Fixing warning after upgrading tagger to use CUDAExecutionprovider instead of CPUExecutionprovider in attempt to improve performance speed.

[andrewtvuong]

Please see #62

This pull request seeks help in fixing the following message after upgrading to use CUDAExecutionprovider instead of CPUExecutionprovider.

[W:onnxruntime:, transformer_memcpy.cc:74 ApplyImpl] 12 Memcpy nodes are added to the graph main_graph for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message.

Warning seems to indicate a bottleneck caused by GPU/CPU data transfer by memcpy.

[piotr-sikora-v]

try to use this, but I have an error:

Error occurred when executing WD14Tagger|pysssss:

Can't allocate memory on the CUDA device using this package of OnnxRuntime. Please use the CUDA package of OnnxRuntime to use this feature.

File "/opt/ComfyUI/execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/opt/ComfyUI/execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/opt/ComfyUI/execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/opt/ComfyUI/custom_nodes/ComfyUI-WD14-Tagger/wd14tagger.py", line 208, in tag
tags.append(wait_for_async(lambda: tag(image, model, threshold, character_threshold, exclude_tags, replace_underscore, trailing_comma)))
File "/opt/ComfyUI/custom_nodes/ComfyUI-WD14-Tagger/pysssss.py", line 214, in wait_for_async
loop.run_until_complete(run_async())
File "/usr/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/opt/ComfyUI/custom_nodes/ComfyUI-WD14-Tagger/pysssss.py", line 204, in run_async
r = await async_fn()
File "/opt/ComfyUI/custom_nodes/ComfyUI-WD14-Tagger/wd14tagger.py", line 84, in tag
ort_inputs = {input_name: ort.OrtValue.ortvalue_from_numpy(image, 'cuda')}
File "/opt/ComfyUI/venv/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 695, in ortvalue_from_numpy
C.OrtValue.ortvalue_from_numpy(