I try to use pre-trained model (VGG 16) to DIGITS for my dataset which has two classes. but I got wrongly training. (I change the name of last layers to fc8_new)
I uploaded deploy.prototxt and VGG_ILSVRC_16_layers.caffemodel and synset_words.txt successfully into DIGITS and tested with my data-set which has two classes.
Asked
Active
Viewed 636 times
0
Video Analysis Deep Learning
- 338
- 2
- 12
-
Your question is not very clear. You have problem with training or testing? – Harsh Wardhan Oct 20 '16 at 09:36
-
why there is not curve on your 2nd picture? What was the snapshot interval??? – MD. Nazmul Kibria Oct 20 '16 at 09:41
1 Answers
1
A deploy.prototxt won't include any loss or accuracy layers. I'm not really sure what Caffe will do when you try to train a network without any loss layers.
As I answered here, you're going to need to create an "all-in-one" network which includes all the layers needed for training, validation and deployment in a single network. @Shai linked to this helpful answer as well.
As explained on our GitHub README, we prefer to answer these questions on our user group instead of here on SO.
Community
- 1
- 1
Luke Yeager
- 1,400
- 1
- 17
- 30