Question

在我的网络中，验证指标是否从纪元固定为0.0000e + 00。

我环顾四周，很少有人遇到相同的问题，但是我无法按照相同的建议进行修复。

行被改组，并且标签已经转换为float32。这些是我在类似问题上发现的建议。你能告诉我我错了吗？

# data here https://www.kaggle.com/crowdflower/twitter-airline-sentiment
dtf_data = pd.read_csv(str_path + "Tweets.csv")

def clean_data(str_text): 
    lst_tokens = str_text.split()
    lst_tokens = [w for w in lst_tokens if not any(True for e in ["@", "#"] if e in w)]
    table = str.maketrans('', '', string.punctuation)
    lst_tokens = [c.translate(table) for c in lst_tokens]
    lst_tokens = [str_word for str_word in lst_tokens if str_word.isalpha()] # solo parole
    lst_stop_words = set(stopwords.words('english'))
    lst_tokens = [str_word for str_word in lst_tokens if not str_word in lst_stop_words and len(str_word) > 1]
    return " ".join(lst_tokens)

dtf_data["text_cleaned"] = dtf_data["text"].apply(lambda x: clean_data(x))
dtf_data["y"] = (dtf_data["airline_sentiment"] == "positive").astype(int)

X_train, X_test, y_train, y_test = train_test_split(dtf_data["text_cleaned"], dtf_data["y"], test_size=.25, random_state=0)

y_train = np.array(y_train, dtype = 'float32')
y_test = np.array(y_test, dtype = 'float32')

def build_corpus(dtf_in, str_col):
    corpus = []
    for sentence in dtf_in[str_col].iteritems():
        word_list = sentence[1].split()
        corpus.append(word_list)

    return corpus

corpus = build_corpus(dtf_data, 'text_cleaned')

model2vec = word2vec.Word2Vec(corpus, size=50)

tokenizer = Tokenizer()
tokenizer.fit_on_texts(corpus)

corpus_train, corpus_test = train_test_split(corpus, test_size=.25, random_state=0)
sequences_train = tokenizer.texts_to_sequences(corpus_train)
sequences_test = tokenizer.texts_to_sequences(corpus_test)

word_index = tokenizer.word_index
print('Found %s unique tokens' % len(word_index))

data_train = pad_sequences(sequences_train, maxlen=20)
data_test = pad_sequences(sequences_test, maxlen=20)
# pred = np.array(data.sentiment.values)
print('Shape of data tensor:', data_train.shape)
print('Shape of label tensor:', data_test.shape)

nb_words = min(200000, len(word_index))+1

embedding_matrix = np.zeros((nb_words, 50))
for word, i in word_index.items():
    if word in model2vec.wv.vocab:
        embedding_matrix[i] = model2vec.wv[word]

data_train, y_train = shuffle(data_train, y_train, random_state=0)
data_test, y_test = shuffle(data_test, y_test, random_state=0)

model_input = Input(shape=(20,))

model = Embedding(nb_words, 50, weights=[embedding_matrix],input_length=20,
        trainable=False)(model_input)
model = Dropout(0.25)(model)

model = LSTM(20, dropout=0.35,recurrent_dropout=0.35)(model)
model = BatchNormalization()(model)

model = Dropout(0.25)(model)
model = Dense(32)(model)
model = Activation('relu')(model)
model = BatchNormalization()(model)

model = Dense(1)(model)
out = Activation('sigmoid')(model)

opt = SGD(lr = 0.1, momentum = 0.9, nesterov=True)

model = Model(inputs=model_input, outputs=out)

model.compile(loss='binary_crossentropy',
              optimizer=opt,
              metrics=['accuracy'])

model.fit(data_train, y_train,
          batch_size=128,
          epochs=5,
          verbose=1,
          validation_data=[data_test, y_test])

Epoch 1/5
68/68 [==============================] - 1s 22ms/step - loss: 0.5084 - accuracy: 0.7975 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 2/5
68/68 [==============================] - 1s 19ms/step - loss: 0.5109 - accuracy: 0.7976 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 3/5
68/68 [==============================] - 1s 19ms/step - loss: 0.5095 - accuracy: 0.7976 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 4/5
68/68 [==============================] - 1s 19ms/step - loss: 0.5084 - accuracy: 0.7975 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00
Epoch 5/5
68/68 [==============================] - 1s 20ms/step - loss: 0.5083 - accuracy: 0.7973 - val_loss: 0.0000e+00 - val_accuracy: 0.0000e+00

此外，我发现验证中的指标实际上是不同的

accuracy_score(y_test, [c[0]>.3 for c in model.predict(data_test)])
0.7661122661122661

我真的不明白为什么会发生此问题。任何想法？谢谢

Answer 1

已修复。我刚刚将我的张量流降级到2.0。 pip install tensorflow == 2.0

keras val_loss：0.0000e + 00-val_accuracy：0.0000e + 00

1 个答案: