All geek questions in one place

What is * Restarting data prefetching from the beginning * means in caffe

I read the output of the magazine. Reload the data prefetch from the beginning. Apparently, this means that one does not have enough data, and the data is preloaded * from the very beginning. However, my data set consists of 10,000 data samples, and the batch size is 4. How is it possible that it should preprogram the data since my batch size is 4, which means that 4 data samples will be taken for each iteration . Can someone clarify my understanding?

LOG:

I0409 20:33:35.053406 20072 data_layer.cpp:73] Restarting data prefetching from start.
I0409 20:33:35.053447 20074 data_layer.cpp:73] Restarting data prefetching from start.
I0409 20:33:40.320605 20074 data_layer.cpp:73] Restarting data prefetching from start.
I0409 20:33:40.320598 20072 data_layer.cpp:73] Restarting data prefetching from start.
I0409 20:33:45.591019 20072 data_layer.cpp:73] Restarting data prefetching from start.
I0409 20:33:45.591047 20074 data_layer.cpp:73] Restarting data prefetching from start.
I0409 20:33:49.392580 20034 solver.cpp:398]     Test net output #0: loss = nan (* 1 = nan loss)
I0409 20:33:49.780678 20034 solver.cpp:219] Iteration 0 (-4.2039e-45 iter/s, 20.1106s/100 iters), loss = 54.0694
I0409 20:33:49.780731 20034 solver.cpp:238]     Train net output #0: loss = 54.0694 (* 1 = 54.0694 loss)
I0409 20:33:49.780750 20034 sgd_solver.cpp:105] Iteration 0, lr = 0.0001
I0409 20:34:18.812854 20034 solver.cpp:219] Iteration 100 (3.44442 iter/s, 29.0325s/100 iters), loss = 21.996
I0409 20:34:18.813213 20034 solver.cpp:238]     Train net output #0: loss = 21.996 (* 1 = 21.996 loss)
+6
source share
1 answer

10 000 , 4, , 10 000/4 = 2,500 , caffe .
BTW, , "".

caffe

+5

Source: https://habr.com/ru/post/1016420/

More articles:


All Articles