def performBatchTest(weightsFilename): tokenizer, wordsToIndex = loadWordMapping() datasetDirectory = "aclImdb/test/" sequenceLength = 300 vecSpaceSize = 8 print("Evaluating model performance...") #Get the testing dataset reviews, ratings = readDataset(datasetDirectory, sequenceLength, vecSpaceSize) #Load the model and its weights model = loadModel(len(wordsToIndex) + 1, sequenceLength, vecSpaceSize) model.load_weights(weightsFilename) X = tokenizer.texts_to_sequences(reviews) X = pad_sequences(X, maxlen=sequenceLength, padding='post') loss, accuracy = model.evaluate(X, ratings) print("\tLoss: {}".format(loss)) print("\tAccuracy: {}".format(accuracy))
#!/usr/bin/env python import tensorflow as tf from tensorflow.keras import datasets, layers, models import matplotlib.pyplot as plt import dataset as ds import numpy as np import sys bin = np.arange(256) if not ds.check_folder(): ds.makeDataset(bin, type="s") x, y = ds.readDataset(bin, type="s") #train_images, train_labels,test_images,test_labels =ds.readDataset(bin,type="s") order = np.random.permutation(y.shape[0]) x = x[order, :, :, :] y = y[order, :] div = int(0.7 * y.shape[0]) train_images, test_images = x[0:div, :, :, :] / 1.0, x[div:, :, :, :] / 1.0 train_labels, test_labels = y[0:div, :], y[div:, :] """ if "-v" in sys.argv: class_names = ['Healthy', 'Parkinson'] plt.figure(figsize=(10,10)) for i in range(26): plt.subplot(5,6,i+1)
return paddedEncoding''' """def readGloveVectors(): wordToVecMap = {} loadedVectors = np.load("embeddings.npy", mmap_mode="r") with open("embeddings.vocab", "r", encoding="utf8") as fileRead: for index, word in enumerate(fileRead): wordToVecMap[word.strip()] = loadedVectors[index] return wordToVecMap""" datasetDirectory = "aclImdb/train/" sequenceLength = 300 vecSpaceSize = 8 reviews, ratings = readDataset(datasetDirectory, sequenceLength, vecSpaceSize) #Get embedded matrix representing vocabulary wordsToIndex, tokenizer = generateWordMapping(reviews) #Generate model and output summary model = loadModel(len(wordsToIndex) + 1, sequenceLength, vecSpaceSize) model.summary() #Define weights checkpoint filepath = "data/weights-{epoch:d}.hdf5" checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, mode='min') #Train the model X = tokenizer.texts_to_sequences(reviews) X = pad_sequences(X, maxlen=sequenceLength, padding='post') #print(encodedReviews.shape) model.fit(X,