Exercicio Deep learning, Exercícios de Probabilidades e Processos Estocásticos

Baixe Exercicio Deep learning e outras Exercícios em PDF para Probabilidades e Processos Estocásticos, somente na Docsity!

25/11/2019 LISTA-23.ipynb - Colaboratory import keras from keras.layers import Embedding, ConviD, MaxPooling1D, GlobalMaxPooling1D, Dense from keras.models import Sequential from keras.datasets import imdb from keras.preprocessing import sequence max features = 2000 max len = 500 (x train, y train), (x test, y test) = imdb.load data(num words=max features) x train = sequence.pad sequences(x train, maxlen=max len) x test = sequence.pad sequences(x test, maxlen=max len) [> Downloading data from https://s3.amazonaws.com/text-datasets/imdb.npz 17465344/17464789 [=: - Is Qus/step model = Sequential() model.add(Embedding(max features, 128,input length=max len,name='embed')) model.add(ConviD(32, 7, activation='relu')) model. add(MaxPooling1D(5)) model.add(ConviD(32, 7, activation='relu')) model. add(GlobalMaxPoolingiD()) model.add(Dense(1)) model.summary() [> WARNING:tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow | WARNING: tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow | WARNING: tensorflow:From /usr/local/lib/python3.6/dist-packages/keras/backend/tensorflow | Model: "sequential 2" Layer (type) Output Shape Param & embed (Embedding) (None, 500, 128) 256000 convid 1 (ConviD) (None, 494, 32) 28704 max poolingld 1 (MaxPooling1 (None, 98, 32) o convid 2 (ConviD) (None, 92, 32) 7200 global max poolingid 1 (Glob (None, 32) 8 dense 1 (Dense) (None, 1) 33 Total params: 291,937 Trainable params: 291,937 Non-trainable params: O model.compile(optimizer='rmsprop', https:/lcolab.research.google.com/drive/152VNvAOBMPOhwozT7BVyPjswRoQwDzVFifscrolTo=gvJg7 SlaeP62&printMode=true 112