15 posts
During deep learning training, we inevitably need to observe changes in metrics such as Loss and Learning_rate, so plotting curves in real time is essential. This article explains how to use PyTorch's TensorBoard to plot curves.
Python has a rich set of useful built-in modules and third-party modules that make it quick and convenient to implement many common features.
This article summarizes basic Python file reading and writing operations, as well as common os operations on directories and files, such as retrieving paths, joining paths, renaming files, and moving files. It also summarizes commonly used JSON operations.
During program execution, you inevitably encounter all kinds of errors. Some are caused by bugs in the code, some by user input, and others are completely unpredictable at runtime. Python includes a built-in exception-handling mechanism to help us handle errors.
Summarizes basic class usage; the characteristics and application examples of encapsulation, inheritance, and polymorphism; and inheritance-oriented advanced features such as multiple inheritance and customized classes.
In Python, less code is better, and simpler code is better. Based on this philosophy, Python provides many useful advanced features, such as list comprehensions, generators, anonymous functions, and decorators.
A summary of some concepts that beginners may find difficult to understand when starting out in deep learning.
Generally, channels refers to the number of convolution kernels in each convolutional layer. The channels of the initial input image sample depend on the image type, such as RGB; after convolution, out_channels depends on the number of convolution kernels. The out_channels then also serves as the in_channels of the convolution kernel in the next convolution.
Convolution is essentially the process of taking a matrix of a specific size each time, sliding it across the input matrix, and computing the inner product at each position.
The process of setting up a deep learning environment with Anaconda + CUDA + TensorFlow 2 + Keras.
An installation tutorial for the commonly used deep learning environment PyTorch.
Cloud drive link: https://pan.baidu.com/s/1yUpRG146dUXC9Gj1D94AHw, extraction code: rsaz. Extract the installation package, run ABB RobotStudio 6.08.msi, and follow the prompts step by step to install it. After installation is complete, depending on your computer, extract...
If you have a gripper model created with other modeling software such as SolidWorks, you can import it into RobotStudio. Here, a simple model is created, mainly to demonstrate the process of creating a dynamic gripper.
Click Create Collision Detection to create a collision check. Once created, ObjectA and ObjectB are the two groups to be checked. If objects in the two groups collide, their colors will change.
This article covers the process of creating a robot path after the mechanical model and robot system have already been created. The project files have been uploaded to a cloud drive, including the initial project file (03Practice_init.rspag), the completed project file (03Practice.rspag), and model files.
