Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

ONNX ati Awoṣe Interoperability adanwo

Test the key ideas behind ONNX graphs, operators, execution providers, model exchange, and graph optimization across runtimes.

Jẹmọ itọsọna awọn ọnaOnnx Ati Awoṣe Interoperability
Ibeere 1 ti 8

Iṣoro pataki wo ni ONNX yanju ni akọkọ?

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  1. Iṣoro pataki wo ni ONNX yanju ni akọkọ?
    • Awọn awoṣe gbigbe laarin awọn ilana oriṣiriṣi ati awọn akoko ṣiṣe nipasẹ ọna kika ti o wọpọ
    • Iforukọsilẹ data ikẹkọ laifọwọyi
    • Ti o npese titun nkankikan nẹtiwọki faaji
    • Encrypting awoṣe òṣuwọn fun aabo
  2. Bawo ni faili ONNX ṣe aṣoju awoṣe?
    • Bi data ikẹkọ aise
    • Bi awọn kan isiro awonya ti idiwon awọn oniṣẹ
    • Bi awọn kan nikan lilefoofo-ojuami nọmba
    • Bi koodu orisun ni 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. Ni ONNX Runtime, kini 'olupese ipaniyan'?
    • A awọsanma ìdíyelé iroyin
    • Eniyan ti o ni ikẹkọ awoṣe
    • A iru ti isonu iṣẹ
    • Afẹyinti ti o nṣiṣẹ awọn oniṣẹ atilẹyin lori ohun elo kan pato bi Sipiyu, CUDA, tabi TensorRT
  5. Kini ẹya 'opset' (ṣeto oniṣẹ ẹrọ) ninu awoṣe ONNX ṣe asọye?
    • Eyi ti ikede ti awọn oniṣẹ idiwon ti awonya nlo
    • Awoṣe ká išedede lori kan igbeyewo ṣeto
    • Awọn nọmba ti GPUs ti a beere
    • Oṣuwọn ikẹkọ ikẹkọ
  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
    • Awoṣe ti wa ni atunṣe laifọwọyi
    • 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