I have designed a Convolutional Neural Network in Keras for image classification with several convolution/max-pooling layers, one densely connected hidden layer and softmax activation on the final layer. I want to replace softmax with an SVM or Random Forest in the final layer to see if that yields a better accuracy. Is there any way to do it in Keras?
In order to have (kind of) SVM simply use a hinge loss instead of log loss. Putting RF does not make sense, as you need a differentiable model to be a part of neural net (unless all you want to do is to train a network, and later chop off its final part and use it as a feature detector which is just fed into RF, but this is not a valid approach in general).
Related
I am new to deep learning as well as using Theano and tensorflow. I was able to understand how the tensor flow example code of a convolution neural network to recognize MNIST benchmark works. But since all inbuilt libraries are used I was not able to get a full grip of it.
I would like to write a fast training algorithm for a convolution neural network that recognizes MNIST benchmark but without tensorflow or Theano. I have already coded the network and I can access the output of each layer as well as the weights and bias used in each layer. I need to use these outputs to update the weights and bias of each layer but I’m not sure how.
I would really appreciate if someone could guide me in this regard.
The network that I have used is the network specified in the tensorflow example. It has two convolution pool layers and two fully connected layers.
Thanks
I am training an SVM model(RBF kernel) on ~ 5000 samples, I tunned my model properly and used it to make predictions.
Now, I have 1000 more samples which can also be used for training.
My question is, do I have to make the model again on total 6000 samples, or is there any way by which I can add training data to my existing SVM model.
Note- Actually the dataset I am using is quite large, and making model again will not be a good thought.
Its called "incremental" or "online" SVM algorithm. Currently its supported mostly for linear kernel type in various libraries:
Liblinear Incremental. Paper
Gert Cauwenberghs
Chris Diehl
After obtaining the image dataset, the feature database is constructed for all images which is a vector based on mean and sd of RGB color model and HSV color model for a portion of the image. How can I use a svm to retieve related images from the database once the query image is given.
Also how to use unsupervised learning for the above problem
Assuming the query images are unlabeled, applying SVM would require a way of knowing the labels for dataset images since SVM is a form of supervised learning, which seeks to correctly determine class labels for unlabeled data. You would need another method for generating class labels, such as unsupervised learning, so this approach does not seem relevant if you only have feature vectors but no class labels.
A neural network allows for unsupervised learning with unlabeled data, but is a rather complex approach and is the subject of academic research. You may want to consider a simpler machine learning approach such as k-Nearest Neighbors, which allows you to obtain the k closest training samples that are similar in your feature space. This algorithm is simple to implement and is found in many machine learning libraries. For example in Python you can use scikit learn.
I am unsure what type of images you are working with, but you might also want to explore using feature detector algorithms such as SIFT rather than just pixel intensities.
I was under the impression the training data given to train an SVM consisted of image features, but after reading this post again, the training_mat that is given to the SVM in the example is just the img_mat flattened to 1-Dimension.
So my question is, when training an SVM, do you give it whole images in their entirety, row by row, or do you detect and extract the features, and then flatten a Mat of that into 1-Dimension?
You can extract features, or you can use pixel intensity values as the features. In this example, they have done the latter. In this case, you end up with a very high number of features that many of them may be not useful. This makes the convergence of the SVM training more difficult, but can be still possible. Based on my personal experience, SVM works better if you extract a lower number of "good" features that best describe your data. However, in recent years, it has been shown that state-of-the-art estimators like deep neural networks (when used instead of SVM) can perform very well with only using the pixel intensity values as features. This has eliminated the need for feature extraction in the methods that has led to state-of-the-art results on public data sets (like ImageNet)
I was given a project on vehicle type identification with neural network and that is how I came to know the awesomeness of neural technology.
I am a beginner with this field, but I have sufficient materials to learn it. I just want to know some good places to start for this project specifically, as my biggest problem is that I don't have very much time. I would really appreciate any help. Most importantly, I want to learn how to match patterns with images (in my case, vehicles).
I'd also like to know if python is a good language to start this in, as I'm most comfortable with it.
I am having some images of cars as input and I need to classify those cars by there model number.
Eg: Audi A4,Audi A6,Audi A8,etc
You didn't say whether you can use an existing framework or need to implement the solution from scratch, but either way Python is excellent language for coding neural networks.
If you can use a framework, check out Theano, which is written in Python and is the most complete neural network framework available in any language:
http://www.deeplearning.net/software/theano/
If you need to write your implementation from scratch, look at the book 'Machine Learning, An Algorithmic Perspective' by Stephen Marsland. It contains example Python code for implementing a basic multilayered neural network.
As for how to proceed, you'll want to convert your images into 1-D input vectors. Don't worry about losing the 2-D information, the network will learn 'receptive fields' on its own that extract 2-D features. Normalize the pixel intensities to a -1 to 1 range (or better yet, 0 mean with a standard deviation of 1). If the images are already centered and normalized to roughly the same size than a simple feed-forward network should be sufficient. If the cars vary wildly in angle or distance from the camera, you may need to use a convolutional neural network, but that's much more complex to implement (there are examples in the Theano documentation). For a basic feed-forward network try using two hidden layers and anywhere from 0.5 to 1.5 x the number of pixels in each layer.
Break your dataset into separate training, validation, and testing sets (perhaps with a 0.6, 0.2, 0.2 ratio respectively) and make sure each image only appears in one set. Train ONLY on the training set, and don't use any regularization until you're getting close to 100% of the training instances correct. You can use the validation set to monitor progress on instances that you're not training on. Performance should be worse on the validation set than the training set. Stop training when the performance on the validation set stops improving. Once you've accomplished this you can try different regularization constants and choose the one that results in the best validation set performance. The test set will tell you how well your final result is performing (but don't change anything based on test set results, or you risk overfitting to that too!).
If your car images are very complex and varied and you cannot get a basic feed-forward net to perform well, you might consider using 'deep learning'. That is, add more layers and pre-train them using unsupervised training. There's a detailed tutorial on how to do this here (though all the code examples are in MatLab/Octave):
http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
Again, that adds a lot of complexity. Try it with a basic feed-forward NN first.