A short overview over the PyTorch operations most relevant for this course. The full documentation can be accessed here.
Operation |
Description |
Create a tensor of a specific shape with uninitialized data |
|
Create a tensor of a specific shape and fill it with zeros |
|
Create a tensor of a specific shape and fill it with ones |
|
Create a tensor with the given data |
|
Create a sparse tensor with the given indices and values |
|
Perform matrix multiplication |
|
Find the indices where a tensor contains non-zero values |
|
Return the sorted values and sorting permutation of a tensor |
|
Concatenate a list of tensors along a new dimension |
|
Concatenate a list of tensors along an existing dimension |
|
Sum a tensor along one or more dimensions |
|
Average a tensor along one or more dimensions |
|
Calculate the norm of tensor along the given dimensions |
|
Return a new tensor containing values from one of two sources depending on a condition |
|
Get top k largest or smallest values and their indices from a tensor |
|
Apply the sigmoid function to all values of a tensor |
|
Perform softmax normalization |
|
Select indices from a tensor along a specific dimension |
|
Create a tensor from a range |
|
Sample from a multinomial distribution |