Graph Neural Networks' and implement it to Hyperspectral images...

You have to apply transfer learning methods with pretrained weights. E.g. Densenet, Resnet, Inception, MobileNet, NASnet and new models on hyperspectral images. these are the folloiwng steps 1. To work with Hyperspectral Image Classification dataset, need to search for a big dataset available with its ground truth. 2. To apply transfer learning methods with pretrained weights. E.g. Densenet, Resnet, Inception, MobileNet, NASnet and new models on hyperspectral images. 3. Checking the accuracy for the trained model with respected ground truth. example you can work on 'Graph Neural Networks' and implement it to Hyperspectral images... Some sources: [login to view URL] [login to view URL] Now, I want you to focus on 'Transfer learning on Hyperspectral Images' You have to apply transfer learning methods with pretrained weights. E.g. Densenet, Resnet, Inception, MobileNet, NASnet and new models on hyperspectral images. You can write your studies in conference proceeding format as you have sent in your previous email. As the weeks pass, the content of the paper will be completed as your work progress. some of resources: [login to view URL] [login to view URL] [login to view URL] You have to apply transfer learning methods with pretrained weights. E.g. Densenet, Resnet, Inception, MobileNet, NASnet and new models on hyperspectral images. these are the folloiwng steps 1. To work with Hyperspectral Image Classification dataset, need to search for a big dataset available with its ground truth. 2. To apply transfer learning methods with pretrained weights. E.g. Densenet, Resnet, Inception, MobileNet, NASnet and new models on hyperspectral images. 3. Checking the accuracy for the trained model with respected ground truth.