Custom Op - Channels Last
Channels Last Custom Ops
qonnx.custom_op.channels_last.base_wrapped_op
- class qonnx.custom_op.channels_last.base_wrapped_op.ChannelsLastWrappedOp(onnx_node, onnx_opset_version=11)
Bases:
CustomOp
- execute_node(context, graph)
Execute this CustomOp instance, given the execution context and ONNX graph.
- infer_node_datatype(model)
Set the DataType annotations corresponding to the outputs of this node.
- verify_node()
Verifies that all attributes the node needs are there and that particular attributes are set correctly. Also checks if the number of inputs is equal to the expected number.
- qonnx.custom_op.channels_last.base_wrapped_op.to_channels_first_args(ndim)
Returns the tuple of parameters to transpose a channels last tensor to a channels first one. :param ndim: Number of dimensions of the tensor to be transposed.
- qonnx.custom_op.channels_last.base_wrapped_op.to_channels_last_args(ndim)
Returns the tuple of parameters to transpose a channels first tensor to a channels last one. :param ndim: Number of dimensions of the tensor to be transposed.
qonnx.custom_op.channels_last.batch_normalization
- class qonnx.custom_op.channels_last.batch_normalization.BatchNormalization(onnx_node, onnx_opset_version=11)
Bases:
ChannelsLastWrappedOp
- get_nodeattr_types()
Returns a dict of permitted attributes for node, where: ret_dict[attribute_name] = (dtype, require, default_value, <allowed_values>) - dtype indicates which member of the ONNX AttributeProto will be utilized - require indicates whether this attribute is required - default_val indicates the default value that will be used if the attribute is not set - <allowed_values> (if specified) indicates that this attribute can only be set to one of the values in the set <allowed_values>. If not specified, all values permitted by dtype are allowed.
- make_shape_compatible_op(model)
Returns a standard ONNX op which is compatible with this CustomOp for performing shape inference.
- verify_node()
Verifies that all attributes the node needs are there and that particular attributes are set correctly. Also checks if the number of inputs is equal to the expected number.
qonnx.custom_op.channels_last.conv
- class qonnx.custom_op.channels_last.conv.Conv(onnx_node, onnx_opset_version=11)
Bases:
ChannelsLastWrappedOp
- get_nodeattr_types()
Returns a dict of permitted attributes for node, where: ret_dict[attribute_name] = (dtype, require, default_value, <allowed_values>) - dtype indicates which member of the ONNX AttributeProto will be utilized - require indicates whether this attribute is required - default_val indicates the default value that will be used if the attribute is not set - <allowed_values> (if specified) indicates that this attribute can only be set to one of the values in the set <allowed_values>. If not specified, all values permitted by dtype are allowed.
- make_shape_compatible_op(model)
Returns a standard ONNX op which is compatible with this CustomOp for performing shape inference.
- verify_node()
Verifies that all attributes the node needs are there and that particular attributes are set correctly. Also checks if the number of inputs is equal to the expected number.
qonnx.custom_op.channels_last.max_pool
- class qonnx.custom_op.channels_last.max_pool.MaxPool(onnx_node, onnx_opset_version=11)
Bases:
ChannelsLastWrappedOp
- get_nodeattr_types()
Returns a dict of permitted attributes for node, where: ret_dict[attribute_name] = (dtype, require, default_value, <allowed_values>) - dtype indicates which member of the ONNX AttributeProto will be utilized - require indicates whether this attribute is required - default_val indicates the default value that will be used if the attribute is not set - <allowed_values> (if specified) indicates that this attribute can only be set to one of the values in the set <allowed_values>. If not specified, all values permitted by dtype are allowed.
- make_shape_compatible_op(model)
Returns a standard ONNX op which is compatible with this CustomOp for performing shape inference.
- verify_node()
Verifies that all attributes the node needs are there and that particular attributes are set correctly. Also checks if the number of inputs is equal to the expected number.