lstm | 易学教程

What is the default activation function of cudnnlstm in tensorflow

阅读更多关于 What is the default activation function of cudnnlstm in tensorflow

问题 What's the default activation function of cudnnlstm in TensorFlow? How can I set an activation function such as relu ? Maybe it's just linear model? I read the document, but I did not find it. For example, the code is below: lstmcell=tf.contrib.cudnn_rnn.CudnnLSTM(1,encoder_size,direction="bidirectional") hq,_ =lstmcell(query) And I read the document of TensorFlow From this link. The function is below __init__( num_layers, num_units, input_mode=CUDNN_INPUT_LINEAR_MODE, direction=CUDNN_RNN

LSTM - predicting on a sliding window data

阅读更多关于 LSTM - predicting on a sliding window data

问题 My training data is an overlapping sliding window of users daily data. it's shape is (1470, 3, 256, 18) : 1470 batches of 3 days of data, each day has 256 samples of 18 features each. My targets shape is (1470,) : a label value for each batch. I want to train an LSTM to predict a [3 days batch] -> [one target] The 256 day samples is padded with -10 for days that were missing 256 sampels I've written the following code to build the model: from tensorflow.keras.models import Sequential from

How to handle LSTMs with many features in python?

阅读更多关于 How to handle LSTMs with many features in python?

问题 I have a binary classification problem. I use the following keras model to do my classification. input1 = Input(shape=(25,6)) x1 = LSTM(200)(input1) input2 = Input(shape=(24,6)) x2 = LSTM(200)(input2) input3 = Input(shape=(21,6)) x3 = LSTM(200)(input3) input4 = Input(shape=(20,6)) x4 = LSTM(200)(input4) x = concatenate([x1,x2,x3,x4]) x = Dropout(0.2)(x) x = Dense(200)(x) x = Dropout(0.2)(x) output = Dense(1, activation='sigmoid')(x) However, the results I get is extremely bad. I thought the

LSTM to classify long time series sequences

阅读更多关于 LSTM to classify long time series sequences

问题 I am trying to train LSTM model to classify long time series sequences with 700 time steps. Sample time series belonging to class 1 Sample time series belonging to class 2 Model model = Sequential() model.add(LSTM(100, input_shape=(700,1), return_sequences=False)) model.add(Dense(1, activation='sigmoid')) sgd = SGD(lr=0.001, decay=1e-6, momentum=0.9, nesterov=True) model.compile(loss='binary_crossentropy', optimizer=sgd, metrics=['accuracy']) history = model.fit(xtrain, y, batch_size = 10,

LSTM to classify long time series sequences

阅读更多关于 LSTM to classify long time series sequences

LSTM having a systematic offset between predictions and ground truth

阅读更多关于 LSTM having a systematic offset between predictions and ground truth

问题 Currently i think i'm experiencing a systematic offset in a LSTM model, between the predictions and the ground truth values. What's the best approach to continue further from now on? The model architecture, along with the predictions & ground truth values are shown below. This is a regression problem where the historical data of the target plus 5 other correlated features X are used to predict the target y . Currently the input sequence n_input is of length 256, where the output sequence n

LSTM having a systematic offset between predictions and ground truth

阅读更多关于 LSTM having a systematic offset between predictions and ground truth

Keras学习手册(三),开始使用 Keras 函数式 API

阅读更多关于 Keras学习手册(三),开始使用 Keras 函数式 API

感谢作者分享- http://bjbsair.com/2020-04-07/tech-info/30658.html Keras 函数式 API 是定义复杂模型（如多输出模型、有向无环图，或具有共享层的模型）的方法。这部分文档假设你已经对 Sequential 顺序模型比较熟悉。让我们先从一些简单的例子开始。例一：全连接网络 Sequential 模型可能是实现这种网络的一个更好选择，但这个例子能够帮助我们进行一些简单的理解。网络层的实例是可调用的，它以张量为参数，并且返回一个张量输入和输出均为张量，它们都可以用来定义一个模型（Model）这样的模型同 Keras 的 Sequential 模型一样，都可以被训练 from keras.layers import Input, Dense from keras.models import Model # 这部分返回一个张量 inputs = Input(shape=(784,)) # 层的实例是可调用的，它以张量为参数，并且返回一个张量 x = Dense(64, activation='relu')(inputs) x = Dense(64, activation='relu')(x) predictions = Dense(10, activation='softmax')(x) #

ValueError: Input 0 is incompatible with layer lstm_13: expected ndim=3, found ndim=4

阅读更多关于 ValueError: Input 0 is incompatible with layer lstm_13: expected ndim=3, found ndim=4

问题 I am trying for multi-class classification and here are the details of my training input and output: train_input.shape= (1, 95000, 360) (95000 length input array with each element being an array of 360 length) train_output.shape = (1, 95000, 22) (22 Classes are there) model = Sequential() model.add(LSTM(22, input_shape=(1, 95000,360))) model.add(Dense(22, activation='softmax')) model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) print(model.summary()) model

How to efficiently connect features to LSTM model?

阅读更多关于 How to efficiently connect features to LSTM model?

问题 I have the following ‍LSTM model where I input my time-series to the LSTM layer. The other input (which is the dense layer) contains the 10 features I manually extracted from the time-series. input1 = Input(shape=(26,6)) x1 = LSTM(100)(input1) input2 = Input(shape=(10,1)) x2 = Dense(50)(input2) x = concatenate([x1,x2]) x = Dense(200)(x) output = Dense(1, activation='sigmoid')(x) model = Model(inputs=[input1,input2], outputs=output) I thought that the performance of my model will hugely