i made a reimplement with tensorflow2

[YuhangJi]

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

[varungupta31]

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

[YuhangJi]

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]

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