Thanks for sending an issue! Please fill in the following template to help quickly solve your problem.
reduce非连续场景,输入地址计算在某些场景下,计算错误
Ascend950
Entering function params: x: aclTensor(view_shape = [7, 257, 17, 15], view_strides = [131070, 510, 30, 2], view_offset = 0, view_format = NCHW, storage_shape = [917490], storage_format = NCHW, ori_shape = [7, 257, 17, 15], ori_format = NCHW, data_type = DT_FLOAT, device_ptr = 0x12004c600000), axes: aclTensor(view_shape = [1], view_strides = [1], view_offset = 0, view_format = ND, storage_shape = [1], storage_format = ND, ori_shape = [1], ori_format = ND, data_type = DT_INT64, device_ptr = 0xfffde2eac360), keepDim: 1, noopWithEmptyAxes: 1, out: aclTensor(view_shape = [7, 1, 17, 15]
精度pass
NA
Thanks for sending an issue! Please fill in the following template to help quickly solve your problem.
Describe the current behavior / 问题描述 (Mandatory / 必填)
reduce非连续场景,输入地址计算在某些场景下,计算错误
Environment / 环境信息 (Mandatory / 必填)
Ascend950
Steps to reproduce the issue / 重现步骤 (Mandatory / 必填)
Entering function params: x: aclTensor(view_shape = [7, 257, 17, 15], view_strides = [131070, 510, 30, 2], view_offset = 0, view_format = NCHW, storage_shape = [917490], storage_format = NCHW, ori_shape = [7, 257, 17, 15], ori_format = NCHW, data_type = DT_FLOAT, device_ptr = 0x12004c600000), axes: aclTensor(view_shape = [1], view_strides = [1], view_offset = 0, view_format = ND, storage_shape = [1], storage_format = ND, ori_shape = [1], ori_format = ND, data_type = DT_INT64, device_ptr = 0xfffde2eac360), keepDim: 1, noopWithEmptyAxes: 1, out: aclTensor(view_shape = [7, 1, 17, 15]
Describe the expected behavior / 预期结果 (Mandatory / 必填)
精度pass
Related log / screenshot / 日志 / 截图 (Mandatory / 必填)
NA
Special notes for this issue/备注 (Optional / 选填)