I’m trying to run this Graph Neural Networks: “https://github.com/guoshnBJTU/ASTGNN” on kaggle, the code still gives me the run summary via wandb however still the status is “Failed” on the website, I wanted to know if it is a problem with the model or with wandb, would anyone be able to help me? At the end of the train after doing all 80 epochs I get this error:

I have a tensor called idx which has integers from 0 to 27. For instance

I have a tensor called idx which has integers from 0 to 27. For instance

I’m currently dealing with PyTorch and Numpy, and I ran across a weird issue. When I run the program, which is simply a PyTorch autoencoder for the MNIST digit dataset, on my windows pc (with cuda), it works just fine. However, when I try to run it on my macbook with either cpu/mps, the program freeze whenever I convert two certain tensors to numpy and check if they are equal.

I’m attempting to train a NN, but am getting an error when I attempt to train it. The data I’m using is .tif images and masks. The images are 3 band. I’ve tried to follow other questions which encountered the same issue to no avail. Any help would be greatly appreciated! I receive the following error when running:

I need to sum a normal numpy array with an empty array

I need to sum a normal numpy array with an empty array

Suppose I have tensor with size [2, 64, 64], I want to stack it either horizontally or vertically along the first dimension, so I want to stack [0,:,:] and [1,:,:] and get a [128,64] or a [64,128] tensor.