When I using PyTorch to train a model, I often use GPU_A to train the model, save model. But if I load the model I saved to test some new data, I always put the new data in a different GPU, we called it GPU_B.
Read More »[PyTorch] How to check which GPU device our data used
Python is a simple and beautiful program language. Today I will record how to learn Python quickly. The cost time, I think it’s just only one hour.
Read More »Easy Python Tutorial Speed Run —— Only one hour When we using the famous Python framework: PyTorch, to build our model, if we can visualize our model, that's a cool idea.
In this way, we can check our model layer, output shape, and avoid our model mismatch.
Read More »[PyTorch] Using "torchsummary" to plot your model structure Today when I use Python to process a NLP task, I get a error message:
OSError: [E050] Can't find model 'en'. It doesn't seem to be a shortcut link, a Python package or a valid path to a data directory.I think if we use Pytorch framework to train a model, the commonly error messages are "Model mismatch" and the following error:
Read More »[Solved][PyTorch] RuntimeError: Expected object of scalar type Float but got scalar type Long for argument
Recently, I encountered a bottleneck in the training of deep learning models. The most important aspect is the speed of training.
Read More »[Linux] Store the data into RAM disk to speed up the program
Jupyter Notebook is a Python Editor (?) or you may think it is like an IDE, which is implemented by IPython.
Read More »[Linux] How to use remote Jupyter Notebook via SSH Today, when I using PyTorch to build a LSTM model, I got an error occured:
LSTM RuntimeError: input must have 3 dimensions, got 2Today, when I load a model I trained with PyTorch and I want to use it to process some new data, I got a error report:
Read More »[Solved] RuntimeError: Input and parameter tensors are not at the same device, found input tensor at cpu and parameter tensor at cuda:0 Today, if we need to split our data for training our model —— we need to split training data and test data. We use "training data" to train our model and check it never peep our "test data", it is very important, because our "test data" can assess the quality of our model.
Read More »[Scikit-Learn] Using "train_test_split()" to split your data