Closed hakS07 closed 5 years ago
I tried to train DeeplabV3 pre-trained model on a new class(eyes iris) my dtat=RGB iris image+gray-scale iris label:1500 images(300*400) num_iteration=7000 crop_size=513 but the loss is unstable between 0.1 to 0.3 this example for a prediction
A Mask-RCNN is usually better for small object detection
@TillBeemelmanns thank you
I tried to train DeeplabV3 pre-trained model on a new class(eyes iris) my dtat=RGB iris image+gray-scale iris label:1500 images(300*400) num_iteration=7000 crop_size=513 but the loss is unstable between 0.1 to 0.3 this example for a prediction![Capture du 2019-05-27 22-56-27](https://user-images.githubusercontent.com/34586193/58440640-5a1fd080-80d3-11e9-8bba-a8e3988e83e6.png)