pytorch RuntimeError: Expected object of scalar type Double but got scalar type Float

Now that I have more experience with pytorch, I think I can explain the error message. It seems that the line

RuntimeError: Expected object of scalar type Double but got scalar type Float for argument #2 'mat2' in call to _th_mm

is actually refering to the weights of the linear layer when the matrix multiplication is called. Since the input is double while the weights are float, it makes sense for the line

output = input.matmul(weight.t())

to expect the weights to be double.

Tags:

Python

Numpy

Pytorch

Related

"SyntaxError: Cannot use import statement outside a module" when running a Jest test with Vue Js gitlab ci error could not translate host name "postgres" to address: Name does not resolve Is there any method to run perf under WSL? Is it true that in multiprocessing, each process gets it's own GIL in CPython? How different is that from creating new runtimes? How to write length function for all Monoids PyTorch Geometric CUDA installation issues on Google Colab How to show the bucket name when using RANGE_BUCKET in bigquery In C++ what is the point of std::array if the size has to be determined at compile time? TypeError [ERR_INVALID_ARG_TYPE]: The "path" argument must be of type string. Received type undefined raised when starting react app How can I get the click event inside an innerHTML? Argument of type 'number' is not assignable to parameter of type 'never' in array.includes() angular 9 library publish error "Trying to publish a package that has been compiled by Ivy"

Recent Posts