[Feature] Add NPU adapter for Deformable RoIPool (#2481)

* add npu adapter for deformroipool

* cleancode

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

* Update deform_roi_pool.cpp

docs/en/understand_mmcv/ops.md

@@ -19,7 +19,7 @@ We implement common ops used in detection, segmentation, etc.
 | CornerPool                   |     | √    |     |     |        |
 | Correlation                  |     | √    |     |     |        |
 | Deformable Convolution v1/v2 | √   | √    |     |     |        |
-| Deformable RoIPool           |     | √    | √   |     |        |
+| Deformable RoIPool           |     | √    | √   |     | √      |
 | DiffIoURotated               |     | √    |     |     |        |
 | DynamicScatter               |     | √    |     |     |        |
 | FurthestPointSample          |     | √    |     |     |        |

docs/zh_cn/understand_mmcv/ops.md

@@ -19,7 +19,7 @@ MMCV 提供了检测、分割等任务中常用的算子
 | CornerPool                   |     | √    |     |     |        |
 | Correlation                  |     | √    |     |     |        |
 | Deformable Convolution v1/v2 | √   | √    |     |     |        |
-| Deformable RoIPool           |     | √    | √   |     |        |
+| Deformable RoIPool           |     | √    | √   |     | √      |
 | DiffIoURotated               |     | √    |     |     |        |
 | DynamicScatter               |     | √    |     |     |        |
 | FurthestPointSample          |     | √    |     |     |        |

mmcv/ops/csrc/pytorch/npu/deform_roi_pool.cpp

+#include "pytorch_npu_helper.hpp"
+
+using namespace NPU_NAME_SPACE;
+using namespace std;
+
+void deform_roi_pool_forward_impl(Tensor input, Tensor rois, Tensor offset,
+                                  Tensor output, int pooled_height,
+                                  int pooled_width, float spatial_scale,
+                                  int sampling_ratio, float gamma);
+
+void deform_roi_pool_backward_impl(Tensor grad_output, Tensor input,
+                                   Tensor rois, Tensor offset,
+                                   Tensor grad_input, Tensor grad_offset,
+                                   int pooled_height, int pooled_width,
+                                   float spatial_scale, int sampling_ratio,
+                                   float gamma);
+
+void deform_roi_pool_forward_npu(Tensor input, Tensor rois, Tensor offset,
+                                 Tensor output, int pooled_height,
+                                 int pooled_width, float spatial_scale,
+                                 int sampling_ratio, float gamma) {
+  c10::SmallVector<int64_t, 2> output_sizes = {pooled_height, pooled_width};
+  at::IntArrayRef output_size = at::IntArrayRef(output_sizes);
+  int64_t sampling_ratio_ = (int64_t)sampling_ratio;
+  OpCommand cmd;
+  cmd.Name("DeformableRoiPool")
+      .Input(input)
+      .Input(rois)
+      .Input(offset)
+      .Output(output)
+      .Attr("spatial_scale", spatial_scale)
+      .Attr("output_size", output_size)
+      .Attr("sampling_ratio", sampling_ratio_)
+      .Attr("gamma", gamma)
+      .Run();
+}
+
+void deform_roi_pool_backward_npu(Tensor grad_output, Tensor input, Tensor rois,
+                                  Tensor offset, Tensor grad_input,
+                                  Tensor grad_offset, int pooled_height,
+                                  int pooled_width, float spatial_scale,
+                                  int sampling_ratio, float gamma) {
+  c10::SmallVector<int64_t, 2> output_sizes = {pooled_height, pooled_width};
+  at::IntArrayRef output_size = at::IntArrayRef(output_sizes);
+  int64_t sampling_ratio_ = (int64_t)sampling_ratio;
+  OpCommand cmd;
+  cmd.Name("DeformableRoiPoolGrad")
+      .Input(grad_input)
+      .Input(input)
+      .Input(rois)
+      .Input(offset)
+      .Output(grad_output)
+      .Output(grad_offset)
+      .Attr("output_size", output_size)
+      .Attr("spatial_scale", spatial_scale)
+      .Attr("sample_ratio", sampling_ratio_)
+      .Attr("gamma", gamma)
+      .Run();
+}
+
+REGISTER_NPU_IMPL(deform_roi_pool_forward_impl, deform_roi_pool_forward_npu);
+
+REGISTER_NPU_IMPL(deform_roi_pool_backward_impl, deform_roi_pool_backward_npu);

tests/test_ops/test_deform_roi_pool.py

@@ -5,7 +5,7 @@ import numpy as np
 import pytest
 import torch
 
-from mmcv.utils import IS_CUDA_AVAILABLE, IS_MLU_AVAILABLE
+from mmcv.utils import IS_CUDA_AVAILABLE, IS_MLU_AVAILABLE, IS_NPU_AVAILABLE
 
 _USING_PARROTS = True
 try:
@@ -133,7 +133,11 @@ class TestDeformRoIPool:
         pytest.param(
             'mlu',
             marks=pytest.mark.skipif(
-                not IS_MLU_AVAILABLE, reason='requires MLU support'))
+                not IS_MLU_AVAILABLE, reason='requires MLU support')),
+        pytest.param(
+            'npu',
+            marks=pytest.mark.skipif(
+                not IS_NPU_AVAILABLE, reason='requires NPU support'))
     ])
     @pytest.mark.parametrize('dtype', [
         torch.float,