Cursos /
Introduction to TensorFlow
Summary
Let's now summarize all the key topics we've discussed in this course. Feel free to download the overview material in the end of this page.
Tensorflow Set Up
![TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-1/tensorflow_logo.png)
Instalation
Import
Tensor Types
![Tensors](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-2/tensors.png)
![Tensors convertion](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-2/3d_tensor_to_4d_1.png)
![ND Tensors Convertion](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-2/nd_tensor.png)
Simple Tensor Creation
Tensor Properties
- Rank: It tells you the number of dimensions present in the tensor. For instance, a matrix has a rank of 2. You can get the rank of the tensor using the
.ndim
attribute:
- Shape: This describes how many values exist in each dimension. A 2x3 matrix has a shape of
(2, 3)
. The length of the shape parameter matches the tensor's rank (its number of dimensions). You can get the the shape of the tensor by the.shape
attribute:
- Types: Tensors come in various data types. While there are many, some common ones include
float32
,int32
, andstring
. You can get the the data type of the tensor by the.dtype
attribute:
![Tensor Properties](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-3/tensor_properties.png)
Tensor Axes
![Tensor Axes](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-3/tensor_axes.png)
Applications of Tensors
- Table Data
![Table as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/table_as_tensor.png)
- Text Sequences
![Text as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/text_as_tensor.png)
- Numerical Sequences
![Numerical Sequence as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/numseq_as_tensor.png)
- Image Processing
![Image as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/image_as_tensor.png)
- Video Processing
![Video as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/video_as_tensor.png)
Batches
![Batches](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/batches.png)
![ND Batches](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/batches_nd.png)
Tensor Creation Methods
Convertions
- NumPy to Tensor
- Pandas to Tensor
- Constant Tensor to a Variable Tensor
Data Types
![Data Types](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-6/data_types.png)
Arithmetic
- Addition
- Subtraction
- Element-wise Multiplication
- Division
Broadcasting
![Broadcasting 1D](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-7/broadcasting_1d.png)
![Broadcasting 2D](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-7/broadcasting_2d.png)
Linear Algebra
- Matrix Multiplication
- Matrix Inversion
- Transpose
- Dot Product
Reshape
![Reshape](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/reshape.png)
Slicing
![Slicing](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/slice.png)
Modifying with Slicing
![Assign](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/assign.png)
Concatenating
![Concatenation](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/concat_fixed.png)
Reduction Operations
![Reduce Sum](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-11/reduce_sum.png)
Gradient Tape
![Partial Derivatives](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+2-1/partial_derivatives.png)
@tf.function
What role does a loss function play in a neural network?
Selecciona unas respuestas correctas
¿Todo estuvo claro?
Sección 2. Capítulo 5
Contenido del Curso
Introduction to TensorFlow
2. Basics of TensorFlow
Introduction to TensorFlow
Summary
Let's now summarize all the key topics we've discussed in this course. Feel free to download the overview material in the end of this page.
Tensorflow Set Up
![TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-1/tensorflow_logo.png)
Instalation
Import
Tensor Types
![Tensors](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-2/tensors.png)
![Tensors convertion](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-2/3d_tensor_to_4d_1.png)
![ND Tensors Convertion](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-2/nd_tensor.png)
Simple Tensor Creation
Tensor Properties
- Rank: It tells you the number of dimensions present in the tensor. For instance, a matrix has a rank of 2. You can get the rank of the tensor using the
.ndim
attribute:
- Shape: This describes how many values exist in each dimension. A 2x3 matrix has a shape of
(2, 3)
. The length of the shape parameter matches the tensor's rank (its number of dimensions). You can get the the shape of the tensor by the.shape
attribute:
- Types: Tensors come in various data types. While there are many, some common ones include
float32
,int32
, andstring
. You can get the the data type of the tensor by the.dtype
attribute:
![Tensor Properties](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-3/tensor_properties.png)
Tensor Axes
![Tensor Axes](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-3/tensor_axes.png)
Applications of Tensors
- Table Data
![Table as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/table_as_tensor.png)
- Text Sequences
![Text as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/text_as_tensor.png)
- Numerical Sequences
![Numerical Sequence as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/numseq_as_tensor.png)
- Image Processing
![Image as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/image_as_tensor.png)
- Video Processing
![Video as Tensor](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/video_as_tensor.png)
Batches
![Batches](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/batches.png)
![ND Batches](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-4/batches_nd.png)
Tensor Creation Methods
Convertions
- NumPy to Tensor
- Pandas to Tensor
- Constant Tensor to a Variable Tensor
Data Types
![Data Types](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-6/data_types.png)
Arithmetic
- Addition
- Subtraction
- Element-wise Multiplication
- Division
Broadcasting
![Broadcasting 1D](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-7/broadcasting_1d.png)
![Broadcasting 2D](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-7/broadcasting_2d.png)
Linear Algebra
- Matrix Multiplication
- Matrix Inversion
- Transpose
- Dot Product
Reshape
![Reshape](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/reshape.png)
Slicing
![Slicing](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/slice.png)
Modifying with Slicing
![Assign](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/assign.png)
Concatenating
![Concatenation](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-10/concat_fixed.png)
Reduction Operations
![Reduce Sum](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+1-11/reduce_sum.png)
Gradient Tape
![Partial Derivatives](https://codefinity-content-media-v2.s3.eu-west-1.amazonaws.com/courses/a668a7b9-f71f-420f-89f1-71ea7e5abbac/Ch.+2-1/partial_derivatives.png)
@tf.function
What role does a loss function play in a neural network?
Selecciona unas respuestas correctas
¿Todo estuvo claro?
Sección 2. Capítulo 5