I want to use Caffe and the googlenet structure coming with Caffe to train a model based on my own image data.
I have 14 categories for classification. But I do have only around 250 images for training and 80 for testing. Is this enough? Are there means to find out how many images I need per class?
Solution 1:
Just finetune the top layer since you only have such few data. By this way, you can think the network as a feature extractor and you just train a classifier on top this features.
Solution 2:
Try aggressive data augmentation. For example you can try random translation, scaling, rotation of your data. In this way, you can get a lot of images from one training image.
Solution 3:
The most effective way is to try to get more real data. Data is very important for deep learning. As a rule of thumb, at least 1000 images for one class.
Related
I want to use convolutional Neural Network (CNN) to classify between two classes of images. I built several CNN architectures, but I always get the same result; the network always classify all cases as a second class sample. Therefore, I always get 50% accuracy in leave-one-out. The data is balanced in terms of the number of samples of each class (16 from 1st, and 16 from 2nd). Could you please clarify what does this mean.
With such small number of training samples, Your CNN model is very likely to overfit the data giving good training accuracy and worst test accuracy.
Else your model can be skewed predicting the same class at all times.
Below are some of the solutions you can try:
1) As you have commented, if you cannot get any more images, then try creating new images by modifying the ones already available. For ex: Let's say you have 16 images of a cat (cat is the class). You can crop the cat and paste it in different backgrounds, try varying the brightness, intensity etc, Try rotation, translation operations etc.
This will help you create a good training set.
2) Try creating a smaller model (with one or two layers) and check if it improves your accuracy.
3) You can do transfer learning by using a good pre-trained model as it can learn pretty well when compared to creating a model from base.
I have images that I want to process. First features are extracted from those images and then those features are fed into a neural network for training. I do not have many images though and would like to generate more data.
1) What yields less overfitting: Should I generate more images from the original images and then feed the entire pipeline with them, or should I bring variation into the extracted features and simply train the neural network with more data this way?
The second approach would be computationally cheaper, but yields better results?
2) What techniques are tried and true for generating more data - either more images or the features?
Is true that when you don't have enough data the performance of your model can be poor. So you have to try a few things:
You can modify the data that you have applying translations, rotations, etc; for example move all the pixel of the image a few pixel to the left. This are operation on images.
Also you can generate more images through generative models: Restricted Boltzmann Machines, Deep Belief Networks etc.
Also you have a way of determine if you need more training data. In the coordinate axis you draw the score of the training data and validation data. In the x axis goes the size of the sets(10% of the all set, 20% of the all set, ..., 90% of the all set) and in the y axis is the score. Then you look at the graph. For understand well enough this what i'm saying i strongly recommend the videos of Andrew Ng of Machine Learning(https://www.coursera.org/learn/machine-learning) specifically the Week 6(Advice for Applying Machine Learning)
Let's suppose I would like to classify motorbikes by model.
there are couple of hundreds models of motorbikes I'm interested in.
I do have tens, sometimes hundreds of pictures of each motorbike model.
Can you please point me to the practical example that demonstrates how to train model on your data and then use it to classify images? It needs to be a deep learning model, not simple logistic regression.
I'm not sure about it, but it seems like I can't use pre-trained neural net because it has been trained on wide range of objects like cat, human, cars etc. They may be not too good at distinguishing the motorbike nuances I'm interested in.
I found couple of such examples (tensorflow has one), but sadly, all of them were using pre-trained model. None of it had example how to train it on your own dataset.
In cases like yours you either use transfer learning or fine tuning. If you have more then thousand images of motorbikes I would use fine tuning and if you have less transfer learning.
Fine tuning is using a pre trained model and using a different classifier part. Then the new classifier part maybe the last 1-2 layers of the trained model are trained to your dataset.
Transfer learning means using a pre trained model and letting it output features for an input image. Now you use a new classifier based on those features. Maybe a SVM or a logistic regression.
An example for this can be seen here: https://github.com/cpra/dlvc2016/blob/master/lectures/lecture10.pdf. slide 33.
This paper Quick, Draw! Doodle Recognition from a kaggle challenge may be similar enough to what you are doing. The code is on github. You may need some data augmentation if you only have a few hundred images for each category.
