Train Dino with focalNet backbone on custom datasets

[4BD0U]

I am having difficulty training a Dino model with a FocalNet backbone on a custom dataset. Although I was able to successfully train the model using a SWIN-L backbone, after 10 epochs with FocalNet, all detection scores are still below 1%. I am unable to understand why this might be the case as the dataset used is identical and the pre-trained model provided in the GitHub repository was used as a starting point. Can you help me understand what might be causing this issue, please

[Hezey]

@4BD0U Hello, how to change backbone with others？Can you tell me ?please

[HaoZhang534]

I am having difficulty training a Dino model with a FocalNet backbone on a custom dataset. Although I was able to successfully train the model using a SWIN-L backbone, after 10 epochs with FocalNet, all detection scores are still below 1%. I am unable to understand why this might be the case as the dataset used is identical and the pre-trained model provided in the GitHub repository was used as a starting point. Can you help me understand what might be causing this issue, please

I recommend to refer to this repo https://github.com/FocalNet/FocalNet-DINO .

[4BD0U]

Thank you for your response. The problem was that the pre-trained model provided was meant for Dino 5scale with focalNet, while the configuration file was set up for Dino 4scale.

[4BD0U]

I simply used the implemented backbone and set up the configuration file.