3.JETSON TX2安装caffe-SSD、tensorflow - CSDN博客
gaicuo解决python在import caffe时出现的no module name _caffe问题 - CSDN博客
我训练的时候是直接把原数据集改成了自己的,我觉得这样比较简单。按上述笔记训练的时候遇到一个问题,Cannot copy param 0 weights from layer 'conv4_3_norm_mbox_conf'; shape mismatch. Source param shape is 84 512 3 3 (387072); target param shape is 12 512 3 3 (55296). To learn this layer's parameters from scratch rather than copying from a saved net, rename the layer.原因是我先用原有数据集训练了几步,导致我训练自己的数据时用了之前训练过的模型,删除caffe/models/vggnet/voc0712即可