TypeError: div() got an unexpected keyword argument 'rounding_mode'

[fardinadii]

Instructions To Reproduce the 🐛 Bug:

/workspace/detectron2/detectron2/detectron2/structures/masks.py:368: UserWarning: This overload of nonzero is deprecated:
nonzero()
Consider using one of the following signatures instead:
nonzero(, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.)
item = item.nonzero().squeeze(1).cpu().numpy().tolist()
/workspace/detectron2/detectron2/detectron2/structures/masks.py:368: UserWarning: This overload of nonzero is deprecated:
nonzero()
Consider using one of the following signatures instead:
nonzero(, bool as_tuple) (Triggered internally at ../torch/csrc/utils/python_arg_parser.cpp:962.)
item = item.nonzero().squeeze(1).cpu().numpy().tolist()
Exception during training:
Traceback (most recent call last):
File "/workspace/detectron2/func_detectron2_v1.py", line 335, in train
self.run_step()
File "/workspace/detectron2/detectron2/detectron2/engine/defaults.py", line 494, in run_step
self._trainer.run_step()
File "/workspace/detectron2/detectron2/detectron2/engine/train_loop.py", line 273, in run_step
loss_dict = self.model(data)
File "/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/workspace/detectron2/detectron2/detectron2/modeling/meta_arch/rcnn.py", line 148, in forward
images = self.preprocess_image(batched_inputs)
File "/workspace/detectron2/detectron2/detectron2/modeling/meta_arch/rcnn.py", line 226, in preprocess_image
images = ImageList.from_tensors(images, self.backbone.size_divisibility)
File "/workspace/detectron2/detectron2/detectron2/structures/image_list.py", line 88, in from_tensors
max_size = (max_size + (stride - 1)).div(stride, rounding_mode="floor") * stride
TypeError: div() got an unexpected keyword argument 'rounding_mode'

Expected behavior:

TypeError: div() got an unexpected keyword argument 'rounding_mode'

Environment:

sys.platform linux
Python 3.6.10 |Anaconda, Inc.|
numpy 1.19.2
detectron2 0.6 @/workspace/detectron2/detectron2/detectron2
Compiler GCC 7.5
CUDA compiler CUDA 11.1
detectron2 arch flags 5.2, 6.0, 6.1, 7.0, 7.5, 8.0, 8.6
DETECTRON2_ENV_MODULE
PyTorch 1.8.0a0+17f8c32 @/opt/conda/lib/python3.6/site-packages/torch
PyTorch debug build True
GPU available Yes
GPU 0 GeForce RTX 3090 (arch=8.6)
Driver version 455.23.04
CUDA_HOME /usr/local/cuda
TORCH_CUDA_ARCH_LIST 5.2 6.0 6.1 7.0 7.5 8.0 8.6+PTX
Pillow 8.4.0
torchvision 0.8.0a0 @/opt/conda/lib/python3.6/site-packages/torchvision
torchvision arch flags 5.2, 6.0, 6.1, 7.0, 7.5, 8.0, 8.6
fvcore 0.1.5.post20211023
iopath 0.1.9
cv2 3.4.1

[ppwwyyxx]

The minimum pytorch version is 1.8 official. Your pytorch version is older than what we supported.