mirror of
https://github.com/saymrwulf/pytorch.git
synced 2026-05-14 20:57:59 +00:00
2fe7fc681d
Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/34578 Right now C10_EXPORT_CAFFE2_OP_TO_C10_CPU didn't work on mobile since we disabled some code paths. This diff added a new macro to enable these code paths so we can register caffe2 ops in PT mobile. Test Plan: verified caffe2 ops are registered in PT mobile (on the whole stack) ``` _caffe2::BBoxConcatBatchSplits(Tensor[] input_list, Tensor[]? _caffe2_preallocated_outputs=None) -> (Tensor output) _caffe2::BBoxTransform(Tensor rois, Tensor deltas, Tensor im_info, float[] weights, bool apply_scale, bool rotated, bool angle_bound_on, int angle_bound_lo, int angle_bound_hi, float clip_angle_thresh, bool legacy_plus_one, Tensor[]? _caffe2_preallocated_outputs=None) -> (Tensor output_0, Tensor output_1) _caffe2::BoxWithNMSLimit(Tensor scores, Tensor boxes, Tensor batch_splits, float score_thresh, float nms, int detections_per_im, bool soft_nms_enabled, str soft_nms_method, float soft_nms_sigma, float soft_nms_min_score_thres, bool rotated, bool cls_agnostic_bbox_reg, bool input_boxes_include_bg_cls, bool output_classes_include_bg_cls, bool legacy_plus_one, Tensor[]? _caffe2_preallocated_outputs=None) -> (Tensor scores, Tensor boxes, Tensor classes, Tensor batch_splits, Tensor keeps, Tensor keeps_size) _caffe2::GenerateProposals(Tensor scores, Tensor bbox_deltas, Tensor im_info, Tensor anchors, float spatial_scale, int pre_nms_topN, int post_nms_topN, float nms_thresh, float min_size, bool angle_bound_on, int angle_bound_lo, int angle_bound_hi, float clip_angle_thresh, bool legacy_plus_one, Tensor[]? _caffe2_preallocated_outputs=None) -> (Tensor output_0, Tensor output_1) _caffe2::HeatmapMaxKeypoint(Tensor heatmaps, Tensor bboxes_in, bool should_output_softmax=True, Tensor[]? _caffe2_preallocated_outputs=None) -> (Tensor keypoints) _caffe2::ResizeNearest(Tensor X, str order, float width_scale, float height_scale, Tensor[]? _caffe2_preallocated_outputs=None) -> (Tensor Y) _caffe2::RoIAlign(Tensor features, Tensor rois, str order, float spatial_scale, int pooled_h, int pooled_w, int sampling_ratio, bool aligned, Tensor[]? _caffe2_preallocated_outputs=None) -> (Tensor) Reviewed By: dreiss Differential Revision: D20128254 fbshipit-source-id: 49a837dddc431eb528b5c72ffdfe0d0131cd10b4 |
||
|---|---|---|
| .. | ||
| hip | ||
| nomnigraph | ||
| __init__.py | ||
| allocator.cc | ||
| allocator.h | ||
| asan.h | ||
| blob.h | ||
| blob_gpu_test.cc | ||
| blob_serialization.cc | ||
| blob_serialization.h | ||
| blob_serialization_gpu.cc | ||
| blob_serializer_base.h | ||
| blob_stats.cc | ||
| blob_stats.h | ||
| blob_test.cc | ||
| CMakeLists.txt | ||
| common.cc | ||
| common.h | ||
| common_cudnn.cc | ||
| common_cudnn.h | ||
| common_gpu.cc | ||
| common_gpu.h | ||
| common_omp.h | ||
| common_test.cc | ||
| context.cc | ||
| context.h | ||
| context_base.cc | ||
| context_base.h | ||
| context_gpu.cu | ||
| context_gpu.h | ||
| context_gpu_test.cc | ||
| context_test.cc | ||
| cudnn_wrappers.h | ||
| db.cc | ||
| db.h | ||
| event.cc | ||
| event.h | ||
| event_cpu.h | ||
| event_gpu.cc | ||
| event_gpu_test.cc | ||
| event_test.cc | ||
| export_c10_op_to_caffe2.cc | ||
| export_c10_op_to_caffe2.h | ||
| export_caffe2_op_to_c10.h | ||
| flags.h | ||
| graph.cc | ||
| graph.h | ||
| graph_test.cc | ||
| init.cc | ||
| init.h | ||
| init_denormals.cc | ||
| init_intrinsics_check.cc | ||
| init_omp.cc | ||
| init_test.cc | ||
| int8_serialization.cc | ||
| logging.h | ||
| macros.h | ||
| macros.h.in | ||
| memonger.cc | ||
| memonger.h | ||
| module.cc | ||
| module.h | ||
| module_test.cc | ||
| net.cc | ||
| net.h | ||
| net_async_base.cc | ||
| net_async_base.h | ||
| net_async_scheduling.cc | ||
| net_async_scheduling.h | ||
| net_async_task.cc | ||
| net_async_task.h | ||
| net_async_task_future.cc | ||
| net_async_task_future.h | ||
| net_async_task_graph.cc | ||
| net_async_task_graph.h | ||
| net_async_tracing.cc | ||
| net_async_tracing.h | ||
| net_async_tracing_test.cc | ||
| net_dag_utils.cc | ||
| net_dag_utils.h | ||
| net_dag_utils_test.cc | ||
| net_gpu_test.cc | ||
| net_parallel.cc | ||
| net_parallel.h | ||
| net_simple.cc | ||
| net_simple.h | ||
| net_simple_refcount.cc | ||
| net_simple_refcount.h | ||
| net_simple_refcount_test.cc | ||
| net_test.cc | ||
| numa.cc | ||
| numa.h | ||
| observer.h | ||
| observer_test.cc | ||
| operator.cc | ||
| operator.h | ||
| operator_gpu_test.cc | ||
| operator_gradient.h | ||
| operator_schema.cc | ||
| operator_schema.h | ||
| operator_schema_test.cc | ||
| operator_test.cc | ||
| parallel_net_test.cc | ||
| plan_executor.cc | ||
| plan_executor.h | ||
| prof_dag_counters.cc | ||
| prof_dag_counters.h | ||
| qtensor.cc | ||
| qtensor.h | ||
| qtensor_serialization.cc | ||
| qtensor_serialization.h | ||
| scope_guard.h | ||
| static_tracepoint.h | ||
| static_tracepoint_elfx86.h | ||
| stats.cc | ||
| stats.h | ||
| stats_test.cc | ||
| storage.h | ||
| tensor.cc | ||
| tensor.h | ||
| tensor_impl.h | ||
| tensor_int8.cc | ||
| tensor_int8.h | ||
| test_utils.cc | ||
| test_utils.h | ||
| timer.h | ||
| timer_test.cc | ||
| transform.cc | ||
| transform.h | ||
| transform_test.cc | ||
| types.cc | ||
| types.h | ||
| workspace.cc | ||
| workspace.h | ||
| workspace_test.cc | ||