update cuda codes to support PyTorch 1.5

pcdet/ops/iou3d_nms/src/iou3d_cpu.cpp

@@ -13,7 +13,19 @@ All Rights Reserved 2020.
 #include <cuda_runtime_api.h>
 #include "iou3d_cpu.h"
 
-#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
+#define CHECK_CUDA(x) do { \
+  if (!x.type().is_cuda()) { \
+    fprintf(stderr, "%s must be CUDA tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_CONTIGUOUS(x) do { \
+  if (!x.is_contiguous()) { \
+    fprintf(stderr, "%s must be contiguous tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
 
 inline float min(float a, float b){
     return a > b ? b : a;

pcdet/ops/iou3d_nms/src/iou3d_nms.cpp

@@ -11,8 +11,18 @@ All Rights Reserved 2019-2020.
 #include <cuda_runtime_api.h>
 #include "iou3d_nms.h"
 
-#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
-#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
+#define CHECK_CUDA(x) do { \
+  if (!x.type().is_cuda()) { \
+    fprintf(stderr, "%s must be CUDA tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_CONTIGUOUS(x) do { \
+  if (!x.is_contiguous()) { \
+    fprintf(stderr, "%s must be contiguous tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
 #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
 
 #define DIVUP(m,n) ((m) / (n) + ((m) % (n) > 0))
@@ -80,7 +90,6 @@ int boxes_iou_bev_gpu(at::Tensor boxes_a, at::Tensor boxes_b, at::Tensor ans_iou
 int nms_gpu(at::Tensor boxes, at::Tensor keep, float nms_overlap_thresh){
     // params boxes: (N, 7) [x, y, z, dx, dy, dz, heading]
     // params keep: (N)
-
     CHECK_INPUT(boxes);
     CHECK_CONTIGUOUS(keep);
 

pcdet/ops/pointnet2/pointnet2_stack/src/ball_query.cpp

@@ -14,8 +14,18 @@ All Rights Reserved 2019-2020.
 
 extern THCState *state;
 
-#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
-#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
+#define CHECK_CUDA(x) do { \
+  if (!x.type().is_cuda()) { \
+    fprintf(stderr, "%s must be CUDA tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_CONTIGUOUS(x) do { \
+  if (!x.is_contiguous()) { \
+    fprintf(stderr, "%s must be contiguous tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
 #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
 
 int ball_query_wrapper_stack(int B, int M, float radius, int nsample,

pcdet/ops/pointnet2/pointnet2_stack/src/group_points.cpp

@@ -13,8 +13,18 @@ All Rights Reserved 2019-2020.
 #include "group_points_gpu.h"
 
 extern THCState *state;
-#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
-#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
+#define CHECK_CUDA(x) do { \
+  if (!x.type().is_cuda()) { \
+    fprintf(stderr, "%s must be CUDA tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_CONTIGUOUS(x) do { \
+  if (!x.is_contiguous()) { \
+    fprintf(stderr, "%s must be contiguous tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
 #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
 
 

pcdet/ops/pointnet2/pointnet2_stack/src/interpolate.cpp

@@ -17,6 +17,20 @@ All Rights Reserved 2019-2020.
 
 extern THCState *state;
 
+#define CHECK_CUDA(x) do { \
+  if (!x.type().is_cuda()) { \
+    fprintf(stderr, "%s must be CUDA tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_CONTIGUOUS(x) do { \
+  if (!x.is_contiguous()) { \
+    fprintf(stderr, "%s must be contiguous tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
+
 
