SA-SSD

SA-SSD copied to clipboard

Changing voxel size for inference speed

4

I've been looking at ways to further increase inference speed, and my first attempt was to increase the voxel size to reduce the tensor input size to the model. However,...

SiftingSands

Train Error

17

Hi! Thank you for your great work！ But I have met some problem when I use this work. > root@679e1e925e7e:/data/SA-SSD/tools# python train.py ../configs/car_cfg.py Traceback (most recent call last): File "train.py",...

chenxyyy

Has anyone encountered this problem?

wdxpython

RuntimeError

4

Any one know that-- opp_labels = (box_preds[..., -1] > 0) ^ dir_labels.byte() RuntimeError: result type Byte can't be cast to the desired output type Bool

Morgan-Gan

@skyhehe123 I meet a issue when I change the point_cloud_range for test. Here is the car_cfg.py: val=dict( type=dataset_type, root=data_root + 'training/', ann_file=data_root + 'ImageSets/val.txt', img_prefix=None, img_scale=(1242, 375), img_norm_cfg=img_norm_cfg, size_divisor=32, flip_ratio=0,...

Xiangzhaohong

CUDA OOM Error

5

I am trying to train the SA-SSD model, but I encounter with CUDA out-of-memory error. I tried to use batch size 1, but the OOM error remains. I am using...

ootts

RuntimeError: one of the variables needed for gradient computation has been modified

6

File "/home/pioneer2_1/anaconda3/envs/pointpillars/lib/python3.7/site-packages/mmcv/runner/hooks/optimizer.py", line 19, in after_train_iter **runner.outputs['loss'].backward()** File "/home/pioneer2_1/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/tensor.py", line 118, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "/home/pioneer2_1/anaconda3/envs/pointpillars/lib/python3.7/site-packages/torch/autograd/__init__.py", line 93, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: one of...

yangz0626