Error in Resume raining neural network 'The output of layer 12 is incompatible with the input expected by layer 13'.

I am trying to resume training a neural network ( finetuned ResNet-50) using the command trainNetwork but I got this error message :

'The output of layer 12 is incompatible with the input expected by layer 13'

what I have so far is autosaved checkpoint 'convnet_checkpoint__254__2017_12_19__06_54_40.mat'

and I have two questions here :

1- whats the reason behind that error noting that I haven't changed anything in the layers' properties of the network (input/output).

2- basically this is my training command :

my_net = trainNetwork(Traindatasource,lgraph,options);

so, I am a bit confused about how to resume the training using A or B command ( after loading the checkpoint network, passing the data and training options):

A)

trainNetwork(trainingdatastor,net.Layers,options) because I can see the after loading the checkpoint Network its named 'net'

B) trainNetwork(trainingdatastore,my_net.Layers,options)

thanks

[Huawei Tian]

I meet the same ERROR. Have you fixed thie error?

[caesar]

unfortunately, NO. when I trained the model without using stop and resume it was ok means I didn't stop the training until its finished. hope that helps.

Answer 1

[Joakim Lindblad]

It's because ResNet is a DAG, and thus the net.Layers in the trainNetwork command is not enough, replace it with

trainNetwork(trainingdatastor,layerGraph(net),options)

[caesar]

have you tried it ?

also is that correct ' layerGraph(net)??

[Lawrence Sherman]

I have tried it and it works. Thanks!

[Adnan Saood]

Worked for me thanks