, encoder_states, decoder_inputs, decoder_embedding,
decoder_lstm, decoder_dense)
texts = [
'stop talking shit', 'it is peanut butter jelly time',
'Are we going to pass this lecture', 'Where are you from',
'do you like me', 'carrot', 'tell me your biggest secret',
'How are you', 'do you know me', 'what does fox say', 'i am happy',
'this is america', 'kill me', 'do not forget to brush your teeth'
]
for text in texts:
print(text)
states_values = enc_model.predict(
conversation.str_to_tokens(tokenizer, text, max_len_questions))
empty_target_seq = np.zeros((1, 1))
empty_target_seq[0, 0] = tokenizer.word_index['start']
end_index = tokenizer.word_index['end']
predictions, _ = beam_search(states_values, empty_target_seq,
dec_model, end_index)
decoded_texts = []
for prediction in predictions:
decoded_text = ['start']
for word_index in prediction[1:]:
decoded_text.append(
reversed_tokenizer_word_dict.get(word_index, 'UNK'))
decoded_texts.append(decoded_text)
print(utils.choose_best(decoded_texts, mle_model))
# for prediction in predictions:
# decoded_translation = ''
# for sampled_word_index in prediction[1:]:
# decoded_translation += ' {}'.format(reversed_tokenizer_word_dict[sampled_word_index])
# print(decoded_translation)
# print(predictions)
print()
print()
if __name__ == '__main__':
questions, answers = load_data(params.data_file_directory, params.files,
params.encoding)
VOCAB_SIZE = params.vocab_size
tokenizer = create_tokenizer(questions + answers, VOCAB_SIZE,
params.unknown_token)
tokenized_questions, tokenized_answers = tokenize_q_a(
tokenizer, questions, answers)
prepared_data = prepare_data(tokenized_questions, tokenized_answers)
max_len_questions, max_len_answers, encoder_input_data, decoder_input_data, decoder_output_data = prepared_data
model_data = utils.load_keras_model(params.model)
_, encoder_inputs, encoder_states, decoder_inputs, decoder_embedding, decoder_lstm, decoder_dense = model_data
enc_model, dec_model = make_inference_models(encoder_inputs,
encoder_states,
decoder_inputs,
decoder_embedding,
decoder_lstm, decoder_dense)
end_index = tokenizer.word_index['end']
for _ in range(10):
states_values = enc_model.predict(
str_to_tokens(tokenizer, input('Enter question : '),
max_len_questions))
empty_target_seq = np.zeros((1, 1))
empty_target_seq[0, 0] = tokenizer.word_index['start']
def predict(data):
model = load_keras_model()
predictions = model.predict_classes(data)
for i in range(5):
print('%s => %d (expected %d)' % (X[i].tolist(), predictions[i], y[i]))
import utils
from data import load_data, create_tokenizer, tokenize_q_a, prepare_data
if __name__ == '__main__':
questions, answers = load_data(params.data_file_directory, params.files)
VOCAB_SIZE = params.vocab_size
tokenizer = create_tokenizer(questions + answers, VOCAB_SIZE,
params.unknown_token)
tokenized_questions, tokenized_answers = tokenize_q_a(
tokenizer, questions, answers)
max_len_questions, max_len_answers, encoder_input_data, decoder_input_data, decoder_output_data = \
prepare_data(tokenized_questions, tokenized_answers)
# new_model = load_model('model_test.h5')
new_model = utils.load_keras_model('checkpoints/train2/cp-0004.hdf5')[0]
"""
Może nadpisać poprzednie checkpointy!!!!!!!! nie zacznie od checkpoint + 1 tylko od 1
"""
checkpoint_path = params.checkpoints_save_path
checkpoint = ModelCheckpoint(
checkpoint_path,
verbose=1,
save_weights_only=params.checkpoints_save_weights_only,
period=params.checkpoints_frequency)
callbacks_list = [checkpoint]
# fit the model
new_model.fit([encoder_input_data, decoder_input_data],
decoder_output_data,
callbacks=callbacks_list,
