classification

BERT get sentence level embedding after fine tuning

由 南楼画角 提交于 2020-04-13 06:34:08
问题 I came across this page 1) I would like to get sentence level embedding (embedding given by [CLS] token) after the fine tuning is done. How could I do it? 2) I also noticed that the code on that page takes a lot of time to return results on the test data. Why is that? When i trained the model it took less time as compared to when i tried to get test predictions. From the code on that page, I didnt use below blocks of the code test_InputExamples = test.apply(lambda x: bert.run_classifier

How to efficiently connect features to LSTM model?

由 ▼魔方 西西 提交于 2020-04-07 08:30:49
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

How to efficiently connect features to LSTM model?

由 核能气质少年 提交于 2020-04-07 08:30:14
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

How do I use knn model for new data in R?

由 烂漫一生 提交于 2020-03-25 19:27:52
问题 I've just written a knn model in R. However, I don't know how to use the output to predict new data. # split into train (treino) and test (teste) treino_index <- sample(seq_len(nrow(iris)), size = round(0.75*nrow(iris))) treino <- iris[treino_index, ] teste <- iris[-treino_index, ] # take a look at the sample head(treino) head(teste) # save specie from later treino_especie = treino$Species teste_especie = teste$Species # exclude species from train and test dataset treino = treino[-5] teste =

How to combine two LSTM layers with different input sizes in Keras?

由 纵然是瞬间 提交于 2020-03-23 10:24:10
问题 I have two types of input sequences where input1 contains 50 values and input2 contains 25 values. I tried to combine these two sequence types using a LSTM model in functional API. However since the length of my two input sequences are different, I am wondering whether what I am currently doing is the right way. My code is as follows: input1 = Input(shape=(50,1)) x1 = LSTM(100)(input1) input2 = Input(shape=(25,1)) x2 = LSTM(50)(input2) x = concatenate([x1,x2]) x = Dense(200)(x) output = Dense

Error in eval(predvars, data, env) : object 'Rm' not found

由 风格不统一 提交于 2020-03-19 04:01:08
问题 dataset = read.csv('dataset/housing.header.binary.txt') dataset1 = dataset[6] #higest positive correlation dataset2 = dataset[13] #lowest negative correlation dependentVal= dataset[14] #dependent value new_dataset = cbind(dataset1,dataset2, dependentVal) # new matrix #split dataset #install.packages('caTools') library(caTools) set.seed(123) #this is needed to garantee that every run will produce the same output split = sample.split(new_dataset, SplitRatio = 0.75) train_set = subset(new

Apple turicreate always return the same label

由 牧云@^-^@ 提交于 2020-03-01 05:12:38
问题 I'm test-driving turicreate, to resolve a classification issue, in which data consists of 10-uples (q,w,e,r,t,y,u,i,o,p,label), where 'q..p' is a sequence of characters (for now of 2 types), +,-, like this: q,w,e,r,t,y,u,i,o,p,label -,+,+,e,e,e,e,e,e,e,type2 +,+,e,e,e,e,e,e,e,e,type1 -,+,e,e,e,e,e,e,e,e,type2 'e' is just a padding character, so that vectors have a fixed lenght of 10. note:data is significantly tilted toward one label (90% of it), and the dataset is small, < 100 points. I use

Apple turicreate always return the same label

由 末鹿安然 提交于 2020-03-01 05:11:42
问题 I'm test-driving turicreate, to resolve a classification issue, in which data consists of 10-uples (q,w,e,r,t,y,u,i,o,p,label), where 'q..p' is a sequence of characters (for now of 2 types), +,-, like this: q,w,e,r,t,y,u,i,o,p,label -,+,+,e,e,e,e,e,e,e,type2 +,+,e,e,e,e,e,e,e,e,type1 -,+,e,e,e,e,e,e,e,e,type2 'e' is just a padding character, so that vectors have a fixed lenght of 10. note:data is significantly tilted toward one label (90% of it), and the dataset is small, < 100 points. I use

Apple turicreate always return the same label

由 Deadly 提交于 2020-03-01 05:11:10
问题 I'm test-driving turicreate, to resolve a classification issue, in which data consists of 10-uples (q,w,e,r,t,y,u,i,o,p,label), where 'q..p' is a sequence of characters (for now of 2 types), +,-, like this: q,w,e,r,t,y,u,i,o,p,label -,+,+,e,e,e,e,e,e,e,type2 +,+,e,e,e,e,e,e,e,e,type1 -,+,e,e,e,e,e,e,e,e,type2 'e' is just a padding character, so that vectors have a fixed lenght of 10. note:data is significantly tilted toward one label (90% of it), and the dataset is small, < 100 points. I use

Spark Decision Tree

由 烂漫一生 提交于 2020-02-29 14:39:35
决策树归纳是从有类标号的训练元组中学习决策树。决策树是一种类似于流程图的树结构，其中，每个内部节点表示在一个属性上的测试，每个分支代表该测试的一个输出，而每个树叶节点存放一个类标号，最顶层节点是跟节点。 一：算法逻辑 D：数据 Attribute_list:元组属性列表 Attribute_selection_method:选择可以按类最好地区分给定元组的属性 树从单个节点N开始，N代表D中的训练元组 如果D中的元组都为同一类，则节点N变为树叶，并用该类标记他。 否则继续调用attribute_selection_method确定如果分裂。目的是使得每个分支上的输出分区都尽可能“纯”。 对分裂准则的每个输出，由节点N生长一个分支，D中的元组据此进行划分。假设A是分裂属性，根据训练数据，由三种可能的情况： (1) A是离散的：在这种情况下，节点N的测试输出直接对应与A的已知值。对A的每个已知值创建一个分支。 (2)A是连续的：有两个可能的输出，分别对应与条件A<=split,A>split (3) A是离散的且必须产生二叉树：子集作为分裂条件 对于D的每个结果分区上的元组，算法使用同样的递归形成决策树。 终止条件 (1)分区D的所有元组都属于同一个类 (2)没有剩余属性可以用来进一步划分元组，使用多数表决。 返回决策树 二： 属性选择度量 属性选择度量是一种选择分裂准则
订阅 classification