i need to convert a frame of the video (which is a nparray) to a pytorch tensor, do some particular actions with it and convert it back but i’m struggling

I encountered a RuntimeError: numel: integer multiplication overflow while attempting to index a PyTorch tensor using a boolean mask tensor. This error occurs when I try to filter a tensor based on the boolean values in another tensor.

I have a list of float values like the following which are ids in my data and in the dataset they are originally like 11.0,11.2,16.2,… but when I try to put them in a Data object like the following:

I have a list of tensors and I want to check if any of the values within that list is not in a set containing tensor values, here is what I have tried but I see this code finds all the values are not in unique_values which is wrong!

I have a 3 lists of ids (sequence[i].id_column) and when I print them, I see (I don’t know for what reason) the format of the second list changes! for example 4.2 becomes 4.2e+00. I tried to add all those lists to a set (unique_values) and then convert it to a list (unique_values_tensor) to make the values inside it to be unique (unique_values-sorted). however I see unique_values_sorted has different format. Please help me how can I keep all these three lists in a list that has unique values of them (not having repeated values) and in the correct format like the values displayed for the first id_column_tensor.

I have a problem with PyTorch, cause I am a begginer. I am trying to implement some encoding algorithm using vocabularies and torch.zero matrix. But I have a trouble, it did not worked properly: