我正在执行ML-examples ->cmsisnn-cifar10
。成功生成均值文件mean.binaryproto,ancifar10_test_lmdb and cifar10_train_lmdb
。在将经过训练的Caffe模型转换为.pkl
文件时,可以通过以下命令将其转换为cmsis-nn
源文件。
python nn_quantizer.py --model models/cifar10_m7_train_test.prototxt --weights models/cifar10_m7_iter_300000.caffemodel.h5 --save models/cifar10_m7.pkl
遇到错误
Check failed: blob_dims == blob->shape() Cannot load blob from hdf5;
shape mismatch. Source shape is 16 32 5 5 (12800) target shape is 32 32 5 5 (25600)
帮帮我,我是Caffe的新手。