Error in executing ResNet 50

[novelmartis]

I get the following error when I try to load resnet-50-dag :

No public property epsilon exists for class dagnn.BatchNorm.

Error in dagnn.Layer/load (line 185)
obj.(f) = s.(f) ;

Error in dagnn.DagNN.loadobj (line 27)
block.load(struct(s.layers(l).block)) ;

Error in untitled (line 4)
net = dagnn.DagNN.loadobj(load('imagenet-resnet-50-dag.mat')) ;

Could someone help me understand what's going on?

[vedaldi]

Hi, can you confirm that you are using the latest version of MCN to load this model?

On 19 Apr 2016, at 09:45, Sushrut Thorat notifications@github.com wrote:

I get the following error when I try to load resnet-50-dag :

No public property epsilon exists for class dagnn.BatchNorm.

Error in dagnn.Layer/load (line 185)
obj.(f) = s.(f) ;

Error in dagnn.DagNN.loadobj (line 27)
block.load(struct(s.layers(l).block)) ;

Error in untitled (line 4)
net = dagnn.DagNN.loadobj(load('imagenet-resnet-50-dag.mat')) ;

Could someone help me understand what's going on?

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub #509

[novelmartis]

Hi,

I just upgraded from beta-18 to beta-19, and now even the GoogLeNet isn't
working (DAG) [Using the code mentioned on the quick start page]

The error is:

Attempt to execute SCRIPT vl_nnconv as a function:
/Users/isush4u/matconvnet-1.0-beta18/matlab/vl_nnconv.m

Error in dagnn.Conv/forward (line 11)
outputs{1} = vl_nnconv(...

Error in dagnn.Layer/forwardAdvanced (line 85)
outputs = obj.forward(inputs, {net.params(par).value}) ;

Error in dagnn.DagNN/eval (line 88)
obj.layers(l).block.forwardAdvanced(obj.layers(l)) ;

Error in untitled3 (line 11)
net.eval({'data', im_}) ;

Thanks

On Tue, Apr 19, 2016 at 10:49 AM, Andrea Vedaldi notifications@github.com
wrote:

Hi, can you confirm that you are using the latest version of MCN to load
this model?

On 19 Apr 2016, at 09:45, Sushrut Thorat notifications@github.com
wrote:

I get the following error when I try to load resnet-50-dag :

No public property epsilon exists for class dagnn.BatchNorm.

Error in dagnn.Layer/load (line 185)
obj.(f) = s.(f) ;

Error in dagnn.DagNN.loadobj (line 27)
block.load(struct(s.layers(l).block)) ;

Error in untitled (line 4)
net = dagnn.DagNN.loadobj(load('imagenet-resnet-50-dag.mat')) ;

Could someone help me understand what's going on?

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub <
https://github.com/vlfeat/matconvnet/issues/509>

—
You are receiving this because you authored the thread.
Reply to this email directly or view it on GitHub
#509 (comment)

Sushrut Thorat
Masters student in Cognitive Sciences
UTrento, Italy
+39 3803764733
http://novelmartis.github.io

[novelmartis]

Hi,

I figured out the problem. I had not added the "matlab" folder into
Matlab's default path.. Sorry for the trouble. It is all functional now :)

On Tue, Apr 19, 2016 at 10:49 AM, Andrea Vedaldi notifications@github.com
wrote:

Hi, can you confirm that you are using the latest version of MCN to load
this model?

On 19 Apr 2016, at 09:45, Sushrut Thorat notifications@github.com
wrote:

I get the following error when I try to load resnet-50-dag :

No public property epsilon exists for class dagnn.BatchNorm.

Error in dagnn.Layer/load (line 185)
obj.(f) = s.(f) ;

Error in dagnn.DagNN.loadobj (line 27)
block.load(struct(s.layers(l).block)) ;

Error in untitled (line 4)
net = dagnn.DagNN.loadobj(load('imagenet-resnet-50-dag.mat')) ;

Could someone help me understand what's going on?

—
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub <
https://github.com/vlfeat/matconvnet/issues/509>

—
You are receiving this because you authored the thread.
Reply to this email directly or view it on GitHub
#509 (comment)

Sushrut Thorat
Masters student in Cognitive Sciences
UTrento, Italy
+39 3803764733
http://novelmartis.github.io

[lenck]

Great to hear that! :)