弹道预测的编解码器 [英] Encoder-Decoder for Trajectory Prediction

问题描述

我需要使用编码器-解码器结构来预测2D轨迹.由于几乎所有可用的教程都与NLP有关(具有稀疏向量)，因此我不确定如何使解决方案适应连续数据.

I need to use encoder-decoder structure to predict 2D trajectories. As almost all available tutorials are related to NLP -with sparse vectors-, I couldn't be sure about how to adapt the solutions to a continuous data.

除了我对序列到序列模型的无知之外，embedding单词处理过程使我更加困惑.我有一个数据集，其中包含3,000,000个样本，每个样本具有x-y坐标(-1，1)和125个观测值，这意味着每个样本的形状为(125, 2).我以为我可以将其视为125个单词，其中已经嵌入了二维单词，但是此

In addition to my ignorance in seqence-to-sequence models, embedding process for words confused me more. I have a dataset that consists of 3,000,000 samples each having x-y coordinates (-1, 1) with 125 observations, which means the shape of each sample is (125, 2). I thought I could think of this as 125 words with 2 dimensional already embedded words, but the encoder and the decoder in this Keras Tutorial expect 3D arrays as (num_pairs, max_english_sentence_length, num_english_characters).

我怀疑是否需要使用此模型分别训练每个样本(125, 2)，就像Google的搜索栏只写一个字一样.

I doubt I need to train each sample (125, 2) separately with this model, as the way Google's search bar does with only one word written.

据我了解，编码器是many-to-one型模型，而解码器是one-to-many型模型.我需要获取一个内存状态c和一个隐藏状态h作为vectors(?).然后，我应该将这些向量用作解码器的输入，并提取与我确定的编码器输出一样多的(x，y)形状的预测.

As far as I understood, an encoder is many-to-one type model and a decoder is one-to-many type model. I need to get a memory state c and a hiddenstate h as vectors(?). Then I should use those vectors as input to decoder and extract predictions in the shape of (x,y) as many as I determine as encoder output.

如果有人能在我的数据集形状上提供一个编码器-解码器LSTM体系结构的示例，尤其是在编码器-解码器输入和输出所需的尺寸方面，尤其是在Keras模型上，我将非常感激.

I'd be so thankful if someone could give an example of an encoder-decoder LSTM architecture over the shape of my dataset, especially in terms of dimensions required for encoder-decoder inputs and outputs, particulary on Keras model if possible.

推荐答案

我假设您要与前125个时间步一起预测50个时间步(作为示例).我为您提供了时间序列的最基本的编码器-解码器结构，但是可以进行改进(使用 Luong Attention 例如).

I assume you want to forecast 50 time steps with the 125 previous ones (as an example). I give you the most basic Encoder-Decoder Structure for time Series but it can be improved (with Luong Attention for instance).

from tensorflow.keras import layers,models

input_timesteps=125
input_features=2
output_timesteps=50
output_features=2
units=100

#Input
encoder_inputs = layers.Input(shape=(input_timesteps,input_features))

#Encoder
encoder = layers.LSTM(units, return_state=True, return_sequences=False)
encoder_outputs, state_h, state_c = encoder(encoder_inputs) # because return_sequences=False => encoder_outputs=state_h

#Decoder
decoder = layers.RepeatVector(output_timesteps)(state_h)
decoder_lstm = layers.LSTM(units, return_sequences=True, return_state=False)
decoder = decoder_lstm(decoder, initial_state=[state_h, state_c])


#Output
out = layers.TimeDistributed(Dense(output_features))(decoder)

model = models.Model(encoder_inputs, out)

所以这里的核心思想是:

So the core idea here is :

1. 将时间序列编码为两种状态:state_h和state_c.检查此以了解LSTM单元的工作.
2. 重复state_h您要预测的时间步数
3. 使用LSTM对初始状态进行解码，该初始状态由编码器计算
4. 使用密集层来调整每个时间步所需的要素数量

1. Encode the time series into two states : state_h and state_c. Check this to understand the work of LSTM cells.
2. Repeat state_h the number of time steps you want to forecast
3. Decode using an LSTM with initial states calculated by the encoder
4. Use a Dense layer to shape the number of needed features for each time steps

我建议您测试我们的建筑并使用model.summary()和tf.keras.utils.plot_model(mode,show_shapes=True)对其进行可视化.对于摘要，它可以为您提供良好的表示形式:

I advise you to test our achtecture and visualize them with model.summary() and tf.keras.utils.plot_model(mode,show_shapes=True). It gives you good representations like, for the summary :

Layer (type)                    Output Shape         Param #     Connected to                     
==================================================================================================
input_5 (InputLayer)            [(None, 125, 2)]     0                                            
__________________________________________________________________________________________________
lstm_8 (LSTM)                   [(None, 100), (None, 41200       input_5[0][0]                    
__________________________________________________________________________________________________
repeat_vector_4 (RepeatVector)  (None, 50, 100)      0           lstm_8[0][1]                     
__________________________________________________________________________________________________
lstm_9 (LSTM)                   (None, 50, 100)      80400       repeat_vector_4[0][0]            
                                                                 lstm_8[0][1]                     
                                                                 lstm_8[0][2]                     
__________________________________________________________________________________________________
time_distributed_4 (TimeDistrib (None, 50, 2)        202         lstm_9[0][0]                     
==================================================================================================
Total params: 121,802
Trainable params: 121,802
Non-trainable params: 0
__________________________________________________________________________________________________

并绘制模型:

这篇关于弹道预测的编解码器的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！