FCN.tensorflow icon indicating copy to clipboard operation
FCN.tensorflow copied to clipboard

i made a reimplement with tensorflow2

Open YuhangJi opened this issue 3 years ago • 3 comments

i made a reimplement with tensorflow2, but it is not very well. In MIT dataset, the model loss value just decline to 2.3.

YuhangJi avatar Dec 24 '21 02:12 YuhangJi

Hey @YuhangJi, I'm tring to train the FCN on my custom dataset, in which I have only 2 classes (background + object). Can you guide me with how to manipulate the code to achieve this?

TIA

varungupta31 avatar Mar 13 '22 14:03 varungupta31

i made a reimplement with tensorflow2, but it is not very well. In MIT dataset, the model loss value just decline to 2.3.

This issue is caused by the absence of a softmax function when training a model.

YuhangJi avatar Mar 16 '22 06:03 YuhangJi

Hey @YuhangJi, I'm tring to train the FCN on my custom dataset, in which I have only 2 classes (background + object). Can you guide me with how to manipulate the code to achieve this?

TIA

No problem. @varungupta31

YuhangJi avatar Mar 16 '22 06:03 YuhangJi