- It is the way to express the location of pixels containing an object, like a list in one dimension, instead of using two dimensions or coordenates. If the object is on the row 1, between pixels 5 and 5, you can express it like : 5 5 , and like this for every row.
- Delete useless images without ships
- Add index for ships existence(0 or 1)
- drop and split train & valid set
- Do transfer learning with Resnet34
- Load training and valid set
- Image size 256 x 256, RGB data
- Use Unet Base on ResNet34 model
- Load training and valid set
- Image size 256 x 256, RGB data
- Use Unet Base on ResNet34 model
- Use pre-trained from Step 1
- Load training and valid set
- Image size 256 x 256, RGB data