What you want is pretty EZ. Follow the darknet YOLO implementation
Instruction: https://pjreddie.com/darknet/yolo/
Code https://github.com/pjreddie/darknet
Training YOLO on COCO
You can train YOLO from scratch if you want to play with different training regimes, hyper-parameters, or datasets. Here's how to get it working on the COCO dataset.
Get The COCO Data
To train YOLO you will need all of the COCO data and labels. The script scripts/get_coco_dataset.sh will do this for you. Figure out where you want to put the COCO data and download it, for example:
cp scripts/get_coco_dataset.sh data
cd data
bash get_coco_dataset.sh
Add your data inside and make sure it is same as testing samples.
Now you should have all the data and the labels generated for Darknet.
Then call training script with the pre-trained weight.
Keep in mind that only training on your motorcycle may not result in good estimation. There would be biased result coming out, I red it somewhere b4.
The rest is all inside the link. Good luck
Away from the common datasets of Iris or wine, let's say we have dataset of 3 classes and this data is non-separable. How by any way to increase its percentage of correct classification samples...for example from 50% to 80 or 90%?
Your Question is way to vague.
If your data is non-separable, there is no way to separate them. Given the data, the classes are the same.
Maybe you are trying to separate them with linear model and they aren't linear-separable? So you need a non-linear classification like a SVM with non-linear kernel.
I am working on Soil Spectral Classification using neural networks and I have data from my Professor obtained from his lab which consists of spectral reflectance from wavelength 1200 nm to 2400 nm. He only has 270 samples.
I have been unable to train the network for accuracy more than 74% since the training data is very less (only 270 samples). I was concerned that my Matlab code is not correct, but when I used the Neural Net Toolbox in Matlab, I got the same results...nothing more than 75% accuracy.
When I talked to my Professor about it, he said that he does not have any more data, but asked me to do random perturbation on this data to obtain more data. I have research online about random perturbation of data, but have come up short.
Can someone point me in the right direction for performing random perturbation on 270 samples of data so that I can get more data?
Also, since by doing this, I will be constructing 'fake' data, I don't see how the neural network would be any better cos isn't the point of neural nets using actual real valid data to train the network?
Thanks,
Faisal.
I think trying to fabricate more data is a bad idea: you can't create anything with higher information content than you already have, unless you know the true distribution of the data to sample from. If you did, however, you'd be able to classify with the Bayes optimal error rate, which would be impossible to beat.
What I'd be looking at instead is whether you can alter the parameters of your neural net to improve performance. The thing that immediately springs to mind with small amounts of training data is your weight regulariser (are you even using regularised weights), which can be seen as a prior on the weights if you're that way inclined. I'd also look at altering the activation functions if you're using simple linear activations, and the number of hidden nodes in addition (with so few examples, I'd use very few, or even bypass the hidden layer entirely since it's hard to learn nonlinear interactions with limited data).
While I'd not normally recommend it, you should probably use cross-validation to set these hyper-parameters given the limited size, as you're going to get unhelpful insight from a 10-20% test set size. You might hold out 10-20% for final testing, however, so as to not bias the results in your favour.
First, some general advice:
Normalize each input and output variable to [0.0, 1.0]
When using a feedforward MLP, try to use 2 or more hidden layers
Make sure your number of neurons per hidden layer is big enough, so the network is able to tackle the complexity of your data
It should always be possible to get to 100% accuracy on a training set if the complexity of your model is sufficient. But be careful, 100% training set accuracy does not necessarily mean that your model does perform well on unseen data (generalization performance).
Random perturbation of your data can improve generalization performance, if the perturbation you are adding occurs in practice (or at least similar perturbation). This works because this means teaching your network on how the data could look different but still belong to the given labels.
In the case of image classification, you could rotate, scale, noise, etc. the input image (the output stays the same, naturally). You will need to figure out what kind of perturbation could apply to your data. For some problems this is difficult or does not yield any improvement, so you need to try it out. If this does not work, it does not necessarily mean your implementation or data are broken.
The easiest way to add random noise to your data would be to apply gaussian noise.
I suppose your measures have errors associated with them (a measure without errors has almost no meaning). For each measured value M+-DeltaM you can generate a new number with N(M,DeltaM), where n is the normal distribution.
This will add new points as experimental noise from previous ones, and will add help take into account exprimental errors in the measures for the classification. I'm not sure however if it's possible to know in advance how helpful this will be !