some problems in using conlab

[So-Yp]

cudnn is used
Interpolate 1 frames
****** Processed frame 1 | Time per frame (avg): 42.13s | Time left: 1:43:12.987946 ******************
Traceback (most recent call last):
File "colab_interpolate.py", line 112, in
y_s, offset, filter = model(torch.stack((X0, X1),dim = 0))
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/content/DAIN/networks/DAIN_slowmotion.py", line 182, in forward
cur_output_rectified_temp = self.rectifyNet(rectify_input) + cur_output_temp
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/content/DAIN/Resblock/BasicBlock.py", line 82, in forward
x = self.block2(x) if self.num_block>=2 else x
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/content/DAIN/Resblock/BasicBlock.py", line 40, in forward
out = self.conv2(out)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 345, in forward
return self.conv2d_forward(input, self.weight)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/conv.py", line 342, in conv2d_forward
self.padding, self.dilation, self.groups)
RuntimeError: CUDA out of memory. Tried to allocate 1.09 GiB (GPU 0; 15.90 GiB total capacity; 13.56 GiB already allocated; 465.88 MiB free; 14.74 GiB reserved in total by PyTorch)

When the environment is ready for 1080p video frame insertion, CUDA out of memory appears，
I'm using this command：
!python -W ignore colab_interpolate.py --netName DAIN_slowmotion --time_step {fps/TARGET_FPS} --start_frame 1 --end_frame {frame_count} --frame_input_dir '{FRAME_INPUT_DIR}' --frame_output_dir '{FRAME_OUTPUT_DIR}'