Clues to solve ValueError: res["lidar"]["bev_map"] axes don't match array

[MaxChanger]

Hi, thanks for the great work. And I meet the same issue with issue#2, as following,

  File "~/Repo/FutureDet/det3d/datasets/pipelines/preprocess.py", line 221, in __call__
    res["lidar"]["bev_map"] = bev.transpose(2, 0, 1)
ValueError: axes don't match array

Although I use the v1.0-mini nuscenes data, I don't think it matters.
After my debugging, I found that the problem lies in the bev process of generating info_xxx.pkl, as follows

FutureDet/det3d/datasets/nuscenes/nusc_common.py

Lines 508 to 509 in 960115e

	ego_map = nusc.get_ego_centric_map(sweeps[0]["sample_data_token"])
	bev = cv2.resize(ego_map, dsize=(180, 180), interpolation=cv2.INTER_CUBIC)

FutureDet/det3d/datasets/nuscenes/nusc_common.py

Line 544 in 960115e

info["bev"] = bev

The BEV image is loaded from the sdk in your another repo python-sdk/nuscenes/nuscenes.py#L837-L842

But their dimensions are (h,w), such as ego_map.shape: (900, 900), bev.shape: (180, 180), so bev.transpose(2, 0, 1) is wrong operations for this.

Hope that can provide clues to solve the problem.

[YiiiMeng]

I also encounter this problem, and I try to uncomment the line 211 and 214 (just above the bug line) in the preprocess.py, and it works.

[MaxChanger]

Thanks @YiMengNB, in issue#2, the author said''res["lidar"]["bev_map"] should be an empty numpy array of size (1, 180, 180)'' .
So, I simply added a dimension to bev before this line, such as bev = bev[None, :, :], it also work. The predicted output can be obtained normally.

But I'm not sure if this is completely correct and consistent with the original intent.

[chenkangyang]

This is reasonable to get 6 channel bevmap
Cuz

if self.bev_map:
    self.bev_conv = nn.Sequential(
        nn.Conv2d(6, 16, kernel_size=3, padding=1, bias=True), nn.BatchNorm2d(16), nn.ReLU(inplace=True),
        nn.Conv2d(16, 32, kernel_size=3, padding=1, bias=True), nn.BatchNorm2d(32), nn.ReLU(inplace=True),
        nn.Conv2d(32, share_conv_channel, kernel_size=3, padding=1, bias=True), nn.BatchNorm2d(share_conv_channel), nn.ReLU(inplace=True),
    )

in center_head.py