Avoid OOM when converting from pytorch to onnx.

[abetancordelrosario]

python tools/deploy.py configs/mmseg/segmentation_onnxruntime_static-1024x2048.py ../mmsegmentation/configs/swin/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K.py ../mmsegmentation/upernet_swin_base_patch4_window12_512x512_160k_ade20k_pretrain_384x384_22K_20210531_125459-429057bf.pth ../../../shared/demosc.jpeg --work-dir work-dir --show --device cuda:1 --dump-info

...................

2022-11-03 11:18:15.119049825 [E:onnxruntime:, sequential_executor.cc:339 Execute] Non-zero status code returned while running ArgMax node. Name:'ArgMax_4134' Status Message: /onnxruntime_src/onnxruntime/core/framework/bfc_arena.cc:330 void* onnxruntime::BFCArena::AllocateRawInternal(size_t, bool) Failed to allocate memory for requested buffer of size 10066329600

2022-11-03:11:18:15 - root - ERROR - Error in execution: Non-zero status code returned while running ArgMax node. Name:'ArgMax_4134' Status Message: /onnxruntime_src/onnxruntime/core/framework/bfc_arena.cc:330 void* onnxruntime::BFCArena::AllocateRawInternal(size_t, bool) Failed to allocate memory for requested buffer of size 10066329600

Traceback (most recent call last):
File "/root/workspace/mmdeploy/mmdeploy/utils/utils.py", line 41, in target_wrapper
result = target(*args, **kwargs)
File "/root/workspace/mmdeploy/mmdeploy/apis/visualize.py", line 72, in visualize_model
result = task_processor.run_inference(model, model_inputs)[0]
File "/root/workspace/mmdeploy/mmdeploy/codebase/mmseg/deploy/segmentation.py", line 197, in run_inference
return model(**model_inputs, return_loss=False, rescale=True)
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/workspace/mmdeploy/mmdeploy/codebase/mmseg/deploy/segmentation_model.py", line 85, in forward
outputs = self.forward_test(input_img, img_metas, *args, **kwargs)
File "/root/workspace/mmdeploy/mmdeploy/codebase/mmseg/deploy/segmentation_model.py", line 110, in forward_test
outputs = self.wrapper({self.input_name: imgs})
File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, **kwargs)
File "/root/workspace/mmdeploy/mmdeploy/backend/onnxruntime/wrapper.py", line 97, in forward
self.__ort_execute(self.io_binding)
File "/root/workspace/mmdeploy/mmdeploy/utils/timer.py", line 66, in fun
result = func(*args, *kwargs)
File "/root/workspace/mmdeploy/mmdeploy/backend/onnxruntime/wrapper.py", line 113, in __ort_execute
self.sess.run_with_iobinding(io_binding)
File "/opt/conda/lib/python3.8/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 229, in run_with_iobinding
self._sess.run_with_iobinding(iobinding._iobinding, run_options)
RuntimeError: Error in execution: Non-zero status code returned while running ArgMax node. Name:'ArgMax_4134' Status Message: /onnxruntime_src/onnxruntime/core/framework/bfc_arena.cc:330 void onnxruntime::BFCArena::AllocateRawInternal(size_t, bool) Failed to allocate memory for requested buffer of size 10066329600

2022-11-03 11:18:16,223 - mmdeploy - ERROR - visualize onnxruntime model failed.