List of all items
Structs
- ASTExpr
- ASTGraph
- ASTStmt
- AddConverter
- AveragePoolConverter
- BackendTransformOptions
- BackendTransformerBase
- BatchMatMulConverter
- BoundShapeInferencer
- BoundShapeInferencerBase
- BoundShapeSpec
- Caffe2Annotation
- CastConverter
- ClipConverter
- ClipRangesConverter
- ClipRangesGatherSigridHashConverter
- ClipRangesGatherSigridHashV2Converter
- ConcatAddMulReplaceNaNClipConverter
- ConcatAddMulReplaceNaNClipOp
- ConcatConverter
- ConvConverter
- ConvTransposeConverter
- FCConverter
- GraphMatcher
- GroupAnnotation
- MatchedSubgraph
- MaxPoolConverter
- MulConverter
- OnnxAnnotation
- OnnxifiOp
- OnnxifiOptionHelper
- OnnxifiTransformer
- OnnxifiTransformerOptions
- OptimizationPass
- OutputReshapeInfo
- QShapeInfo
- ReplaceNaNConverter
- ShapeInfo
- SigridHashConverter
- SliceConverter
- TransformSubgraph
- TvmTransformOptions
- TvmTransformer
- VisitorContext
- WorkspaceOptimizationPass
Enums
Traits
Macros
Functions
- addNNPACK
- add_blob_device_options
- add_conv
- adjust_quantized_offset
- adjust_quantized_offset_impl
- alloc_string
- alloc_vector
- blob_to_tensor_descriptor
- change_tensor_bound_shapes
- check
- check_net
- check_shape_info
- clean_up_predict_net
- collect_inputs_and_outputs
- compose_result_net
- compute_dedup_rename_map
- concat_add_mul_nan_clip_elim
- concat_elim
- construct_shape_info_with_default_dim_type
- convert_to_c2net
- convert_to_caffe_2proto
- convert_to_caffe_2proto_with_old_net
- convert_to_neural_net_operator
- convert_to_nqlstring
- convert_to_operator_def
- convert_to_value_info
- convert_to_vec
- copy_descriptor
- create_test
- dead_code_elim
- dealloc_token_strings
- detect_boundary_references
- dump_graph
- enforce_fp_32inputs_to_fp16
- explore
- extract_shape_info_from_tensor_bound_shapes
- fake_fp_16fold_layer_norm
- fake_fp_16fold_layer_norm_quant
- fake_fp_16fold_swish
- fake_fp_16fold_tanh_quant
- fake_fp_16fuse_ops
- fake_fp_16transform
- fetch_inputs_to_if_ops_subnet
- fill_model_info
- find_mutable_operator_by_input
- freeze_quantization_params
- fuse_activation
- fuse_cast_batch_one_hot
- fuse_convBN
- fuse_conv_bnhelper
- fuse_nnpackconv_relu
- gather_fuse_8bit_rowwise_quant_float_mul_lengths_sum_elim
- gen_tensors
- get_blob1st_dim_size
- get_bound_shape_inferencer
- get_dilations
- get_fake_fp_16op_mapping
- get_group
- get_info
- get_info_mut
- get_input_edges
- get_layout
- get_name_for_blob
- get_node_name
- get_nqlstring_for_blob
- get_onnxifi_data_type
- get_or_add_caffe2_annotation
- get_output_edges
- get_pads
- get_shape_info_from_blob
- get_strides
- get_weights_and_inputs
- graph_optimzations
- in_batch_broadcast
- inject_data_edge_indicators
- inject_data_edge_indicators_with_nnmodule
- insert_copies
- is_nnpackconv_relu_efficient
- is_number
- make_tensor_info
- make_tensor_info_with_quantized_flag
- map_onnx_status_to_string
- merge_external_tensors
- merge_fp_32inputs_and_convert_to_fp16
- modify_tensor_shape_dim_size
- onnxifi
- onnxifi_data_type
- onnxifi_type_to_data_type
- optimize
- optimize_for_backend
- optimize_for_mkldnn
- optimize_with_workspace
- parse_block_list_ops
- parse_file
- parse_net_position_list
- parse_shape_info_map_from_string
- parse_string
- prune_unreferered_nodes
- push_op_to_front
- remove_data_edge_indicators
- remove_data_edge_indicators_with_nnmodule
- replace_subgraph
- set_device_option
- set_dim_type_with_first
- set_input_tensor_descriptor_type_and_buffer
- set_input_tensor_descriptor_type_and_buffer_with_int8tensor_cpu
- set_output_tensor_descriptor_type_and_buffer
- show_node
- size_from_dim
- size_to_dim
- split_sparse_lengths_sum_sparse
- strip_shape_info_map
- supports
- take_precedence_over
- to_lower
- to_tensor_proto_data_type
- transform
- tvm_transform
- verify_shape_info
- workspace_optimizations
- wrap_shape_info_into_qtensor_proto
- wrap_shape_info_into_tensor_proto