Closed YanYan0716 closed 6 years ago
It is fine as long as you can get a good final accuracy. But generally, I would recommend getting more GPUs as training with 1GPU will be very slow.
how did u change the iteration size
I only used one GPU ,i set iters more than four times,the result is the same as the paper shown
I meant from which file? I could not find the file where you can change the iter_size. Thank you for your help
about temporal-segment-networks-master/models/ucf101/tsn_bn_inception_flow_solver.prototxt , you can change max_iter=....
@Mohamad73 It is in the solver file. The option is named iter_size
I am a new about this field, and have a question when i was training the network. I just have one GPU, so when i was training,i set the batch_size=12 ,in order to meet the condition about "batch_sizeiter_sizen_gpu=128", i set iter_size=11, so when i was training ,the log showed "Gradient clipping: scaling down gradients (L2 norm 68.3038 > 40) by scale factor 0.585619" . i want to know, if it will make a big influence about the result. thanks a lot and i am looking forward to your reply if you can give me some advice