RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

Trying to re-implement this code on Cloud Server, however I can't get past this cuda error. Any help on this?
Traceback (most recent call last):
File "tools/run_net.py", line 45, in
main()
File "tools/run_net.py", line 41, in main
demo(cfg)
File "/home/slowfast/tools/demo_net.py", line 114, in demo
for task in tqdm.tqdm(run_demo(cfg, frame_provider)):
File "/opt/conda/lib/python3.7/site-packages/tqdm/std.py", line 1167, in __iter__
for obj in iterable:
File "/home/slowfast/tools/demo_net.py", line 79, in run_demo
model.put(task)
File "/home/slowfast/slowfast/visualization/predictor.py", line 142, in put
task = self.predictor(task)
File "/home/slowfast/slowfast/visualization/predictor.py", line 61, in __call__
task = self.object_detector(task)
File "/home/slowfast/slowfast/visualization/predictor.py", line 201, in __call__
outputs = self.predictor(middle_frame)
File "/opt/conda/lib/python3.7/site-packages/detectron2/engine/defaults.py", line 251, in __call__
predictions = self.model([inputs])[0]
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/detectron2/modeling/meta_arch/rcnn.py", line 149, in forward
return self.inference(batched_inputs)
File "/opt/conda/lib/python3.7/site-packages/detectron2/modeling/meta_arch/rcnn.py", line 203, in inference
features = self.backbone(images.tensor)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/detectron2/modeling/backbone/fpn.py", line 126, in forward
bottom_up_features = self.bottom_up(x)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/detectron2/modeling/backbone/resnet.py", line 444, in forward
x = self.stem(x)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/detectron2/modeling/backbone/resnet.py", line 355, in forward
x = self.conv1(x)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
result = self.forward(*input, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/detectron2/layers/wrappers.py", line 85, in forward
x, self.weight, self.bias, self.stride, self.padding, self.dilation, self.groups
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED