Chunyes的专栏

Q1: Check failed: registry.count(type) == 1 (0 vs. 1) Unknown layer type I1221 19:43:06.790405 12895 layer_factory.hpp:76] Creating layer proposal F1221 19:43:06.790431 12895 layer_factory.hpp:80] C

在已安装了caffe-master的电脑上，用GPU-mode跑caffe模型，由于是公用电脑，我在自己的账户下也要设置一下环境。在～/.bashrc里添加：export CUDAHOME=/usr/local/cuda-8.0 export CUDA_INSTALL_PATH=/usr/local/cuda-8.0 export PATH=$PATH:$CUDA_INSTALL_PATH/bin

错误1：./tools/train_net.py", line 96, _solver.train_model(args.max_iters)MNC/tools/../lib/caffeWrapper/SolverWrapper.py", line 127, in train_model self.solver.step(1) MemoryError解决： 把batch_size改成从64改成8，