Generative Adversarial Network (GAN) is a famous neural network model, its function is to input a set of noise and then generate a set of fake pictures through the Generator, and then use the Discriminator to distinguish whether it is a real picture.
Read More »[PyTorch] Build a GAN model to generate false MNIST pictures
If we have both the model classification results and correct answers, we can calculate the Binary Cross Entropy, it is a famous loss function.
Read More »[Machine Learning] Introduction to Binary Cross Entropy
When using sigmoid function in PyTorch as our activation function, for example it is connected to the last layer of the model as the output of binary classification. After all, sigmoid can compress the value between 0-1, we only need to set a threshold, for example 0.5 and you can divide the value into two categories.
Read More »[PyTorch] Set the threshold of Sigmoid output and convert it to binary value Today if you are preprocessing some machine learning data, maybe you need to convert PyTorch tensor to one-hot encoding type. There is a intuitive method that is convert TENSOR to NUMPY-ARRAY, and then convert NUMPY-ARRAY to one-hot encoding type, just like this article: [Python] Convert the value to one-hot type in Numpy
Read More »[PyTorch] Convert Tensor to One-Hot Encoding Type NLLLoss is a loss function commonly used in multi-classes classification tasks. Its meaning is to take log the probability value after softmax and add the probability value of the correct answer to the average.
Read More »[Machine Learning] NLLLoss function introduction and program implementation
Recently, I encountered a task to perform Multi-label Classification, and I realized that I had never trained a model in this task.
Read More »[Keras] How to build a Multi-label Classification Model
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 32x32, 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
