Dear all,
I try and understand how CNN training works by having the net image, learning curve and intermediate images of CNN training.
For draw the net i use
~/caffe/python/draw_net.py ~/openmv/ml/cmsisnn/models/lettre_O_V3/fnt-lettre_O_V3_train_test.prototxt ~/openmv/ml/cmsisnn/models/fnt-lettre_O_V3-net.png
For learning curve i used the plot_learning_curve.py (need python-pandas) from : A Practical Introduction to Deep Learning with Caffe and Python // Adil Moujahid // Data Analytics and more
with :
// Train before because weights file should exist
~/caffe/build/tools/caffe train --solver=models/lettre_O_V3/fnt-lettre_O_V3_solver.prototxt
// Create log file
~/caffe/build/tools/caffe train --solver=models/lettre_O_V3/fnt-lettre_O_V3_solver.prototxt --weights models/lettre_O_V3/fnt-lettre_O_V3_iter_10000.caffemodel 2>&1 | tee models/lettre_O_V3/fnt-lettre_O_V3_train.log
// Plot the curve
python2 ./tools/plot_learning_curve.py /home/christophe/openmv/ml/cmsisnn/models/lettre_O_V3/fnt-lettre_O_V3_train.log /home/christophe/openmv/ml/cmsisnn/models/fnt-lettre_O_V3_learning_curve.png
For intermediate image, i dont have any to clue to do it.
Any help would be great ?
Thanks,
plot_learning_curve.py (2.34 KB)