Guide-yakabatana mibvunzo · Pakati Nhanho

ONNX uye Model Interoperability Quiz

Edza iwo akakosha mazano kuseri kweONNX magirafu, vashandisi, vanopa kuuraya, modhi shanduko, uye optimization yemagirafu mukati menguva yekumhanya.

Nzira dzekutungamira dzinoenderanaOnnx Uye Model Kudyidzana
Mubvunzo 1 ye 8

Nderipi dambudziko guru rinogadziriswa neONNX?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Nderipi dambudziko guru rinogadziriswa neONNX?
    • Kufambisa modhi pakati pezvimiro zvakasiyana uye nguva dzekumhanya kuburikidza neyakajairwa fomati
    • Kuisa mazita ekudzidziswa data otomatiki
    • Kugadzira itsva neural network architectures
    • Encrypting modhi huremu kuitira kuchengetedza
  2. Ko faira reONNX rinomiririra sei modhi?
    • Sezvo mbishi kudzidziswa data
    • Sekuverengera girafu yevashandi vakamira
    • Senhamba imwe chete inoyangarara-nzvimbo
    • Sezvo sosi kodhi muPython
  3. What does the acronym ONNX stand for?
    • Optimized Network Node Execution
    • Open Neural Network Extension
    • Vhura Neural Network Exchange
    • Operator Network Normalization Exchange
  4. MuONNX Runtime, chii chinonzi 'execution provider'?
    • A cloud billing account
    • Munhu akadzidzisa modhi
    • Mhando yebasa rekurasikirwa
    • Iyo backend inomhanyisa vanotsigirwa vanobata pane chaiyo hardware seCPU, CUDA, kana TensorRT
  5. Ko iyo 'opset' (opareta set) mumhando yeONNX inotsanangura chii?
    • Ndeipi vhezheni yevashandi vakamisikidzwa iyo girafu inoshandisa
    • Kurongeka kwemuenzaniso pane test set
    • Nhamba yeGPU inodiwa
    • Chiyero chekudzidzira kudzidzira
  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
    • Iyo modhi inodzidziswa zvakare
    • 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