cpu box_iou_rotated.cpp deform_conv.cpp modulated_deform_conv.cpp nms.cpp nms_rotated.cpp pixel_group.cpp points_in_boxes.cpp psamask.cpp roi_align.cpp roi_align_rotated.cpp voxelization.cpp cuda box_iou_rotated_cuda.cu cudabind.cpp deform_conv_cuda.cu furthest...
Include torchvision_12.json in the sdist package (#2039) make iou3d.boxes_iou3d actually calculate 3D IoU (#2018) Fix batched_nms for rotated box and add type hints for nms.py (#2006) Type Hints Thanks to contributors for their efforts, mmcv has added type hints, which makes the code...
copying mmcv\ops\csrc\common\cuda\points_in_boxes_cuda_kernel.cuh -> build\lib.win-amd64-3.7\mmcv\ops\csrc\common\cuda copying mmcv\ops\csrc\common\cuda\psamask_cuda_kernel.cuh -> build\lib.win-amd64-3.7\mmcv\ops\csrc\common\cuda copying mmcv\ops\csrc\common\cuda\roi_align_cuda_kerne...
points_in_boxes_cpu,points_in_boxes_gpu) 1414 from.sparse_blockimport(SparseBasicBlock,SparseBottleneck, 1515 make_sparse_convmodule) 16+ from.utilsimportget_compiler_version,get_compiling_cuda_version 1617 from.voxelimportDynamicScatter,Voxelization,dynamic_scatter,voxelization ...
3.286 copying mmcv/ops/csrc/pytorch/cpu/pixel_group.cpp -> build/lib.linux-aarch64-3.11/mmcv/ops/csrc/pytorch/cpu 3.286 copying mmcv/ops/csrc/pytorch/cpu/points_in_boxes.cpp -> build/lib.linux-aarch64-3.11/mmcv/ops/csrc/pytorch/cpu 3.286 copying mmcv/ops/csrc/pytorch/cpu/psamask.cpp ...
TORCH_CHECK((boxes.scalar_type() == at::ScalarType::Float), "The type of boxes tensor passed in nms_npu should be float"); int64_t offset_64 = offset; at::Tensor iou_threshold_y = at_npu::native::OpPreparation::ApplyTensor( {}, boxes.options().dtype(at::kFloat), boxes) .fil...
GatherPoints √ √ GroupPoints √ Iou3d √ √ KNN √ MaskedConv √ √ √ MergeCells √ MinAreaPolygon √ ModulatedDeformConv2d √ √ √ √ MultiScaleDeformableAttn √ √ NMS √ √ √ √ NMSRotated √ √ √ √ NMSQuadri √ √ PixelGroup √ PointsInBoxes √ √ PointsInPo...
int *>(output_size.cpu().data_ptr()); auto ret = .to(boxes.options().dtype(at::kLong)); return retslice(0, 0, output_num); } 446 changes: 446additions & 0 deletions 446 mmcv/ops/csrc/pytorch/mlu/sparse_convmlu.cpp Show comments View file Edit file Delete ...
default value for this argument is currently False, but it will be changed to True in Numba 0.59.0. See https://numba.readthedocs.io/en/stable/reference/deprecation.html#deprecation-of-object-mode-fall-back-behaviour-when-using-jit for details. def compute_2d_bbox_xyxy_from_pose_v2(points...
The unexpected results still exist in the latest version. Describe the Issue This bug occurs when I use mmrotate, but it's caused by the Unexpected polys value. So I think it might be a mmcv bug. For some specific pts tensor value: pts = torch.load('pts.pt').detach().cpu().cuda...