Keras code and weights files for the VGG16-places365 and VGG16-hybrid1365 CNNs for scene classification
It is an application of deep learning and fully convolutional neural network that attempts to replicate the basic techniques used by professional restorators. After the user selects the regions to be restored, the algorithm automatically fills-in these regions with information surrounding them. The fill-in is done in such a way that isophote lin…
Places2 (A Large-Scale Database for Scene Understanding Deep Learning Project) Dot Net Api
Python code for re-arranging Places2-large dataset
EdgeConnect+: Adversarial Inpainting with Edge and Color Guidance A deep learning-based image inpainting framework that integrates edge and color guidance to enhance image restoration. Suitable for photo restoration, object removal, and content-aware editing, evaluated on CelebA and Places2 datasets.
Add a description, image, and links to the places2-dataset topic page so that developers can more easily learn about it.
To associate your repository with the places2-dataset topic, visit your repo's landing page and select "manage topics."