Image recognition on Arm Cortex-M with CMSIS-NN

Troubleshooting

Here are some tips to help you troubleshoot some common issues.

Mbed CLI issues

Purge the cache with the following command:

mbed cache purge

No module named caffe

ImportError: No module named caffe

Check if it has been appended in pythonpath properly by typing

python >>> import sys >>> sys.path ['', '/home/embedded/caffe/python', '/usr/lib/python2.7', '/usr/lib/python2.7/plat-x86_64-linux-gnu', '/usr/lib/python2.7/lib-tk', '/usr/lib/python2.7/lib-old', '/usr/lib/python2.7/lib-dynload', '/home/embedded/.local/lib/python2.7/site-packages', '/usr/local/lib/python2.7/dist-packages', '/usr/lib/python2.7/dist-packages']

if /caffe/python is not there

>>> exit()

export PYTHONPATH=/caffe/python

Check failed: mdb_status == 0 (2 vs. 0) No such file or directory

Check failed: mdb_status == 0 (2 vs. 0) No such file or directory

Open the file:

gedit ~/CMSISNN_Webinar/ML-examples/cmsisnn-cifar10/models/cifar10_m7_train_test.prototxt

and check that the mean_file and source are pointing to the files in caffe/examples/cifar10/directory as shown below

# The following lines will have to be updated.# Note: You will have to replace  with the path where you have cloned the Caffe repositorymean_file: "/caffe/examples/cifar10/mean.binaryproto"source: "/caffe/examples/cifar10/cifar10_train_lmdb"source: "/caffe/examples/cifar10/cifar10_test_lmdb/"