I want to train a facial recognition CNN from scratch. I can write a Keras Sequential() model following popular architectures and copying their networks.
I wish to use the LFW dataset, however I am confused regarding the technical methodology. Do I have to crop each face to a tight-fitting box? That seems impractical, as the dataset has 13000+ faces.
Lastly, I know it's stupid, but all I have to do is preprocess the images (of course), then fit the model to these images? What's the exact procedure?
Your question is very open ended. Before preprocessing and fitting the model, you need to understand Object Detection. Once you understand what object detection you will get answer to your 1st question whether you are required to manually crop every 13000 image. The answer is no. However, you will have to draw bounding boxes around faces and assign label to images if they are not available in the training data.
Your second question is very vague . What do you mean by exact procedure? Is it the steps you need to do or how to do preprocessing and fitting of the model in python/or any other language? There are lots of references available on the internet about how to do preprocessing and model training for every specific problem. There are no universal steps which can be applied to any problem
Related
I'm using Windows 10 machine. Libraries: Keras with Tensorflow 2.0 Embeddings: Glove(100 dimensions).
I am trying to implement an LSTM architecture for multi-label text classification.
I am using different types of fine-tuning to achieve better results but with no luck so far.
The main problem I believe is the difference in class distributions of my dataset but after a lot of tries and errors, I couldn't implement stratified-k-split in Keras.
I am also experimenting with dropout layers, batch sizes, # of layers, learning rates, clip values, validation splits but I get a minimum boost or worst performance sometimes.
For metrics, I use mainly ROC and F1.
I also followed the suggestion from a StackOverflow member who said to delete some of my examples so I can balance my dataset but if I do that I will have a very low number of examples.
What would you suggest to me?
If someone can provide code based on my implementation for
stratified-k-split I would be grateful cause I have checked all the
online resources but can't implement it.
Any tips, suggestions will be really helpful.
Metrics Plots
Dataset form+Embedings form+train-test-split form
Dataset's labels distribution
My LSTM implementation
I'm using Windows 10 machine.
Libraries: Keras with Tensorflow 2.0
Embeddings:Glove(100 dimensions)
I am trying to implement an LSTM architecture for multi-label text classification.
My problem is that no matter how much fine-tuning I do, the results are really bad.
I am not experienced in DL practical implementations that's why I ask for your advice.
Below I will state basic information about my dataset and my model so far.
I can't embed images since I am a new member so they appear as links.
Dataset form+Embedings form+train-test-split form
Dataset's labels distribution
My Implementation of LSTM
Model's Summary
Model's Accuracy plot
Model's Loss plot
As you can see my dataset is really small (~6.000 examples) and maybe that's one reason why I cannot achieve better results. Still, I chose it because it's unbiased.
I'd like to know if there is any fundamental mistake in my code regarding the dimensions, shape, activation functions, and loss functions for multi-label text classification?
What would you recommend to achieve better results on my model? Also any general advice regarding optimizing, methods,# of nodes, layers, dropouts, etc is very welcome.
Model's best val accuracy that I achieved so far is ~0.54 and even if I tried to raise it, it seems stuck there.
There are many ways to get this wrong but the most common mistake is to get your model overfit the training data.
I suspect that 0.54 accuracy means that your model selects the most common label (offensive) for almost all cases.
So, consider one of these simple solutions:
Create balanced training data: like 400 samples from each class.
or sample balanced batches for training (exactly the same number of labels on each training batch)
In addition to tracking accuracy and loss, look at precision-recall-f1 or even better try plotting area under curve, maybe different classes need different thresholds of activation. (If you are using Sigmoid on last layer maybe one class could perform better with 0.2 activations and another class with 0.7)
first try simple model. embedding 1 layer LSTM than classify
how to tokenize text , is vocab size enough ?
try dice loss
I am currently working on fingers-count deep learning problem. When you look at the dataset, images in the training and validation set are very basic and are almost the same. The network can achieve high training and validation accuracies. But when it comes to prediction in real-life images, it performs very badly(this is because the model has been trained on very basic images).
To overcome this, I converted the training and validation images to HSV(Hue-Saturation-Value) and trained the model on new HSV images. Example of 1 such image from new training set is:
I then convert my image from real life to HSV and pass it to model for prediction. But still, the model is not able to predict correctly. I assumed that since the training images and predicting image are almost same after applying HSV, the model should be predicting good. Is there something which I am thinking incorrectly here? Can HSV images be actually used for training CNN?
It seems you have the overfitting issue, and your model only memorize the simple samples of the training set and in contrast it can not generalize to more complex and diverse data.
In the context of Deep Learning there are various methods to avoid overfitting and I think you don't need to transform your input to HSV necessarily. First of all you can apply various data augmentation methods like random crop or rotation to create various versions of your data. If this method does not work, you can use a smaller model or applying techniques such as Drop Out or Regularization.
Here is a good tutorial from TensorFlow.
Is it possible to add a new face features into trained face recognition model, without retraining it with previous faces?
Currently am using facenet architecture,
Take a look in Siamese Neural Network.
Actually if you use such approach you don't need to retrain the model.
Basically you train a model to generate an embedding (a vector) that maps similar images near and different ones far.
After you have this model trainned, when you add a new face it will be far from the others but near of the samples of the same person.
basically, by the mathematics theory behind the machine learning models, you basically need to do another train iteration with only this new data...
but, in practice, those models, especially the sophisticated ones, rely on multiple iterations for training and a various technics of suffering and nose reductions
a good approach can be train of the model from previous state with a subset of the data that include the new data, for a couple of iterations
I am trying to train a classifier to separate images taken by a particle physics detector into two classes. For each image, I also have a coordinate (x,y,z) describing where the particle interaction took place. That coordinate is very useful is understanding these images by eye, but doesn't have an obvious translation to weighting image pixels.
I've been trying some basic machine learning techniques in scikit-learn, feeding in data points with 103 features: the three axes of the coordinates, and the 10x10 pixels of the image. Those basic techniques aren't cutting it, unfortunately, so I thought I'd try to take advantage of the properties of convolutional neural networks. Since I've never tried that before, Keras seemed like an easy way to get started.
Looking at Keras, I see that I ought to provide an input shape. I could presumably use a input shape of (103), but if I understand CNN correctly, I'd lose all the advantages of CNN for images. Intuitively, what I want the input shape to be is (3)+(10,10). Is that a sensible concept in the world of CNN? Can it be done in Keras?
You might want to look into the Merge layer. In essence this allows you to use two independent inputs, maybe give them a few different processing layers and them combine them for the rest of the model.
With this you could, for example, do several convolutional layers to process the image and then simply merge it with the coordinate inputs.