I used this project for example(framework - caffe, arhitecture of net - mod of AlexNet, 400 images are used for training). I have this result: enter image description here

or this: enter image description here


net: "./CDNet/Models/train.prototxt"
test_iter: 500
test_interval: 500
base_lr: 0.001
lr_policy: "step"
gamma: 0.1
stepsize: 100000
display: 50
max_iter: 450000
momentum: 0.9
weight_decay: 0.0005
snapshot: 10000
snapshot_prefix: "./CDNet/Models/Training/cdnet"
solver_mode: GPU

Model of net: enter image description here

Can anybody explain such behavior of accuracy and loss of my Net? What I am doing wrong?

Author of tutorial has got this result: enter image description here


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.