Created by: jbq123

版本：Paddle1.7.0；PaddleSeg-release-v0.4.0 环境：Nvidia jetson TX2；ubuntu18.04 模型：Deeplabv3+Mobilenetv2（预训练） 问题描述：在运行pdseg/vis.py对下预训练模型进行推理时，出现如下错误： W0324 16:37:16.218273 8639 operator.cc:181] elementwise_add raises an exception thrust::system::system_error, parallel_for failed: too many resources requested for launch /usr/local/lib/python3.6/dist-packages/paddle/fluid/executor.py:782: UserWarning: The following exception is not an EOF exception. "The following exception is not an EOF exception.") Traceback (most recent call last): File "pdseg/vis.py", line 219, in visualize(cfg, **args.dict) File "pdseg/vis.py", line 134, in visualize return_numpy=True) File "/usr/local/lib/python3.6/dist-packages/paddle/fluid/executor.py", line 783, in run six.reraise(*sys.exc_info()) File "/usr/local/lib/python3.6/dist-packages/six.py", line 696, in reraise raise value File "/usr/local/lib/python3.6/dist-packages/paddle/fluid/executor.py", line 778, in run use_program_cache=use_program_cache) File "/usr/local/lib/python3.6/dist-packages/paddle/fluid/executor.py", line 831, in _run_impl use_program_cache=use_program_cache) File "/usr/local/lib/python3.6/dist-packages/paddle/fluid/executor.py", line 905, in _run_program fetch_var_name) RuntimeError: parallel_for failed: too many resources requested for launch 这个错误是程序执行到run这一步发生的，如图： 请问是什么原因造成的，该如何解决，谢谢！