I am experimenting with the Bayesian hierarchical models and I want to use some categorical features as predictors. for the moment I am constructing the features by hand (each vector), is there any way to pass a matrix where there is every categorical feature and assign to each one of them a parameter in TensorFlow?
Related
I'm attempting to train an xgboost classification model using BQML. But I'd like to give one feature a higher weight. I couldn't find any documentation about assigning feature weights. There is CLASS_WEIGHTS to assign weights to class labels but that is not what I want. BQML documentation.
I feel like this feature is not available yet and I have to create handmade models using sklearn.
In deep learning based model training, in general batch of inputs are passed. For example for training a deep learning model with [512] dimensional input feature vector, say for batch size= 4, we mainly pass [4,512] dimenional input. I am curious what are the logical significance of passing the same input after flattening the input across the batch and channel dimenions [2048]. Logically the locality structure will be destroyed but will it significanlty speed up my implementation? And can it affect the performance?
In supervised learning, you would usually be working with data points (e.g. a feature vector or a multi-dimensional input such as an image) paired with some kind of ground-truth (a label for classifications tasks, or another multi-dimensional object altogether). Feeding to your model a flattened tensor containing multiple data points would not make sense in terms of supervision. Assuming you do an inference this way, what would be the supervision signal at the output level of your model? Would you combine the labels as well? All of this seem to depend heavily on the use case: is there some kind of temporal coherence between the elements of the batch?
Performance-wise, this has no implications whatsoever. Tensors are already 'flattened' by design since their memory is laid out in contiguous memory buffers. The idea of multi-dimensionality is an abstraction layer provided by those libraries (namely NumPy's arrays and Torch's tensors) to allow for easier and more flexible control over data.
I'm trying to consume this tutorial by Google to use TensorFlow Estimator to train and recognise images: https://www.tensorflow.org/tutorials/estimators/cnn
The data I can see in the tutorial are: train_data, train_labels, eval_data, eval_labels:
((train_data,train_labels),(eval_data,eval_labels)) =
tf.keras.datasets.mnist.load_data();
In the convolutional layers, there should be feature filter image data to multiply with the input image data? But I don't see them in the code.
As from this guide, the input image data matmul with filter image data to check for low-level features (curves, edges, etc.), so there should be filter image data too (the right matrix in the image below)?: https://adeshpande3.github.io/A-Beginner%27s-Guide-To-Understanding-Convolutional-Neural-Networks
The filters are the weight matrices of the Conv2d layers used in the model, and are not pre-loaded images like the "butt curve" you gave in the example. If this were the case, we would need to provide the CNN with all possible types of shapes, curves, colours, and hope that any unseen data we feed the model contains this finite sets of images somewhere in them which the model can recognise.
Instead, we allow the CNN to learn the filters it requires to sucessfully classify from the data itself, and hope it can generalise to new data. Through multitudes of iterations and data( which they require a lot of), the model iteratively crafts the best set of filters for it to succesfully classify the images. The random initialisation at the start of training ensures that all filters per layer learn to identify a different feature in the input image.
The fact that earlier layers usually corresponds to colour and edges (like above) is not predefined, but the network has realised that looking for edges in the input is the only way to create context in the rest of the image, and thereby classify (humans do the same initially).
The network uses these primitive filters in earlier layers to generate more complex interpretations in deeper layers. This is the power of distributed learning: representing complex functions through multiple applications of much simpler functions.
How to implement Multi-target classification in tensorflow? Say I have a list of features f1,f2,...,fn and i want to predict the class or a value of three targets t1,t2,and t3. So each target belongs to a single class only.
It sounds like you're interested in multinomial logistic regression. In TensorFlow, the most important function for this is tf.nn.softmax_cross_entropy_with_logits_v2.
This site gives a good idea how the softmax function makes it possible to classify a point in multiple categories.
I am working with the Tensorflow Wide and Deep model. It currently trains against a binary classification (>50K or not).
Can this model be coerced to train directly against numeric values to produce more precise (if less accurate) predictions?
I have seen an example of using LSTM RNNs to make such predictions using TensorFlowEstimator directly here, but DNNLinearCombinedClassifier will not accept n_classes=0.
I like the structure of the Wide and Deep model, especially the ability to run the linear regression and the DNN separately to determine how learnable the data is, but my application involves data that clusters, but in an overlapping, input-dependent fashion.
Use DnnLinearCombinedRegressor for regression problems.