Name |
Last commit
|
Last update |
---|---|---|
.. | ||
annotation | ||
contrib | ||
image | ||
nn | ||
vision | ||
__init__.py | ||
_algorithm.py | ||
_make.py | ||
_reduce.py | ||
_tensor.py | ||
_tensor_grad.py | ||
_transform.py | ||
algorithm.py | ||
op.py | ||
op_attrs.py | ||
reduce.py | ||
tensor.py | ||
transform.py |
* [Relay] Rewrite pass. This pass transforms an expression to other expression. This pass has many usecases * Replace a expr to another expr, if the other expr has faster performance. * For ASICs, we might want to modify the inputs to adapt to the HW support. * Alter op layout can work in conjunction with this pass. The supporting usecase is the Intel i8 x i8 conv. Intel HW supports u8 x i8 conv in HW. Using this pass, we can replace an i8 x i8 conv to a sequence of operators where one of the operators is now u8 x i8 conv. This will also help automatic quantizaion performance. * Better API name. * Removing the conv2d legalization for x86. Will send a separate PR. * Test name changes. * Registering one funtion to register FTVMLegalize. * Better comments.
Name |
Last commit
|
Last update |
---|---|---|
.. | ||
annotation | Loading commit data... | |
contrib | Loading commit data... | |
image | Loading commit data... | |
nn | Loading commit data... | |
vision | Loading commit data... | |
__init__.py | Loading commit data... | |
_algorithm.py | Loading commit data... | |
_make.py | Loading commit data... | |
_reduce.py | Loading commit data... | |
_tensor.py | Loading commit data... | |
_tensor_grad.py | Loading commit data... | |
_transform.py | Loading commit data... | |
algorithm.py | Loading commit data... | |
op.py | Loading commit data... | |
op_attrs.py | Loading commit data... | |
reduce.py | Loading commit data... | |
tensor.py | Loading commit data... | |
transform.py | Loading commit data... |