M4 Flashcards
What is tensor flow?
Open source - high performance library for numerical and computation that uses directed graphs
What are various abstraction layers of TF
CPU-GPU-TPU-android
Core TF, C++
Core TF Python == Python gives full control
tf.losses, tf.metrics, tf.optimizers, etc. == Components useful for building NN Models
tf.esimator, tf.keras, tf.data == High level APIs for distributed learning
Which are useful components when building custom Neural Network models?
all:
tf.losses
tf.metrics
tf.optimizers
How does TensorFlow represent numeric computations?
Using a Directed Acyclic Graph (or DAG)
Which of the following is true when we compute a loss gradient?
All:
It uses tape and the gradients associated with each recorded operation to compute the gradients.
check
The computed gradient of a recorded computation will be used in reverse mode differentiation.
TensorFlow records all operations executed inside the context of a tf.GradientTape onto a tape.
Which of the following statements is true of TensorFlow?
TensorFlow is a scalable and multi platform programming interface for implementing and running machine learning algorithms, including convenience wrappers for deep learning.
Which API is used to build performant, complex input pipelines from simple, re-usable pieces that will feed your model’s training or evaluation loops.
tf.data.Dataset
What does The tf.keras.layers. TextVectorization
It transforms a batch of strings, where one example equals one string into one of two things, either a list of token indices, where one example equals one detensor of integer token indices, or a dense representation with one example equal to one detensor of float values representing data about the examples tokens. Essentially, the TextVectorization layer turns raw strings into an encoded representation that can be read by an Embedding layer or Dense layer.
what does tf.keras Discretization layer do?
this layer turns continuous numerical features into bucket data, with discrete ranges
