Episode #125 of the Stack Overflow podcast is here. We talk Tilde Club and mechanical keyboards. Listen now

Questions tagged [training]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
2
votes
1answer
139 views

Smart data split (train/eval) for Object Detection

I am looking for a smart way of splitting object detection data (images with labelled objects inside them) while taking into account the distribution of the objects themselves and not just the images. ...
0
votes
3answers
60 views

How to know when to stop trainning a deep network?

I've been training several auto encoders containing two GRUs as encoder and decoder during last year. It occurred to me that ...
0
votes
0answers
8 views

Looking for approaches to large scale NER train test split without overlaps

I would like to train test split a list of texts with the associated entities so there are no entities overlapping splits. Ensuring no overlaps is challenging: I currently achieve it with 2 groupby ...
5
votes
1answer
81 views

Why could an overfitted CNN model have a higher validation accuracy?

I am currently training a CNN model by using cifar10 images (50000 for training, another 10000 for validation). I plot training loss, validation loss and accuracy against training iteration: I am ...
2
votes
1answer
42 views

How to predict based on multiple samples?

I am relatively new to ML so I apologies in advance if my question shows lack of understating of the field. The problem A particular study course has a high drop-out rate and we want to reduce it. ...
3
votes
0answers
27 views

A Deep CNN model delivering better results with standardization, when compared with normalization

I developed a deep CNN model, based on the architecture discussed in this paper, to generate predictions for time series data. My training data is shown in the figure below: In order to train the ...
0
votes
1answer
27 views

Ideal score of a model on training and cross validation data

The question is little bit broad, but I could not find any concrete explanation anywhere, hence decided to ask the experts here. I have trained a classifier model for binary classification task. Now ...
0
votes
1answer
32 views

Potential problems with expanding training set

The problem is a binary classification one. My dataset contains users with activity over multiple days, where they all start with class 0 and can become class 1 after a certain activity (which is not ...
0
votes
1answer
35 views

What could make a set of the train data more predictive than the whole train data

I took a sample of my training data and balanced it and then trained my model. The results obtained are more accurate than using the whole set of train data (balanced or imbalanced). My question is: ...
0
votes
1answer
121 views

Do we have to split our dataset into training & testing when using ARIMA model?

I am working on a project where I predict the total quantities sold at the ITEM/DAY leve. As for the model, I decided to with an ARIMA model (I'm using R). For guidance, I decided to follow the two ...
3
votes
1answer
180 views

Does increasing kernel size in a CNN result in higher accuracy on the training set?

In a convolutional neural network, does increasing the size of kernel always result in better training set accuracy? For example, if I use 5x5 kernels in a CNN instead of 3x3 ones, will it always ...
0
votes
0answers
9 views

What research exists to help design training data sets where contamination due to privacy is an issue?

Suppose one is building a classifier that: takes as input the e-mail body text returns true or false if person X should be included in the address list To build this classifier we have historical ...
1
vote
1answer
19 views

Model biased towards low frequency data?

Generally model gets biased towards data_samples/target whose frequency is high in training data set. Is it possible during training that model gets biased towards low frequency training data set.
0
votes
0answers
13 views

The principle and understanding of adversarial training

In the paper《ADVERSARIAL TRAINING METHODS FOR SEMI-SUPERVISED TEXT CLASSIFICATION》and its related papers. The researcher apply the adversarial perturbation to word embeddings. Why do this methods ...
0
votes
1answer
70 views

Am I using GridSearch correctly or do I need to use all data for cross validation?

I'm working with a dataset that has 400 observations, 34 features and quite a few outliers, some of them extreme. Given the nature of my data, these need to be in the model. I started by doing a 75-...
1
vote
1answer
27 views

When to enhance a dataset of images with flips and rotations of the images?

