Skip to content

Latest commit

 

History

History
17 lines (13 loc) · 644 Bytes

README.md

File metadata and controls

17 lines (13 loc) · 644 Bytes

###Digit Recognition via CNN
####to train:

  • download dataset
  • at examples/digit/ run creat_digit.sh to create LMDB database for training
  • run solve.sh to train digital model

####to test:

  • download pre-trained model or train your own model as metioned above.
  • run demo.m(need Matlab and matcaffe)
  • python bindings are on the go.

Code base on caffe


Mail: [email protected] Page: http://zhaok.xyz