[Linux] Speed Up Pure Python Programs with Cython
When we developing a large-scale Python project, we will start to try various acceleration methods.
Read More »[Linux] Speed Up Pure Python Programs with CythonBlog
[Machine Learning] Introduction to Binary Cross Entropy
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
[PyTorch] Set the threshold of Sigmoid output and convert it to binary value
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
[PyCharm] How to Restore the deleted files
When we using PyCharm IDE to develop a project, sometimes we may delete some files by mistake. Maybe we will feel nervous, but in fact we can restore the deleted files.
Read More »[PyCharm] How to Restore the deleted files[PyTorch] Convert Tensor to One-Hot Encoding Type
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
[Python] Convert the value to one-hot type in Numpy
Numpy is an important package for processing data in Python. It is often used for various data analysis tasks.
Read More »[Python] Convert the value to one-hot type in Numpy[Machine Learning] NLLLoss function introduction and program implementation
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
[Linux] Install the Chewing Chinese input method in Ubuntu
After most Linux are installed, the Chinese input method is not installed on the system. However, we can actively install the Chinese input method in the system through configuration.
Read More »[Linux] Install the Chewing Chinese input method in Ubuntu[PyCharm] Introduction of Console、Terminal、Script、TODO
When we using PyCharm IDE for developing, we can divide PyCharm into 3 areas.
Read More »[PyCharm] Introduction of Console、Terminal、Script、TODO
[Keras] How to build a Multi-label Classification Model
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