SA-SSD

SA-SSD copied to clipboard

RuntimeError: Output 0 of SplitBackward is a view and is being modified inplace.

3

Hello Everone! When i am trying to run `python3 train.py ../configs/car_cfg.py` i get the following RunTimeError "Traceback (most recent call last): File "tools/train.py", line 128, in main() File "tools/train.py", line...

msmekala

The values for bbox, bev, 3d and aos seems to be very low as compared to what is specified in read me file

1

Hi Everyone When i run the test the pre-trained model with the command `python3 tools/test.py configs/multi_cfg.py epoch_50.pth `specified in read me file i get following results Car [email protected], 0.70, 0.70:...

msmekala

PRE-TRAINED MODEL for multi-class detection

1

Hello, Can you please provide a pre-trained model for multi-class detection? The current model provided "epoch_50.pth" seems to be for detecting only cars as it gives very poor performance when...

CharviVitthal

cuda 102 pytorch1.7.0 spconv2.2.1.how can i fix this error?

Jaida19

`export NUMBAPRO_CUDA_DRIVER=/usr/lib/x86_64-linux-gnu/libcuda.so export NUMBAPRO_NVVM=/usr/local/cuda/nvvm/lib64/libnvvm.so export NUMBAPRO_LIBDEVICE=/usr/local/cuda/nvvm/libdevice export LD_LIBRARY_PATH=/home/billyhe/anaconda3/lib/python3.7/site-packages/spconv;` How to configure these on Windows, I use pycharm

Dejavusd

Hello, I want to test on a very small dataset. I reduced my validation dataset size to only 3 point clouds. (The same issue is also present if dataset contains...

CharviVitthal

CUDA kernel failed : invalid device function

3

When I try to train the model, I get `CUDA kernel failed`: ```shell File "mmdet/core/bbox3d/geometry.py", line 240: def points_in_convex_polygon_jit(points, polygon, clockwise=True): # first convert polygon to directed lines num_points_of_polygon =...

binlidaily

Update numba implementation for points in convex polygon

1

Replacing `np.einsum` with faster implementation from SECOND repository.

bytebagels

training error

1

Thanks for the great work ! My enviornment as follows: CUDA10.0 torch1.1.0 torchvision0.3.0 python3.6.5 spconv1.0 cmake3.16.0 Evaluate the model is OK, however, when I try to train a model by...

hitxing

setup.py build_ext fail RuntimeError: Error compiling objects for extension

14

I met such errors. Can anybody help me how to fix this problem? Thanks advance! My cuda =10.1,pytorch=1.7 (SASSD) a3168@3168:~/SUN/SA-SSD-master/mmdet/ops/points_op$ python setup.py build_ext --inplace running build_ext building 'points_op_cpu' extension Emitting...

stephen20190822