In the process of designing the interface, we may need to set up a “scrollable” area in the interface so that we can maximize the display of the information we want to display in the limited layout.
Read More »[PyQt5] How to use the QScrollArea component to make a scrolling page When we are developing the front-end interface, if we want to display a picture on the interface, in addition to open the directory for user to choose file, I think drag a picture to the QLabel component and display is a great way.
Read More »[PyQt5] Drag the picture onto the QLabel component and display the picture When we use PyQt5 to develop a graphical interface, maybe sometimes we need to save the image of QLabel component. Of course, if we proactively show a picture on QLabel, we don’t need to worry about this problem. OF COURSE WE ALREADY HAVE THAT DREAM PICTURE.
Read More »[PyQt5] How to save text or images in QLabel component as pictures I always want to try to use PyQt5 in Python to make a simple handwriting/drawing board, which can write and draw on the interface we develop at will.
Read More »[PyQt5] Make a simple drawing board through the program
If we want to use GPU for deep learning (for example, through Tensorflow or Keras), the installation environment is not really complicated, and it usually only takes a few hours to complete the environment in the first time.
Read More »[Linux] Install CUDA and CuDNN on Ubuntu 18.04
Today I want to record how to use Deep generative Adversarial Network (DCGAN) to implement a simple generate picture model. I wanted to demo with delicious snack pictures, but the effect was not very good, I downloaded half a million snack pictures in vain.
Finally, I used the official demo CelebA dataset.
Read More »[PyTorch] Tutorial(7) Use Deep Generative Adversarial Network (DCGAN) to generate pictures Just as torchvision is a module in PyTorch that specializes in processing pictures, torchaudio to be recorded today is a module in PyTorch that specializes in processing audio.
Today we challenged the classifiers of different data sets again. This time, CIFAR-19 is a more difficult problem than MNIST handwriting recognition. In addition to the size of the picture becoming 32×32, CIFAR-10 is no longer a pure grayscale value, but a picture with the three primary colors of RGB.
Read More »[PyTorch] Tutorial(5) How to train a model to classify CIFAR-10 database “Use a toy dataset to train a classification model” is a simplest deep learning practice.
Today I want to record how to use MNIST A HANDWRITTEN DIGIT RECOGNITION dataset to build a simple classifier in PyTorch.
Read More »[PyTorch] Tutorial(4) Train a model to classify MNIST dataset The so-called Neural Network is the model architecture we want to build for deep learning. In official PyTorch document, the first sentence clearly states:
You can use torch.nn to build a neural network.
