From a11ca5b503dec62be730dbe1d5d0b3e6c2c3d652 Mon Sep 17 00:00:00 2001 From: Amir Zadeh Date: Mon, 30 Jul 2018 15:14:10 -0400 Subject: [PATCH] Update readme.txt --- model_training/ce-clm_training/cen_training/readme.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/model_training/ce-clm_training/cen_training/readme.txt b/model_training/ce-clm_training/cen_training/readme.txt index e1333af9..f0a5b86d 100644 --- a/model_training/ce-clm_training/cen_training/readme.txt +++ b/model_training/ce-clm_training/cen_training/readme.txt @@ -4,7 +4,6 @@ in ../patch_generation. Then run the training code via train_cen.py. Each patch expert is trained for a single scale, view and landmark. - python train_cen.py (location of patches) (model to train) (scale to train) (view to train) (landmark to train) (minibatch size) (folder to save models to) (menpo or general/300W patches) @@ -17,3 +16,5 @@ other options: e.g. python train_cen.py menpo_data/ arch6 0.35 profile3 5 256 model_saves menpo --num_epochs 100 --outfile menpo_acc_120.txt --acc_file menpo_acc_20.txt + +Subsequently, run the keras2matlab.py for getting your model in matlab format. Each landmark patch detector needs to be converted into a matlab input file using this script. The script takes in an input file which would be one output output of the train_cen code. Then it turns it into matlab object. The code is written for architecture 4, if you are using other architecture you need to copy and paste the architecture to build_model.