在百度的BaiduCN1.2k Model基础上继续训练,出现错误 Check failed: src.getSize() == this->getSize() (8060928 vs. 4030464)
Created by: QAQ1551QAQ
我也是加载预训练模型训练的时候出错,--init_model_path = 'models/baiduCN/params.tar.gz'
I0626 07:27:05.990948 1586 Util.cpp:166] commandline: --use_gpu=1 --rnn_use_batch=True --log_clipping=True --trainer_count=2 [INFO 2019-06-26 07:27:07,147 layers.py:2606] output for conv_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2019-06-26 07:27:07,148 layers.py:3133] output for batch_norm_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2019-06-26 07:27:07,148 layers.py:7224] output for scale_sub_region_0: c = 32, h = 81, w = 54, size = 139968 [INFO 2019-06-26 07:27:07,149 layers.py:2606] output for conv_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2019-06-26 07:27:07,150 layers.py:3133] output for batch_norm_1: c = 32, h = 41, w = 54, size = 70848 [INFO 2019-06-26 07:27:07,150 layers.py:7224] output for scale_sub_region_1: c = 32, h = 41, w = 54, size = 70848 I0626 07:27:26.776872 1586 MultiGradientMachine.cpp:99] numLogicalDevices=1 numThreads=2 numDevices=2 I0626 07:27:26.796452 1586 GradientMachine.cpp:94] Initing parameters.. I0626 07:27:29.301322 1586 GradientMachine.cpp:101] Init parameters done. F0626 07:27:31.709532 1663 Vector.cpp:266] Check failed: src.getSize() == this->getSize() (8060928 vs. 4030464) *** Check failure stack trace: *** F0626 07:27:31.712079 1659 Vector.cpp:266] Check failed: src.getSize() == this->getSize() (8060928 vs. 4030464) *** Check failure stack trace: *** @ 0x7f30387ce04d google::LogMessage::Fail() @ 0x7f30387d0398 google::LogMessage::SendToLog() @ 0x7f30387ce04d google::LogMessage::Fail() @ 0x7f30387d0398 google::LogMessage::SendToLog() @ 0x7f30387cdb5b google::LogMessage::Flush() @ 0x7f30387d126e google::LogMessageFatal::~LogMessageFatal() @ 0x7f30387cdb5b google::LogMessage::Flush() @ 0x7f30385d3e3e paddle::GpuVectorT<>::copyFrom() @ 0x7f30387d126e google::LogMessageFatal::~LogMessageFatal() @ 0x7f303846aae4 paddle::TrainerThread::valueDispatchThread() @ 0x7f30385d3e3e paddle::GpuVectorT<>::copyFrom() @ 0x7f30bf26bc80 (unknown) @ 0x7f303846aae4 paddle::TrainerThread::valueDispatchThread() @ 0x7f30c9a5b6ba start_thread @ 0x7f30c97913dd clone @ 0x7f30bf26bc80 (unknown) @ 0x7f30c9a5b6ba start_thread @ (nil) (unknown) Aborted (core dumped) Failed in training!