 void three_nn_wrapper_stack(at::Tensor unknown_tensor, 
     at::Tensor unknown_batch_cnt_tensor, at::Tensor known_tensor, 
@@ -28,6 +42,12 @@ void three_nn_wrapper_stack(at::Tensor unknown_tensor,
     // Return:
     // dist: (N1 + N2 ..., 3)  l2 distance to the three nearest neighbors
     // idx: (N1 + N2 ..., 3)  index of the three nearest neighbors
+    CHECK_INPUT(unknown_tensor);
+    CHECK_INPUT(unknown_batch_cnt_tensor);
+    CHECK_INPUT(known_tensor);
+    CHECK_INPUT(known_batch_cnt_tensor);
+    CHECK_INPUT(dist2_tensor);
+    CHECK_INPUT(idx_tensor);
 
     int batch_size = unknown_batch_cnt_tensor.size(0);
     int N = unknown_tensor.size(0);
@@ -50,6 +70,10 @@ void three_interpolate_wrapper_stack(at::Tensor features_tensor,
     // weight_tensor: [N1 + N2 ..., 3]
     // Return:
     // out_tensor: (N1 + N2 ..., C)
+    CHECK_INPUT(features_tensor);
+    CHECK_INPUT(idx_tensor);
+    CHECK_INPUT(weight_tensor);
+    CHECK_INPUT(out_tensor);
 
     int N = out_tensor.size(0);
     int channels = features_tensor.size(1);
@@ -69,6 +93,10 @@ void three_interpolate_grad_wrapper_stack(at::Tensor grad_out_tensor, at::Tensor
     // weight_tensor: [N1 + N2 ..., 3]
     // Return:
     // grad_features_tensor: (M1 + M2 ..., C)
+    CHECK_INPUT(grad_out_tensor);
+    CHECK_INPUT(idx_tensor);
+    CHECK_INPUT(weight_tensor);
+    CHECK_INPUT(grad_features_tensor);
 
     int N = grad_out_tensor.size(0);
     int channels = grad_out_tensor.size(1);

pcdet/ops/pointnet2/pointnet2_stack/src/sampling.cpp

@@ -6,11 +6,28 @@
 #include "sampling_gpu.h"
 
 extern THCState *state;
+#define CHECK_CUDA(x) do { \
+  if (!x.type().is_cuda()) { \
+    fprintf(stderr, "%s must be CUDA tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_CONTIGUOUS(x) do { \
+  if (!x.is_contiguous()) { \
+    fprintf(stderr, "%s must be contiguous tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
 
 
 int furthest_point_sampling_wrapper(int b, int n, int m,
     at::Tensor points_tensor, at::Tensor temp_tensor, at::Tensor idx_tensor) {
 
+    CHECK_INPUT(points_tensor);
+    CHECK_INPUT(temp_tensor);
+    CHECK_INPUT(idx_tensor);
+
     const float *points = points_tensor.data<float>();
     float *temp = temp_tensor.data<float>();
     int *idx = idx_tensor.data<int>();

pcdet/ops/roiaware_pool3d/src/roiaware_pool3d.cpp

@@ -11,9 +11,9 @@ All Rights Reserved 2019-2020.
 #include <assert.h>
 
 
-#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
-#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
-#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
+//#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
+//#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
+//#define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
 
 
 void roiaware_pool3d_launcher(int boxes_num, int pts_num, int channels, int max_pts_each_voxel,
@@ -36,12 +36,12 @@ int roiaware_pool3d_gpu(at::Tensor rois, at::Tensor pts, at::Tensor pts_feature,
     // params pooled_features: (N, out_x, out_y, out_z, C)
     // params pool_method: 0: max_pool 1: avg_pool
 
-    CHECK_INPUT(rois);
-    CHECK_INPUT(pts);
-    CHECK_INPUT(pts_feature);
-    CHECK_INPUT(argmax);
-    CHECK_INPUT(pts_idx_of_voxels);
-    CHECK_INPUT(pooled_features);
+//    CHECK_INPUT(rois);
+//    CHECK_INPUT(pts);
+//    CHECK_INPUT(pts_feature);
+//    CHECK_INPUT(argmax);
+//    CHECK_INPUT(pts_idx_of_voxels);
+//    CHECK_INPUT(pooled_features);
 
     int boxes_num = rois.size(0);
     int pts_num = pts.size(0);
@@ -72,10 +72,10 @@ int roiaware_pool3d_gpu_backward(at::Tensor pts_idx_of_voxels, at::Tensor argmax
     // params grad_in: (npoints, C), return value
     // params pool_method: 0: max_pool 1: avg_pool
 
