Reputation: 14258
I'm running the basic example on the darknet https://pjreddie.com/darknet/train-cifar/ and are getting a bunch of outputs:
1382, 3.538: 0.954143, 0.969863 avg, 0.027415 rate, 0.559997 seconds, 176896 images
Loaded: 0.000033 seconds
1383, 3.540: 0.816129, 0.954489 avg, 0.027385 rate, 0.565249 seconds, 177024 images
Loaded: 0.000069 seconds
1384, 3.543: 0.961585, 0.955199 avg, 0.027355 rate, 0.564356 seconds, 177152 images
Loaded: 0.000037 seconds
What do these outputs mean and what is the actual interim accuracy?
Upvotes: 0
Views: 170
Reputation: 1509
1384 - iteration number (number of batch)
0.961585 - current loss
0.955199 avg - average loss (error) - the lower, the better
When you see that average loss 0.xxxxxx avg no longer decreases at many iterations then you should stop training.
for more details see AlexeyAB/darknet
Upvotes: 1