I am a beginner in machine learning, so I'm sorry if my question is a bit trivial. Suppose I have a dataset of images and which I want to classify, say using a neural network. It makes sense to me to ...
0
votes
0answers
21 views

Difference between retraining on different parts of the data and training initially on larger data set

I have a large data set that doesn't fit in memory and would have to use something like Keras's model.fit_generator if I would like to train the model on all of the ...
0
votes
0answers
58 views

Keras functional API multi-input size error

I'm trying to define a multi-input model on a list of different arrays, all with the same shape (n_points, size, size, 1). I defined this model using the ...
0
votes
0answers
14 views

Using fastai library to get data from Google

So I was doing the fastai online course and I have a doubt in lecture 2 (link for the code given below). First of all, when we are using Google to generate the dataset, where have we ensured that the ...
2
votes
1answer
820 views

Training Keras model with multiple CSV files

I'm currently trying to train a Keras model on several large CSV files. I can fit one in memory, but not all combined. From my point of view, there are several ways to deal with this problem. I could ...
0
votes
3answers
99 views

Split the data between the Training Data and Test Data using sklearn

Work to do My job is to take the data and divide it between Training and Test using 30% of the data as Test where both should have the same ratio between positive and negative. CSV File ...
0
votes
0answers
33 views

Very Fast Training After First Epoch

I trained an InceptionV3 model using plant images. I used Keras library. When training was started, first epoch took 29s per step and then other steps took approximately 530ms per step. So that made ...
0
votes
0answers
37 views

Training loss and accuracy is oscillating and failed to converge

I was using AlexNet to do dog&cat classification tasks practice: https://github.com/stephen-v/tensorflow_alexnet_classify While I run the training, the loss oscillated while decreasing, which ...
2
votes
1answer
51 views

Training a model where each response in the observation data has a different known varience

I have a dataset where each response variable is the number of successes of N Bernoulli trials with N and p (the probability of success) being different for each observation. The goal is to train a ...
3
votes
1answer
39 views

What happens to the left over unpicked data in Random Forest

I believe in Random forest we pick random samples of training data with replacement. My question is there still is a possibility that we might leave some data out. What happens to that. Does it not ...
0
votes
1answer
29 views

Difference - Batch Training or training multiple times?

I have a question on batch learning of neural network. A neural network learns in batches and modifies weights in every iteration. Question: If I save checkpoints after a batch, and then load the ...
2
votes
1answer
22 views

Running multiple times of a model is for model randomness or data randomness?

When a paper report the average and std of a model on a dataset, it means that they have changed the split of training and test sets and run the model multiple times or they just run the model on ...
0
votes
2answers
28 views

Given a single discrete data set, how should I divide it into training data and test data?

I have a dataset in libSVM format consisting of 6000 entries, each with 5 indices, and each index has a binary value 1 or 2. Each of the 6000 entries has a label of ...
6
votes
2answers
178 views

Why real-world output of my classifier has similar label ratio to training data?

I trained a neural network on balanced dataset, and it has good accuracy ~85%. But in real world positives appear in about 10% of the cases or less. When I test network on set with real world ...
1
vote
1answer
71 views

Training data : forecasted or actual?

I am working on a time series prediction problem. I am using keras models for machine learning. For this prediction, weather variables are used as input. They can be of two types: forecasted and ...
2
votes
2answers
41 views

oversampling data with subclass

Oversampling of under-represented data is a way to combat class imbalance. For example, if we have a training data set with 100 data points of class A and 1000 data points of class B, we can over ...
0
votes
0answers
23 views

Speeding up actor critic training

I'm simulating a very simple system, recommendation system, and I am running an actor-critic model to predict what item I should recommend next. The agent is learning and is doing just fine. However, ...
2
votes
0answers
38 views

Replacing mean by median over batch-size to lessen the impact of outliers

In the case of training a Neural Network on a regression task. Assuming the data has a significant amount of outliers. Provided that the error needs to be RMS and not MAE. Can it be better (as in less ...
0
votes
0answers
34 views

Should images with multiple objects of the same class be used as training sample for multi-classes object detection models?

