预训练模型加载问题
Created by: NeVermore2
每次我使用预训练模型时,都会有如下警告 2020-03-30 11:08:48,866-INFO: Loading parameters from /home/renpeng2/Project/ssx/paddle/PaddleDetection/output/pretrain/ResNet34_pretrained... 2020-03-30 11:08:49,114-WARNING: /tmp/tmpxd3y6eev/ResNet34_pretrained.pdparams not found, try to load model file saved with [ save_params, save_persistables, save_vars ] 2020-03-30 11:08:49,114-WARNING: /tmp/tmpxd3y6eev/ResNet34_pretrained.pdparams not found, try to load model file saved with [ save_params, save_persistables, save_vars ] 2020-03-30 11:08:49,126-WARNING: variable file [ /tmp/tmpxd3y6eev/ResNet34_pretrained/fc_0.b_0 /tmp/tmpxd3y6eev/ResNet34_pretrained/fc_0.w_0 ] not used 2020-03-30 11:08:49,126-WARNING: variable file [ /tmp/tmpxd3y6eev/ResNet34_pretrained/fc_0.b_0 /tmp/tmpxd3y6eev/ResNet34_pretrained/fc_0.w_0 ] not used 2020-03-30 11:08:53,787-INFO: 4498 samples in file dataset/voc/train.txt 2020-03-30 11:08:59,357-INFO: places would be ommited when DataLoader is not iterable I0330 11:08:59.377758 196774 parallel_executor.cc:440] The Program will be executed on CUDA using ParallelExecutor, 2 cards are used, so 2 programs are executed in parallel. I0330 11:09:06.142910 196774 build_strategy.cc:354] set enable_sequential_execution:1 W0330 11:09:06.271733 196774 fuse_all_reduce_op_pass.cc:74] Find all_reduce operators: 177. To make the speed faster, some all_reduce ops are fused during training, after fusion, the number of all_reduce ops i s 114. 请问我这个是加载预训练模型成功了吗? 以及这个警告是什么原因?