We’re rewarding the question askers & reputations are being recalculated! Read more.

Questions tagged [training]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
66
votes
2answers
46k views

Training an RNN with examples of different lengths in Keras

I am trying to get started learning about RNNs and I'm using Keras. I understand the basic premise of vanilla RNN and LSTM layers, but I'm having trouble understanding a certain technical point for ...
28
votes
4answers
24k views

Should a model be re-trained if new observations are available?

So, I have not been able to find any literature on this subject but it seems like something worth giving a thought: What are the best practices in model training and optimization if new observations ...
23
votes
4answers
8k views

Is it always better to use the whole dataset to train the final model?

A common technique after training, validating and testing the Machine Learning model of preference is to use the complete dataset, including the testing subset, to train a final model to deploy it on, ...
14
votes
1answer
7k views

What is the advantage of keeping batch size a power of 2?

While training models in machine learning, why is it sometimes advantageous to keep the batch size to a power of 2? I thought it would be best to use a size that is the largest fit in your GPU memory /...
14
votes
1answer
12k views

Is stratified sampling necessary (random forest, Python)?

I use Python to run a random forest model on my imbalanced dataset (the target variable was a binary class). When splitting the training and testing dataset, I struggled whether to used stratified ...
8
votes
3answers
657 views

What knowledge do I need in order to write a simple AI program to play a game?

I'm a B.Sc graduate. One of my courses was 'Introduction to Machine Learning', and I always wanted to do a personal project in this subject. I recently heard about different AI training to play games ...
8
votes
5answers
8k views

tool to label images for classification

Can anyone recommend a tool to quickly label several hundred images as an input for classification? I have ~500 microscopy images of cells. I want to assign categories such as 'healthy', 'dead', 'sick'...
7
votes
4answers
25k views

Train, test split of unbalanced dataset classification

I have a model that does binary classification. My dataset is highly unbalanced, so I thought that I should balance it by undersampling before I train the model. So balance the dataset and then ...
7
votes
1answer
6k views

How to train data by batch from disk?

I am working on a convolutional neural network for image classification. The training dataset is too large to be loaded on my computer memory (4gb), on top of that I also need to try some augmentation ...
7
votes
4answers
3k views

Build a tool for manually classifying training data images

I have a large number of images that I need to classify for training a clustering algorithm, and I would like to do so offline (the data is proprietary). Basically, I'd like to build a desktop survey ...
7
votes
2answers
2k views

How to fix class imbalance in training sample?

I was very recently asked in a job interview about solutions to fix an imbalance of classes in the training dataset. Let's focus on a binary classification case. I offered two solutions: oversampling ...
7
votes
1answer
1k views

CNN for phoneme recognition

I am currently studying this paper, in which CNN is applied for phoneme recognition using visual representation of log mel filter banks, and limited weight sharing scheme. The visualisation of log ...
6
votes
4answers
11k views

Tool to Label Images for Supervised Classification

I have a couple thousand photos of whales taken from drones and I'm planning to build a simple binary classifier to run on these and future images to see if they contain a whale. I'd like to label ...
6
votes
2answers
8k views

How to deal with large training data?

Currently, I use image files and transform them into a *.npy file(saved as a numpy array) as training data. At present this training data set is nearly 3GB. Now I have more image files, so the ...
6
votes
2answers
180 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 ...
5
votes
2answers
4k views

Cross validation when training neural network?

The standard setup when training a neural network seems to be to split the data into train and test sets, and keep running until the scores stop improving on the test set. Now, the problem: there is ...
5
votes
1answer
29 views

On design of the training set: conceptual question

I am curious to know how training data should be constructed so that it scales to examples that are not a part of the training data. For example, the problem that I am facing right now is in the ...
5
votes
3answers
95 views

Can you learn an algorithm from a trained model?

Are there any papers where an algorithm was entirely based on the results of a trained model? Let me explain. Suppose you want to come up with an algorithm that sorts three numbers $a,b,c$. I can ...
5
votes
2answers
3k views

Train object detection without annotated data/bounding boxes

From what I can see most object detection NNs (Fast(er) R-CNN, YOLO etc) are trained on data including ...
5
votes
1answer
1k views

What is the difference between tensorflow saved_model.pb and frozen_inference_graph.pb?

I've re-trained a model (following this tutorial) from the google's object detection zoo (ssd_inception_v2_coco) on a WIDER Faces Dataset and it seems to work if I use ...
5
votes
1answer
1k views

Batching in Recurrent Neural Networks (RNNs) when there is only a single instance per time step?

I have scoured the internet and books, but everything seems to use num_steps and batch_size or similar terms interchangeably and ...
5
votes
2answers
422 views

Type of images used to train a neural network

I am a newbie in neural network. Saw this article Object detection with deep learning and OpenCV. These three type of neural network are shortlisted in the article Faster R-CNNs You Only Look Once (...
5
votes
1answer
92 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 ...
4
votes
2answers
180 views

Training a model sample by sample

I'm training a Scikit model but it seems that in all examples, they call the fit method on the entire training set. What I want to do however is call it per sample (...
4
votes
1answer
12k views

Number of features of the model must match the input. Model n_features is `N` and input n_features is `X`.

