dgd_person_reid
dgd_person_reid copied to clipboard
change batch_size value
hi every body I wanna run these instructions in caffe and as wrote in *_train.prototxt files ,the value of batch_size for training set to 50 and for test set to 20, I use a GeForce GTX 980 Ti GPU and when I trying to run with these values I ahead with this error error == cudaSuccess (2 vs. 0) out of memory and I have to decrease batch_size value and it causes my accuracy change? how should I manage this problem? thanks