Last Updated on 2023-02-17 by Clay
Today when I reading the document of the “Transformers” package which Hugging Face developed, I suddenly discovered the model I build, its state is “eval()”, not “train()”. It seems that as long as we use “from_pretrained()” method is the default state “eval()”.
Read More »[PyTorch] How to check the model state is “train()” or “eval()”Last Updated on 2021-07-05 by Clay
This is very common error message in PyTorch.
RuntimeError: bool value of Tensor with more than one value is ambiguousLast Updated on 2021-07-05 by Clay
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
Last Updated on 2021-07-05 by Clay
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 hourLast Updated on 2021-07-05 by Clay
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 structureLast Updated on 2021-07-05 by Clay
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.Last Updated on 2021-07-01 by Clay
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
Last Updated on 2021-07-01 by Clay
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
Last Updated on 2021-06-28 by Clay
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 SSHLast Updated on 2021-06-28 by Clay
Today, when I using PyTorch to build a LSTM model, I got an error occured:
LSTM RuntimeError: input must have 3 dimensions, got 2