时间戳

首页 > 解决方案 > 如何在不反复重新加载的情况下测试神经网络模型

python - 如何在不反复重新加载的情况下测试神经网络模型

问题描述

我已经在 jupyter notebook 中编写了一个神经网络代码，一旦我运行该程序，我就可以在另一个单元格中进行测试，而无需再次运行整个模型。现在，如果我在其他一些文本编辑器中编写代码，我该如何做同样的事情。

from __future__ import division, print_function
import pandas as pd
import numpy as np
import re
import nltk
from nltk.corpus import stopwords

from numpy import array
from keras.preprocessing.text import one_hot
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.layers.core import Activation, Dropout, Dense
from keras.layers import Flatten
from keras.layers import GlobalMaxPooling1D
from keras.layers.embeddings import Embedding
from sklearn.model_selection import train_test_split
from keras.preprocessing.text import Tokenizer
import re
import string

data = pd.read_csv('totaldt.csv',encoding='UTF-8')
data.columns = ['Text', 'Label']
data.head()
data.Label.value_counts()
def remove_punct(text):
    text_nopunct = ''
    text_nopunct = re.sub('['+ string.punctuation +']', '', text)
    return text_nopunct
data['Text_Clean'] = data['Text'].apply(lambda x: remove_punct(x))
from nltk import word_tokenize
tokens = [word_tokenize(sen) for sen in data.Text_Clean]
def lower_token(tokens): 
    return [w.lower() for w in tokens]       
lower_tokens = [lower_token(token) for token in tokens]
from gensim import models
from keras.callbacks import ModelCheckpoint
from keras.layers import Dense, Dropout, Reshape, Flatten, concatenate, Input, Embedding
from keras.layers.recurrent import LSTM
from keras.models import Sequential
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.models import Model
from sklearn.model_selection import train_test_split
from gensim.models.wrappers import FastText
import numpy as np
import pandas as pd
import os
import collections
import re
import string
from gensim.models import Word2Vec
from gensim.models.wrappers import FastText

model = FastText.load_fasttext_format('cc.te.300.bin')
def get_average_word2vec(tokens_list, vector, generate_missing=False, k=300):
    if len(tokens_list)<1:
        return np.zeros(k)
    if generate_missing:
        vectorized = [vector[word] if word in vector else np.random.rand(k) for word in tokens_list]
    else:
        vectorized = [vector[word] if word in vector else np.zeros(k) for word in tokens_list]
    length = len(vectorized)
    summed = np.sum(vectorized, axis=0)
    averaged = np.divide(summed, length)
    return averaged



    x = Dense(128, activation='relu')(lstm)
    x = Dropout(0.2)(x)
    preds = Dense(labels_index, activation='sigmoid')(x)

    model = Model(sequence_input, preds)
    model.compile(loss='binary_crossentropy',
                  optimizer='adam',
                  metrics=['acc'])
    model.summary()
    return model

model = recurrent_nn(train_embedding_weights, MAX_SEQUENCE_LENGTH, len(train_word_index)+1, EMBEDDING_DIM, 
                len(list(label_names)))

num_epochs = 4
batch_size = 34
hist = model.fit(x_train, y_tr, epochs=num_epochs, validation_split=0.1, shuffle=True, batch_size=batch_size)
#predictions = model.predict(test_cnn_data, batch_size=10, verbose=1)
#labels = ["pos", "neg"]
#prediction_labels=[]
#for p in predictions:
#    prediction_labels.append(labels[np.argmax(p)])
#sum(data_test.Label==prediction_labels)/len(prediction_labels)

这是测试部分，我需要输入尽可能多的句子并测试模型而无需再次运行

s = list(input("enter sentence"))
test_sequence = tokenizer.texts_to_sequences(s)
test_cnn_dat = pad_sequences(test_sequence, maxlen=MAX_SEQUENCE_LENGTH)
prediction= model.predict(test_cnn_dat, batch_size=1  , verbose=1)
print(prediction)

标签： pythonmachine-learningneural-network

解决方案

为什么不在while True:代码的预测部分之前添加一个？这允许它连续循环并要求您输入下一个输入句子。

推荐阅读