CUDA out of memory

[fatalfeel]

File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 541, in call result = self.forward(*input, **kwargs) File "/root/projects/slimyolov3_erikguo/models.py", line 216, in forward x = module(x) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py", line 541, in call result = self.forward(*input, **kwargs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/modules/pooling.py", line 141, in forward self.return_indices) File "/usr/local/lib/python3.7/dist-packages/torch/_jit_internal.py", line 138, in fn return if_false(*args, **kwargs) File "/usr/local/lib/python3.7/dist-packages/torch/nn/functional.py", line 488, in _max_pool2d input, kernel_size, stride, padding, dilation, ceil_mode) RuntimeError: CUDA out of memory. Tried to allocate 48.00 MiB (GPU 0; 7.76 GiB total capacity; 6.79 GiB already allocated; 17.00 MiB free; 82.59 MiB cached) 0%| | 0/1 [01:14<?, ?it/s]

Process finished with exit code 1

[cartovarc]

Try kill useless process... you can see them with: nvidia-smi -l

[fatalfeel]

if i use yolov3_ktian08 branch memory is enough~~~ forgive it now i use the most powerful ai -> detectron2 best than yolov3 spp even spp3