Open kaishijeng opened 7 years ago
What about trying something like this?
net = rna_model_a1(1000, 32)
net.save('ilsvrc-cls_rna-a1_cls1000_ep-symbol.json')
Zifeng,
It works with this trick. However, it seems synset is different from the link below because the prediction output is different from actual image. 'http://data.mxnet.io/models/imagenet/resnet/synset.txt'.
On Sun, Jan 8, 2017 at 6:37 PM, Zifeng Wu notifications@github.com wrote:
What about trying something like this?
net = rna_model_a1(1000, 32) net.save('ilsvrc-cls_rna-a1_cls1000_ep-symbol.json')
— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/itijyou/ademxapp/issues/6#issuecomment-271201893, or mute the thread https://github.com/notifications/unsubscribe-auth/AMGg3u13vn4ajHOln7DY8bMinwh1DnrZks5rQZ1ygaJpZM4Ld1-J .
The order of examples in our val.lst is different. But the class IDs of the two coincide with each other.
I want to use mx.model.FeedForward.load to load pretrained model, but it needs ilsvrc-cls_rna-a1_cls1000_ep-symbol.json. Can you share ilsvrc-cls_rna-a1_cls1000_ep-symbol.json if you have one available?
Thanks,