Let's say the model try to detect all the grapes on a branch of grapes. Can I use images of a grape branch with all the grapes labeled as a training sample? Will it affect the quality of the RPN ? Is ...
1
vote
2answers
136 views

Why can decision trees have a high amount of variance

I've heard that decision trees can have a high amount of variance, and that for a data set $D$ split into test/train the decision tree could be quite different depending on how the data was split. ...
0
votes
2answers
843 views

Over fitting in Transfer Learning with small dataset

I am using Transfer Learning to perform image classification. Base model used : Resnet50 using ImageNet dataset ...
3
votes
1answer
33 views

Validation data shall be in broken down into batches or not?

I am using fit_generator to train the model. The training dataset is being read from a generator function which gives data in a constant batch size. Now I want to ...
2
votes
1answer
572 views

Incrementally Train BERT with minimum QnA records - to get improved results

We are using Google BERT for Question and Answering. We have fine tuned BERT with SQUAD QnA release train data set (https://github.com/google-research/bert , https://rajpurkar.github.io/SQuAD-explorer/...
0
votes
1answer
61 views

review: gradient descent, epochs, validation in neural network training

These days, training data aren't put in gradient descent all at once. Rather, they are put in batch after batch. Gradient descent is run once for each batch of training data. When all batches are ...
1
vote
1answer
539 views

Using SMOTE for Synthetic Data generation to improve performance on unbalanced data

I presently have a dataset with 21392 samples, of which, 16948 belong to the majority class (class A) and the remaining 4444 belong to the minority class (class B). I am presently using SMOTE (...
1
vote
1answer
86 views

Accuracy and Loss in MLP

I am trying to explore models for predicting whether the a team will win or lose based on features about the team and their opponent. My training data is 15k samples with 760 numerical features. Each ...
0
votes
0answers
43 views

What to do when Kfold is not enough?

I have a dataset made of roughly 100 time-series and my final goal is to obtain a classification of each point (detection problem). To do so I have labels so I decided to use an XGB model to perform ...
0
votes
0answers
21 views

How to train non image data in batches from disk?

I am working on a project where I have 50 .npy files with each of shape (77156, 30, 50, 1) representing ...
1
vote
1answer
15 views

Change rate of cross validation data, after training

Say we have N of labeled data, and we need to take some part for the cross validation (we will skip test part for this case). We ...
0
votes
0answers
105 views

FaceNet training, tripletloss not decrease but accuracy increase then stuck,what are possible causes?

as you can see,triplet loss(pink curve in the left) do not change,but accuracy increase then stuck,what are possible reasons?
1
vote
1answer
442 views

Issues with training SSD on own dataset

I'm new to ML and trying to train a SSD300, with some Keras-Code github.com/pierluigiferrari/ssd_keras I found on github. For training I'm using an own (very small) dataset of objects that are not in ...
0
votes
1answer
45 views

Is “adding the predictions to the real data for new training and prediction” a good idea for LSTM?

Considering we have trained our model with a lot of data for "many-to-one" prediction. Then we like to forecast the future data of next 10 days. So we use last 60 of existent data and predict the ...
1
vote
0answers
31 views

Performance diagnostics in mxnet gluon (e.g. plotting training vs validation loss over time)?

Tensorflow has tensorboard, is there any recommended way to plot classification error/loss over time in mxnet?
2
votes
1answer
62 views

Is splitting the data set into train and validation applicable in unsupervised learning?

I am having a tough time implementing all the steps of setting up support vector machine (SVM) for unsupervised learning. My data set is labelled but for educational purposes I am learning ...
1
vote
1answer
72 views

Suggestions for labeling data for named entity recognition [closed]

Is it good to label the data based on sub category than parent category? For example: for drugs data ... label the drugs dose as drug_dose or label the drug dose as different type of dose like ...