Created by: atczyh

使用faster_rcnn_r50_1x.yml完成模型训练后，按照EXPORT_MODEL.md教程方法导出模型： python3 tools/export_model.py -c configs/faster_rcnn_r50_1x.yml --output_dir=./inference_model -o weights=output/faster_rcnn_r50_1x/model_final 导出模型后使用https://github.com/PaddlePaddle/PaddleDetection/pull/147/files/bab5c42223eb5fb5daf537b2c43b67a5e6689ca6#diff-62bd3de6f2c75660138c062aaaf2797e提供的tools/tensorrt_infer.py 进行预测，预测命令如下： python3 tools/tensorinfer.py --model_path=inference_model/faster_rcnn_r50_1x/ --infer_img=PaddleDetection/000003.jpg --arch=RCNN --mode=trt_fp32 --visualize --min_subgraph_size=30 启动预测后内存用量不断增加，直至内存全部使用完毕，预测停止 I0118 21:40:01.983398 20802 graph_pattern_detector.cc:96] --- detected 2 subgraphs --- Running IR pass [repeated_fc_relu_fuse_pass] --- Running IR pass [squared_mat_sub_fuse_pass] --- Running IR pass [conv_bn_fuse_pass] --- Running IR pass [conv_eltwiseadd_bn_fuse_pass] --- Running IR pass [is_test_pass] --- Running IR pass [runtime_context_cache_pass] --- Running analysis [ir_params_sync_among_devices_pass] --- Running analysis [adjust_cudnn_workspace_size_pass] --- Running analysis [inference_op_replace_pass] --- Running analysis [ir_graph_to_program_pass] I0118 21:40:02.078835 20802 analysis_predictor.cc:474] ======= optimize end ======= W0118 21:40:02.124074 20802 naive_executor.cc:45] The NaiveExecutor can not work properly if the cmake flag ON_INFER is not set. W0118 21:40:02.124132 20802 naive_executor.cc:47] Unlike the training phase, all the scopes and variables will be reused to save the allocation overhead. W0118 21:40:02.124141 20802 naive_executor.cc:50] Please re-compile the inference library by setting the cmake flag ON_INFER=ON if you are running Paddle Inference Killed 请帮忙看看什么原因导致的？