11
votes
Accepted
Effect of batch size and number of GPUs on model accuracy
This should make a difference, but how big is the difference heavily depends on your task. However, generally speaking, a smaller batch size will have a lower speed if counted in sample/minutes, but ...
- 1,745
6
votes
Should I continue training if the neural network attains 100% training accuracy?
First of all, as mentioned by @Neil Slater in the comment - you need to have three splits into the train, validation and test set.
One sometimes disregards the difference between validation and test ...
- 2,724
6
votes
Should I choose a model with the smallest loss or highest accuracy?
You should choose the model A. The loss is just a differentiable proxy for accuracy.
That said, the situation should be examined in more detail. If the higher loss is due to the data term, examine ...
- 499
5
votes
Accepted
Why is my test error lower than the training error?
You use dropout during traing to reduce overfitting, but this reduces the training accuracy. The dropout will not be used during testing, therefore the accuracy will be higher.
That's normal behavior ...
- 1,684
5
votes
Accepted
Should I choose a model with the smallest loss or highest accuracy?
You should note that both your results are consistent with a "true" probability of 87% accuracy, and your measurement of a difference between these models is not statistically significant. With an 87% ...
- 32.9k
4
votes
Why is my test error lower than the training error?
I will just add to all the good answers already here.
Like I said on my comment earlier, this is not a bad this(provided you have a split your data correctly).
Other reasons could be:
High ...
- 840
4
votes
Accepted
Why is there more than one way of calculating the accuracy?
In machine learning, the accuracy is usually defined as the number of correct predictions divided by the total number of predictions. The correct predictions are the true positives ($\mathrm {TP}$) ...
- 41.1k
3
votes
Accuracy dropped when I ran the program the second time
It is common during the training of Neural Networks for accuracy to improve for a while and then get worse -- in general, This is caused by over-fitting. It's also fairly common for the Neural Network ...
- 1,114
3
votes
Accepted
What are possible ways to combat overfitting or improve the test accuracy in my case?
There are a few issues you need to address first.
Normalise your data. You should try and keep your values for each input in a good range, otherwise you're never going to train anything useful. A ...
- 1,406
3
votes
Effect of batch size and number of GPUs on model accuracy
No. Different batch sizes mean different gradients (check stochastic gradient descent concept you will get how loss calculated) are calculated in each step, and thus the gradient descent will likely ...
- 224
3
votes
Accepted
Can we calculate mean recall and precision
For the precision metric for example you have:
$$
Precision = \frac{TP}{TP+FP},
$$
with TP = True Positive and FP = False Positive.
Imagine you have the following values:
Image 1: $TP = 2, FP = 3$
...
- 797
3
votes
Why don't people always use TensorFlow Lite, if it doesn't decrease the accuracy of the models?
This partly answer to question 1.
There is no general rule concerning accuracy or size of the model. It depends on the training data and the processed data.
The lightest is your model compared to the ...
- 241
3
votes
Accepted
Should I choose the model with highest validation accuracy or the model with highest mean of training and validation accuracy?
Neither of the above mentioned methods could be a potent indicator of the performance of a model.
A simple way to train the model just enough so that it generalizes well on unknown datasets would be ...
- 370
3
votes
Accepted
Which preprocessing is the correct way to forecast time-series data using LSTM?
A standard method for pre-processing time series data for neural network architectures, such as an LSTM, is to normalize the data. Good tutorials will include this step. There are several variations ...
- 1,937
2
votes
How to express accuracy of a regression ANN that uses MSE loss function?
You can not use error to reliably measure accuracy. Error is best used as a measure of how fast the model is currently learning.
As an example, using different loss functions (cross entorpy vs MSE) ...
- 1,406
2
votes
Accepted
What does top N accuracy mean?
It is explained in this CrossValidated post.
Top1 accuracy means the best guess (class with highest probability) is the correct result 58.9% of the time, while top5 accuracy means the correct result ...
- 890
2
votes
Accepted
Could I just choose the other (non-predicted) class when the accuracy is low?
The short answer is no, you shouldn't do that.
There is a "distribution shift" thing when you have different x-y relation on the validation set then on the train set. The distribution shift ...
- 684
2
votes
Accepted
Where can I find authentic references on "categorical cross entropy" and "categorical accuracy metric"?
Categorical just means that we will conduct multiclass classification. The output of the classifier is a binary vector. Each entry $x_i$ in the binary vector is a prediction whether or not the input ...
- 562
2
votes
Accepted
Is it possible training accuracy never changed while training?
What happened with your model is that it suffered from a Neural Network collapse. This means that your network didn't learn to generalize with the data or that the local minimum found in the gradient ...
- 598
1
vote
Test accuracy decreases during my train process
This looks like overfitting. You can try stop training earlier by using a validation dataset to prevent this, or you can try other regularization effects such as weight-decay, dropout etc.
- 1,020
1
vote
Is it ok to have an accuracy of 65% and a sensitivity of 90% with Naive Bayes for sentiment analysis?
I could get perfect sensitivity for positive sentiment if I always predict positive sentiment, but my accuracy could be 50%ish depending on the distribution of positive sentiment in the data. The ...
- 249
1
vote
Accepted
Is it a good practice to pad signal before feature extraction?
Padding is a common practice both in image-processing (typically via CNNs) and in sequence-processing tasks (RNNs, Transformers).
For CNNs all the standard convolutional layers - Conv1D, Conv2D and ...
- 2,554
1
vote
Do larger numbers of hidden layers have a bigger effect on a classification model's accuracy?
In your case the most probable explanation would be the case of overfitting. The model with too many hidden layers have lots of parameters. By means of all these parameters the model is remembering ...
- 126
1
vote
Accepted
Accuracy Not Going Above 30%
You have two questions in one.
Is it maxpool that ruins the model?
I would say no, the maxpool is a standard operation for convolution networks, it down-samples the intermediate representation to ...
- 684
1
vote
Is it possible that the model is overfitting when the training and validation accuracy increase?
I'll try to answer on more general questions
Is it ok that model performs better on validation, then on train?
It's certainly fine if you use techniques like dropout or data augmentation and the ...
- 684
1
vote
Why does the accuracy drop while the loss decrease, as the number of epochs increases?
Decrease of loss does not essentially lead to increase of accuracy (most of the time it happens but sometime it may not happen). To know why, you can have a look at this question. The network cares ...
- 420
1
vote
Accepted
Choosing Data Augmentation smartly for different application
In fact, choosing smartly the values of the image augmentation can help the performance of your system. Where I work we developed an object detector for cars. We had the following image augmentation ...
- 1,148
1
vote
Should I choose the model with highest validation accuracy or the model with highest mean of training and validation accuracy?
The training accuracy tells you nothing about how good it is on other data than the ones it learned on, it could be better on this data because it memorized this examples.
On the other hand the ...
- 434
1
vote
Accepted
Given the precision and recall of this model, what can I say about it?
The second model has the same precision, but worse recall, than model 1. Therefore we would rather have model 1 than model 2.
The third model has worse recall than model 1, and worse precision than ...
- 9,327
1
vote
Accepted
What is the relationship between the training accuracy and validation accuracy?
very interesting questions:
1. what exactly is happening when training and validation accuracy change during training
The accuracy change after every batch ...
- 1,148
Only top scored, non community-wiki answers of a minimum length are eligible