I am new to data science and trying get some results. I'm applying Decision Tree Classifier. When my train and test datasets' size are not equal I get an error `...
4
votes
2answers
61 views

Will my neural network get lazy if I give it an “easy” feature?

Let's say I start with a standard conv net architecture capable of 99% accuracy on MNIST such as this one, but let's say I merge in an "easy" feature to the fully-connecter layer such as a vector of ...
4
votes
2answers
69 views

Can I use the training rows multiple times while training with different labels attached to it?

If I have a data set where for every text message, same but two labels are given. It could be that only one label has been filled. To visualise this scenario in real life, one may classify the accent ...
4
votes
1answer
5k views

Possible to use different learning rate for different neuron in Keras/Tensorflow?

The simplest example is to have faster/slower learning rates in the upper/lower layers of a network. I found this post on tensorflow. Is there a similar trick in Keras? Going one step further, can ...
4
votes
1answer
367 views

How to implement clipping the reward in DQN in keras

How to implement clipping the reward in DQN in keras? especially how to implement clipping the reward? Is this pseudo code correct: ...
4
votes
1answer
2k views

Train loss vs validation loss

I have a few basic questions about tracking losses during training. If I am using mini-batch training, should I validate after each batch update or after I have seen the entire dataset? What should ...
4
votes
1answer
219 views

Using GPS signal, determine is this person driving a cab

New York City provides tens of gigs of data of taxi routes all over the city. What I'd like to do, is use this data (or some other method), to come up with an algorithm that can take a persons GPS ...
4
votes
1answer
6k views

How to train an image dataset in TensorFlow? [closed]

As I am new to TensorFlow, I would like to do image recognition in TensorFlow using Python. For this Image Recognition I would like to train my own image dataset and test that dataset. Please answer ...
4
votes
4answers
179 views

Extract 2 pieces of information from a string - what to use?

First of all, I am a complete newbie in regard to data science and I am not asking for the complete solution but some guidance as to what I should read up to achieve my task (what algorithms, ...
3
votes
4answers
127 views

Weights not converging while cost function has converged in neural networks

My cost/loss function drops drastically and approaches 0, which looks a sign of convergence. But the weights are still changing in a visible way, a lot faster than the cost function. Should I ensure ...
3
votes
2answers
66 views

Why can we not split train test data with 0.01 as parameter or 99% training data

Most of the blogs mention about a good thumb rule to be 80-20 split for the train and test respectively. My special case is a time series dataset and it is for the stock prices, which IMO is very ...
3
votes
2answers
691 views

Accelerate deep learning model training on several GPUs

I have a deep learning model that can be trained in one GPU, however, is very slow. Is there a way to accelerate the training by parallelizing it across several GPUs? How would be the training process?...
3
votes
2answers
646 views

In the context of Deep Learning, what is training warmup steps

I found this term "training warmup steps" in some of the papers, what exactly does this term mean? Has it got anything to do with "learning rate"? If so, how does it affect?
3
votes
1answer
543 views

How to use live data to improve a existing model?

I am using logistic regression to train a model to predict 'click/non-click' using ['browser info', 'publisher info', , 'location', 'time', 'day']. I wanted to know the ways in which I can use the ...
3
votes
1answer
826 views

Evaluating Logistic Regression Model in Tensorflow

Following this tutorial, I have a doubt about the evaluation part in: ...
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 ...
3
votes
1answer
649 views

Gumbel Softmax vs Vanilla Softmax for GAN training

When training a GAN for text generation, i have seen many people feeding the gumbel-softmax from the generator output and feed into the discriminator. This is to bypass the problem of having to sample ...
3
votes
2answers
223 views

Why can't I choose my hyper-parameter in the training set?

Say I've divided the data into 3 parts: training, validation and test. I know for example, that in Neural Networks, the number of hidden layers is a hyper parameter. Why can't I train numerous NN ...
3
votes
1answer
230 views

Using already trained classifiers in Orange

I know that with Orange it is possible, using the 'Test & Score" widget, to test the performance of a classifier trained on a specific training set using a different test set ('Test on test data' ...
3
votes
1answer
541 views

Understanding the training phase of the tutorial “Using Keras and Deep Deterministic Policy Gradient to play TORCS” tutorial

I am trying to understand the training phase of the tutorial Using Keras and Deep Deterministic Policy Gradient to play TORCS (mirror, code) by Ben Lau published on October 11, 2016. The tutorial ...
3
votes
1answer
108 views

When forecasting time series, how does one incorporate the test data back into the model after training?

When you build a classification or regression model, you typically split the data into a train data set and a test data set. The test data is a randomly selected subset of the overall data. Once you ...
3
votes
1answer
250 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 ...
3
votes
1answer
611 views

“other” class in Image classification

In the MNIST dataset, you have 10 defined classes, one for each digit. But you don't have a "not a digit" class. It seems that most image classification datasets are the same. But in a business ...
3
votes
1answer
46 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 ...
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 ...