Hi, you can grab them here: https://github.com/Lasagne/Recipes/blob/master/examples/resnet50/imagenet_classes.txt
Regards, Sergey. среда, 5 апреля 2017 г., 15:39:23 UTC+3 пользователь Miguel de Prado написал: > > Hello, > > Could you please share the mapping between the class number and string > labels? I cant find it anywhere! > > Thanks > > El viernes, 17 de junio de 2016, 14:19:34 (UTC), AT escribió: >> >> I now have the "sysnet_words" mapping for the 1000 classes of images for >> ILSVRC2012. Earlier, someone suggested that I could resize my test image >> and input it into the CNN. If I convert my test JPG image to HKL format and >> resize it as needed, then how to I input this HKL test image into the CNN >> program *alex_net.py* <http://alex_net.py/>? Please provide some >> suggestions based on this or other similar CNN programs. Also, what is the >> output vector variable called? As I understand, the softmax layer = 1000. >> How do I access the softmax layer output data? >> >> >> On Friday, June 10, 2016 at 10:37:03 AM UTC-4, AT wrote: >>> >>> Can anyone provide me a copy of the file "synset_words.txt" for the >>> synset/name mapping of the ILSVRC2012 data set. >>> >>> Someone saw it mentioned on >>> http://caffe.berkeleyvision.org/gathered/examples/imagenet.html but I >>> can't find it on https://github.com/BVLC/caffe. >>> >>> >>> On Thursday, June 9, 2016 at 5:29:34 PM UTC-4, AT wrote: >>>> >>>> I have a list of 1.2 million ILSVRC2012 training images with >>>> corresponding class codes, 000 to 999. Where can I find the semantic >>>> labels >>>> for these codes? >>>> >>> -- --- You received this message because you are subscribed to the Google Groups "theano-users" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. For more options, visit https://groups.google.com/d/optout.
