This is the Linux app named DomainBed whose latest release can be downloaded as DomainBedsourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named DomainBed with OnWorks for free.
Postępuj zgodnie z tymi instrukcjami, aby uruchomić tę aplikację:
- 1. Pobrałem tę aplikację na swój komputer.
- 2. Wpisz w naszym menedżerze plików https://www.onworks.net/myfiles.php?username=XXXXX z wybraną nazwą użytkownika.
- 3. Prześlij tę aplikację w takim menedżerze plików.
- 4. Uruchom emulator online OnWorks Linux lub Windows online lub emulator online MACOS z tej witryny.
- 5. W systemie operacyjnym OnWorks Linux, który właśnie uruchomiłeś, przejdź do naszego menedżera plików https://www.onworks.net/myfiles.php?username=XXXXX z wybraną nazwą użytkownika.
- 6. Pobierz aplikację, zainstaluj ją i uruchom.
ZRZUTY EKRANU
Ad
DomainBed
OPIS
DomainBed is a PyTorch-based research suite created by Facebook Research for benchmarking and evaluating domain generalization algorithms. It provides a unified framework for comparing methods that aim to train models capable of performing well across unseen domains, as introduced in the paper In Search of Lost Domain Generalization. The library includes a wide range of well-known domain generalization algorithms, from classical baselines such as Empirical Risk Minimization (ERM) and Invariant Risk Minimization (IRM) to more advanced techniques like Domain Adversarial Neural Networks (DANN), Adaptive Risk Minimization (ARM), and Invariance Principle Meets Information Bottleneck (IB-ERM/IB-IRM). DomainBed also integrates multiple standard datasets—including RotatedMNIST, PACS, VLCS, Office-Home, DomainNet, and subsets from WILDS—allowing consistent experimentation across image classification tasks.
Funkcjonalności
- Comprehensive PyTorch suite for domain generalization research and benchmarking
- Implements 25+ algorithms including ERM, IRM, DANN, Fish, and more
- Includes diverse domain generalization datasets such as PACS, DomainNet, and WILDS subsets
- Supports reproducible model selection methods and evaluation protocols
- Automates large-scale training sweeps and hyperparameter optimization
- Provides detailed result collection and LaTeX-compatible reporting utilities
Język programowania
Python
Kategorie
This is an application that can also be fetched from https://sourceforge.net/projects/domainbed.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.
