What's your output node of your model file ?help.

[wangyarui]

Hi, friends, I am a postgraduate at school. I am trying to transplant this model file to my android examples, I added the following code in your inference.py to save your ckpt model file
saver=tf.train.Saver() saver.save(sess,'checkpoint/ICNet.ckpt')
Then I adopt the 'CkptToPb.py' written by myself to transform the ckpt model to pb file.
But I need know your output node for your model, and I can not find something obviously about your output node, I need your help .Can you update your 'model.ckpt' to your git ? I really want to check it with mine to find what is wrong.
I am so appreciated your warm heart, thank you very much.
Thanks again sincerely.

[hellochick]

Hey, @wangyarui you can call net.layers['conv6_cls'] to get the node. Btw, I have put the model.ckpt on the google drive. Is that helpful for you?

[wangyarui]

Hey, @hellochick thanks for your response. I downloaded your model.ckpt and transformed it to ICNet.pb. But when I was transforming it to ICNet.pb，when I set the output node con6_cls, the error dedicated that conv6_cls is not existed in this graph. Although I adopted tensorboard and I find the conv6_cls......I really do not know what happed, Now I am reading carefully your train.py code. Thanks again.

[hellochick]

Hey, @wangyarui. Sorry for my late reply. Have you solved your problem yet?

[wangyarui]

@hellochick yes，I have solve my problem,thank you very much.

[pewpewpeww]

Hi @wangyarui, may I know what is the output node you used in the end? I am also facing the same problem; trying to convert to .pb file and used conv6_cls as output node name but it does not work.

[chegnyanjun]

Hi, @pewpewpeww, I am also facing the same problem as you.Do you have solved?