Closed chowkamlee81 closed 4 years ago
Did you install spconv using the version in my README.md?
@poodarchu i meet the similar problem and i indeed install the spconv using the version in your README.md
Traceback (most recent call last):
File "./tools/train.py", line 133, in
I installed spconv module succesfully. I had ubuntu18.0.4, cuda10.2 , torch=1.20 torch vision=0.4.0,
After installing, i tried execute python test/test_conv.py , but i got error below.. Kindly help
/usr/local/lib/python3.6/dist-packages/numpy/core/fromnumeric.py:3335: RuntimeWarning: Mean of empty slice. out=out, kwargs) /usr/local/lib/python3.6/dist-packages/numpy/core/_methods.py:161: RuntimeWarning: invalid value encountered in double_scalars ret = ret.dtype.type(ret / rcount) spconv time nan Traceback (most recent call last): File "test_conv.py", line 619, in main() File "test_conv.py", line 612, in main out = net(features_t, indices_t, bs) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in call result = self.forward(*input, *kwargs) File "test_conv.py", line 57, in forward return self.net(x)# .dense() File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in call result = self.forward(input, kwargs) File "/usr/local/lib/python3.6/dist-packages/spconv/modules.py", line 130, in forward input = module(input) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 547, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.6/dist-packages/spconv/conv.py", line 177, in forward use_hash=self.use_hash) File "/usr/local/lib/python3.6/dist-packages/spconv/ops.py", line 93, in get_indice_pairs stride, padding, dilation, out_padding, int(subm), int(transpose), int(use_hash)) RuntimeError: /module/src/lidar_detection/spconv-master/src/spconv/indice.cu 60 cuda execution failed with error 98