How to use new pretraining model with different dataset in DIGITS (different labels)?

Question

I want to use VGG_ILSVRC_19_layers as a pretrained model in digits but with different dataset. Do I need different label files? How can I upload this model and use it for my dataset?

for the VGG 16 layers I got

ERROR: Cannot copy param 0 weights from layer 'fc6'; shape mismatch. Source param shape is 1 1 4096 25088 (102760448); target param shape is 4096 32768 (134217728). To learn this layer's parameters from scratch rather than copying from a saved net, rename the layer.

how can modify layers?

score 1 · Accepted Answer · edited May 23 '17 at 10:32

1

Your labels are associated with your dataset in DIGITS - not your model. When you upload a pretrained VGG model, you'll probably need to rename your last inner product layer (see this answer) so that your model will work on N classes instead of 1000.

edited May 23 '17 at 10:32

Community

1
1

answered Oct 19 '16 at 16:55

Luke Yeager

1,400
1
17
30

Thanks for your answer but I got "ERROR: Your deploy network is missing a Softmax layer! Read the documentation for custom networks and/or look at the standard networks for examples" – Video Analysis Deep Learning Oct 20 '16 at 01:10
Well that's a different problem. Feel free to post another question either here on SO or on GitHub. – Luke Yeager Oct 20 '16 at 01:23

How to use new pretraining model with different dataset in DIGITS (different labels)?

1 Answers1

Linked