I used Caffe GoogleNet model to train my own data (10k images, 2 classes). I stop it at 400000th iteration with an accuracy of ~80%.
If I run the below comment: ./build/examples/cpp_classification/classification.bin models/bvlc_googlenet/deploy.prototxt models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel data/ilsvrc12/imagenet_mean.binaryproto data/ilsvrc12/synset_words.txt 1.png
it would give me a random result each time I run it (e.i. if I run it n times, then I get n results). Why? Does my training fail? or does it still use the old data from the reference model? I'm sorry if the question is too simple.