tvm_book.transforms.graphpack
#
Relay 实现的 graph packing
Module Contents#
Functions#
|
Round the channel const variant if the value not divisible by cfactor_out |
|
Pad the constant if the shape[0] not divisible by cfactor_out. |
|
Get node shape. |
|
Get node type. |
|
Pack the data channel dimension. |
|
Pack a constant parameter. |
|
Pack the weight into packed format. |
|
Pack the weight into packed format. |
|
convert shape into tuple. |
|
Unpack the data channel dimension. |
|
Pad the weight if the shape[0] not divisible by cfactor_out. |
|
Pad the weight if the shape[1] not divisible by cfactor_out. |
- tvm_book.transforms.graphpack._channel_const_match(channel_length, cfactor_out)[源代码]#
Round the channel const variant if the value not divisible by cfactor_out
- tvm_book.transforms.graphpack._const_shape_match(data, dshape, cfactor_out)[源代码]#
Pad the constant if the shape[0] not divisible by cfactor_out.
- tvm_book.transforms.graphpack._pack_batch_channel(data, dshape, bfactor, cfactor)[源代码]#
Pack the data channel dimension.
- tvm_book.transforms.graphpack._pack_const(data, dshape, dtype, bfactor, cfactor)[源代码]#
Pack a constant parameter.
- tvm_book.transforms.graphpack._pack_weight(data, dshape, cfactor)[源代码]#
Pack the weight into packed format.
- tvm_book.transforms.graphpack._pack_weight_conv2d_transpose(data, dshape, cfactor)[源代码]#
Pack the weight into packed format.
- tvm_book.transforms.graphpack._unpack_batch_channel(data, old_shape, unpack_transpose=False)[源代码]#
Unpack the data channel dimension.