-    CHECK_INPUT(pts_idx_of_voxels);
-    CHECK_INPUT(argmax);
-    CHECK_INPUT(grad_out);
-    CHECK_INPUT(grad_in);
+//    CHECK_INPUT(pts_idx_of_voxels);
+//    CHECK_INPUT(argmax);
+//    CHECK_INPUT(grad_out);
+//    CHECK_INPUT(grad_in);
 
     int boxes_num = pts_idx_of_voxels.size(0);
     int out_x = pts_idx_of_voxels.size(1);
@@ -100,9 +100,9 @@ int points_in_boxes_gpu(at::Tensor boxes_tensor, at::Tensor pts_tensor, at::Tens
     // params pts: (B, npoints, 3) [x, y, z]
     // params boxes_idx_of_points: (B, npoints), default -1
 
-    CHECK_INPUT(boxes_tensor);
-    CHECK_INPUT(pts_tensor);
-    CHECK_INPUT(box_idx_of_points_tensor);
+//    CHECK_INPUT(boxes_tensor);
+//    CHECK_INPUT(pts_tensor);
+//    CHECK_INPUT(box_idx_of_points_tensor);
 
     int batch_size = boxes_tensor.size(0);
     int boxes_num = boxes_tensor.size(1);
@@ -145,9 +145,9 @@ int points_in_boxes_cpu(at::Tensor boxes_tensor, at::Tensor pts_tensor, at::Tens
     // params pts: (num_points, 3) [x, y, z]
     // params pts_indices: (N, num_points)
 
-    CHECK_CONTIGUOUS(boxes_tensor);
-    CHECK_CONTIGUOUS(pts_tensor);
-    CHECK_CONTIGUOUS(pts_indices_tensor);
+//    CHECK_CONTIGUOUS(boxes_tensor);
+//    CHECK_CONTIGUOUS(pts_tensor);
+//    CHECK_CONTIGUOUS(pts_indices_tensor);
 
     int boxes_num = boxes_tensor.size(0);
     int pts_num = pts_tensor.size(0);

pcdet/ops/roipoint_pool3d/src/roipoint_pool3d.cpp

 #include <torch/serialize/tensor.h>
 #include <torch/extension.h>
 
-
-#define CHECK_CUDA(x) AT_CHECK(x.type().is_cuda(), #x, " must be a CUDAtensor ")
-#define CHECK_CONTIGUOUS(x) AT_CHECK(x.is_contiguous(), #x, " must be contiguous ")
+#define CHECK_CUDA(x) do { \
+  if (!x.type().is_cuda()) { \
+    fprintf(stderr, "%s must be CUDA tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
+#define CHECK_CONTIGUOUS(x) do { \
+  if (!x.is_contiguous()) { \
+    fprintf(stderr, "%s must be contiguous tensor at %s:%d\n", #x, __FILE__, __LINE__); \
+    exit(-1); \
+  } \
+} while (0)
 #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x)
 
 

setup.py

@@ -27,7 +27,7 @@ def write_version_to_file(version, target_file):
 
 
 if __name__ == '__main__':
-    version = '0.2.0+%s' % get_git_commit_number()
+    version = '0.3.0+%s' % get_git_commit_number()
     write_version_to_file(version, 'pcdet/version.py')
 
     setup(
@@ -37,7 +37,7 @@ if __name__ == '__main__':
         install_requires=[
             'numpy',
             'torch>=1.1',
-            'spconv==1.0',
+            'spconv',
             'numba',
             'tensorboardX',
             'easydict',