Tutorial 0: Overview of MMFewShot Classification Design of Data Sampling Design of Models API Design of Meta Testing meta testing on multiple gpus Tutorial 1: Learn about Configs Modify config through script arguments Config Name Style An Example of Baseline FAQ Use intermediate variables in configs Ignore some fields in the base configs Tutorial 2: Adding New Dataset Customize datasets by reorganizing data Customize loading annotations Customize different subsets Customize datasets sampling EpisodicDataset Customize sampling logic Create a new dataset wrapper Update dataset builder Update the arguments in model using customize dataset wrapper in config Tutorial 3: Customize Models Add a new classifier 1. Define a new classifier 2. Import the module 3. Use the classifier in your config file Add a new backbone 1. Define a new backbone 2. Import the module 3. Use the backbone in your config file Add new heads 1. Define a new head 2. Import the module 3. Use the head in your config file Add new loss Tutorial 4: Customize Runtime Settings Customize optimization settings Customize optimizer supported by Pytorch Customize self-implemented optimizer 1. Define a new optimizer 2. Add the optimizer to registry 3. Specify the optimizer in the config file Customize optimizer constructor Additional settings Customize training schedules Customize workflow Customize hooks Customize self-implemented hooks 1. Implement a new hook 2. Register the new hook 3. Modify the config Use hooks implemented in MMCV Customize self-implemented eval hooks with a dataset Modify default runtime hooks Checkpoint config Log config Evaluation config Customize Meta Testing