Викторина, связанная с руководством · Средний Уровень
Тест ExecuTorch для PyTorch на устройстве
Выполните экспорт и понижение ExecuTorch, изучите серверные делегаты и секционирование, а также проверьте совместимость на предполагаемом устройстве.
Вопрос 1 из 8
Какую задачу развертывания призван поддерживать ExecuTorch?
Предварительный просмотр каждого вопроса8 вопросы
Ответы и пояснения появляются по мере прохождения теста.
- Какую задачу развертывания призван поддерживать ExecuTorch?
- Training PyTorch models on edge devices during inference
- Exporting arbitrary Python code without input or operator constraints
- Exporting PyTorch programs for execution with supported edge runtimes
- Converting TensorFlow SavedModels into cloud containers
- Что делает бэкенд-делегат?
- Runs every model operation even when the backend lacks support
- Runs supported operations through a backend implementation
- Converts a model into a portable artifact without executing operations
- Sets application input validation rules
- Что может произойти, если модель содержит операции, которые делегат не поддерживает?
- Every unsupported operator automatically runs on the delegate
- All unsupported operators always fall back to the portable runtime
- Unsupported operators are approximated without checking outputs
- Some operations may remain on a runtime path, or lowering may fail
- Why can partitioning a graph across backend and runtime add overhead?
- Data movement or synchronization can occur at partition boundaries
- Partitioning guarantees that tensors stay on one device
- Partition boundaries eliminate copies by definition
- Every partition incurs a fixed penalty regardless of workload
- Что следует сравнить после экспорта?
- Compare only the exported artifact name
- Compare only how many nodes the lowered graph contains
- Compare runtime outputs with eager PyTorch on representative inputs
- Compare output values only after changing model preprocessing
- Зачем тестировать целевое устройство, а не полагаться только на успешный экспорт?
- Export proves identical behavior on every device
- Backend coverage and performance depend on the target and build
- The runtime has no platform-specific libraries
- Every delegate supports all exported operators
- Which deployment measurements are useful for an on-device model?
- Training loss and validation accuracy only
- Load time, warm latency, memory, binary size, and energy
- Backend compile time and training throughput only
- Model parameter count and source-code line count
- What should be recorded with an exported model artifact?
- Source version, export settings, backend, and runtime pairing
- Only a portable Python checkpoint without export metadata
- Only example output values without the source version
- The exact private inputs submitted by app users