Insert Topic Here PyTorch
Created : 20/01/2022 | on Linux: 5.4.0-91-generic
Updated: 20/01/2022 | on Linux: 5.4.0-91-generic
Status: Draft
previous topic 1: Starting Development with PyTorch
previous topic 2: Tensors and Data Handling with PyTorch previous topic 3: Building a network in eager mode
Typical Workflow
Teensorflow 1 is based on a graph style programing model. A typical top level workflow can be summarised into 4 key slots.
- Defining graph elements.
- Defining connectivty (layout the graph).
- Defining functionality (algorithmic components).
- Running the graph and interpriting results.
Graph Elements
Basic graph element objects are
- Constants : Holds the value once declared.
- Placeholders : Placeholders need placement at somepoint using a feed dictionary.
- Variables : Variables need proper initialisation and can change within graph execution.
Within Tensorflow these data elements are usually called Tensors. We can say that Tensor attributes vary depending on the element types. This differents can be a mix of qualititative and quantative attributes.
for example, A constant, placeholder or a Variable can be of different type and differnt shape, we could also designate where they reside in computer memory.
Check the next topic
Source: PyTorch Tutorial
Click here to report Errors, make Suggestions or Comments!