Ikibazo gihuza ibibazo · Hagati Urwego

Icyitegererezo cyo Gukurikirana Imiterere Ikibazo

Igeragezwa rya serialisation portable, umutekano wibintu, tensor-gusa dosiye yuburemere, hamwe no kugenzura imiterere yoherejwe hanze mugihe cyogukora.

Inzira zijyanye no kuyoboraIcyitegererezo cyo Gukurikirana
Ikibazo 1 Bya 8

Kuki imiterere ya Python ifatwa nkikibazo cyumutekano kuri moderi?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Kuki imiterere ya Python ifatwa nkikibazo cyumutekano kuri moderi?
    • Kuremera birashobora gukora code uko bishakiye yashyizwe muri dosiye
    • Ihagarika dosiye cyane
    • Cyakora muri wikendi
    • Isiba icyitegererezo cyumwimerere
  2. Ni izihe nyungu nyamukuru z'imiterere ya ONNX?
    • Nuburyo buto bushoboka
    • Ireka icyitegererezo cyatojwe murwego rumwe gikoreshwa mubindi bihe byinshi byindimi
    • Irashobora gufungurwa gusa muri PyTorch
    • Irahita itezimbere ukuri
  3. Ni ukubera iki abashinzwe umutekano bamenyekanye cyane mugusangira uburemere bw'icyitegererezo?
    • Ikoresha code kumutwaro kugirango byorohe
    • Nuburyo bwa kera buraboneka
    • Irabika gusa amakuru ya tensor gusa mumutekano, hamwe na memoire yihuta-mappable yipakurura kandi nta code ikora
    • Irabika gusa icyitegererezo cyukuri
  4. GGUF ifitanye isano niki nikibazo cyo gukoresha?
    • Kubika urupapuro
    • Guhisha imeri
    • Imyitozo yimyitozo kuva mubicu
    • Gukoresha urugero runini rwururimi rwicyitegererezo neza kubikoresho byaho
  5. Ni ubuhe buryo bwo guhanahana amakuru nka ONNX bubika cyane?
    • Igishushanyo gisanzwe cyo kubara hamwe nuburemere bwikitegererezo
    • Video yerekana inzira y'amahugurwa
    • Gusa amahugurwa yamakuru
    • Umushinga winkomoko yamakuru yatanzwe
  6. When exporting a Keras 3 model for TensorFlow serving, which directory format can model.export produce?
    • GGUF
    • Yakijijwe
    • CSV
    • A pickle file containing the entire Python application
  7. After exporting a model to ONNX for a new runtime, what should the team check?
    • That the ONNX file guarantees identical speed on every device
    • That the export automatically includes the original training data
    • That supported operators run and outputs match the reference model on representative inputs
    • That no preprocessing code is needed
  8. Why can a state-dictionary checkpoint be preferable to loading a whole Python object from an untrusted file?
    • It guarantees the model architecture is embedded
    • It makes every checkpoint safe regardless of loader and version
    • It automatically converts the model to ONNX
    • It can load tensor state without reconstructing arbitrary pickled Python objects, subject to the loader’s security settings