ackbar03

Results 8 comments of ackbar03

Semi Supervised Kernel Learning

Hi, I'm trying to do the same thing, the original code base they provided is too difficult to work with. Did any of you manage to implement the paper using...

Correct my understanding if I'm wrong but why do I feel that this is very low quality research?

its been archived, can't comment on it anymore. Again I could be wrong but I think this is a bit concerning. I've noticed quite a few subpar research pieces in...

A problom about batch size

I see that it can be set in the train.prototext and test.prototext. I also set batch size to 1 for training because of memory issue, however after every 2500 iterations...

A problom about batch size

I see that it can be set in the train.prototext and test.prototext. I also set batch size to 1 for training because of memory issue, however after every 2500 iterations...

when i try to train the res101-9s-600-rfcn-cascade detector using my gpus 4,5 , it said Multi-GPU execution not avilable -rebuild with USE_NCCL. CAN'T use two GPUS???

I encounter the same problem but I only have 1 gpu. How did you train it with 1 gpu only?

when i try to train the res101-9s-600-rfcn-cascade detector using my gpus 4,5 , it said Multi-GPU execution not avilable -rebuild with USE_NCCL. CAN'T use two GPUS???

nvm I'm an idiot... i think you need to go to the Makefile.config, uncomment USE_NCCL , make clean, and remake caffe

when i try to train the res101-9s-600-rfcn-cascade detector using my gpus 4,5 , it said Multi-GPU execution not avilable -rebuild with USE_NCCL. CAN'T use two GPUS???

nvm I'm an idiot... i think you need to go to the Makefile.config, uncomment USE_NCCL , make clean, and remake caffe

when i try to train the res101-9s-600-rfcn-cascade detector using my gpus 4,5 , it said Multi-GPU execution not avilable -rebuild with USE_NCCL. CAN'T use two GPUS???

same here, don't have matlib