Maswali yanayounganishwa na mwongozo · Kati Kiwango

Maswali ya ONNX na Mfano wa Mwingiliano

Jaribu mawazo makuu nyuma ya grafu za ONNX, waendeshaji, watoa huduma wa utekelezaji, ubadilishanaji wa miundo, na uboreshaji wa grafu katika nyakati za utekelezaji.

Njia za mwongozo zinazohusianaUshirikiano wa Onnx na Mfano
Swali 1 ya 8

Ni tatizo gani la msingi ambalo ONNX hutatua kimsingi?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Ni tatizo gani la msingi ambalo ONNX hutatua kimsingi?
    • Kusonga miundo kati ya mifumo tofauti na nyakati za kukimbia kupitia umbizo la kawaida
    • Kuweka lebo data ya mafunzo kiotomatiki
    • Inazalisha usanifu mpya wa mtandao wa neva
    • Usimbaji wa uzani wa mfano kwa usalama
  2. Je, faili ya ONNX inawakilishaje mfano?
    • Kama data mbichi ya mafunzo
    • Kama grafu ya hesabu ya waendeshaji sanifu
    • Kama nambari moja ya sehemu inayoelea
    • Kama nambari ya chanzo katika Python
  3. What does the acronym ONNX stand for?
    • Optimized Network Node Execution
    • Open Neural Network Extension
    • Open Neural Network Exchange
    • Operator Network Normalization Exchange
  4. Katika ONNX Runtime, 'mtoa huduma wa utekelezaji' ni nini?
    • Akaunti ya malipo ya wingu
    • Mtu aliyemfundisha mwanamitindo
    • Aina ya kazi ya kupoteza
    • Mazingira ya nyuma ambayo yanaendesha waendeshaji wanaotumika kwenye maunzi maalum kama vile CPU, CUDA, au TensorRT
  5. Toleo la 'opset' (seti ya kiendeshaji) katika modeli ya ONNX inafafanua nini?
    • Ni toleo gani la waendeshaji sanifu ambao grafu hutumia
    • Usahihi wa mfano kwenye seti ya majaribio
    • Idadi ya GPU zinazohitajika
    • Kiwango cha mafunzo
  6. Which graph-level operations can ONNX Runtime apply?
    • Automatic retraining and label correction
    • Constant folding and node fusion, among other optimizations
    • Changing a model’s architecture to a new framework
    • Generating new training examples from inference requests
  7. What can happen when an ONNX Runtime execution provider supports only part of a model graph?
    • The provider must execute every node or fail by definition
    • Mfano huo umefunzwa tena kiatomati
    • The runtime can assign supported nodes or subgraphs to that provider and others to a different provider
    • All unsupported operators are deleted
  8. Why should an ONNX deployment check the model’s opset against the target runtime?
    • The opset specifies the model’s training dataset size
    • An opset number guarantees identical performance
    • The opset controls the number of GPU devices
    • The graph uses versioned operator definitions that the runtime must support