尝试复现训练和评测的时候报错

[WuYiYiYi]

hello，非常感谢您的开源，在我按照quick_start.md尝试运行的时候遇到了以下几个问题，向您请教下：

1. train

bash local_train.sh sparse4dv3_temporal_r50_1x8_bs6_256x704 执行的时候报错：
File "/home/amax/workspace/sourc_code/Sparse4D-main/projects/mmdet3d_plugin/models/sparse4d_head.py", line 456, in loss
reg_loss = self.loss_reg(
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/amax/workspace/sourc_code/Sparse4D-main/projects/mmdet3d_plugin/models/detection3d/losses.py", line 66, in forward
box_loss = self.loss_box(
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/mmdet/models/losses/smooth_l1_loss.py", line 138, in forward
loss_bbox = self.loss_weight * l1_loss(
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/mmcv/utils/parrots_jit.py", line 22, in wrapper_inner
return func(*args, **kargs)
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/mmdet/models/losses/utils.py", line 96, in wrapper
loss = loss_func(pred, target, **kwargs)
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/mmdet/models/losses/smooth_l1_loss.py", line 43, in l1_loss
assert pred.size() == target.size() and target.numel() > 0
debug发现reg和reg_target都是空，导致计算loss的时候报错，尝试调整config中cls_threshold_to_reg=0.02可以解决，请问原配置0.05的阈值是怎么设置的呢？您有遇到相同的问题吗？
2. # test
bash local_test.sh sparse4dv3_temporal_r50_1x8_bs6_256x704 ckpt/sparse4dv3_r50.pth
这里的checkpoint用的是您release的版本， 报错：
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/mmdet/models/backbones/resnet.py", line 635, in forward
x = self.conv1(x) #val: [1,1,6,3,256,704] train:[36,3,256,704]
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 446, in forward
return self._conv_forward(input, self.weight, self.bias)
File "/home/amax/anaconda3/envs/bevformer/lib/python3.8/site-packages/torch/nn/modules/conv.py", line 442, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Expected 4-dimensional input for 4-dimensional weight [64, 3, 7, 7], but got 6-dimensional input of size [1, 6, 6, 3, 256, 704] instead
十分期待您的答复，感谢！