Idanwo Itọnisọna Ọfẹ Classifier

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

1. Why do diffusion models apply classifier-free guidance?
   • Lati teramo bi o ṣe sunmọ itusilẹ ti o tẹle itọsi imuduro
   • Lati compress awoṣe sinu iwọn kekere
   • Lati yọ koodu koodu kuro patapata
   • Lati yi awọn aworan pada si ohun ohun
2. Bawo ni awoṣe ṣe kọ ẹkọ lati ṣe awọn asọtẹlẹ lainidi fun itọnisọtọ-ọfẹ?
   • Nipa ikẹkọ a keji lọtọ classifier
   • Nipa sisọ awọn kondisona silẹ laileto lakoko ikẹkọ
   • Nipa lilo awọn aworan dudu nikan
   • Nipa piparẹ GPU
3. Kini jijẹ iwọn itọnisọna ni gbogbogbo ṣe?
   • Nigbagbogbo mu oniruuru dara si
   • Yọ ipa ti o tọ kuro
   • Ṣe okunkun ifaramọ ni kiakia ṣugbọn o le fa oversaturation
   • O jẹ ki aworan naa jẹ grẹyscale
4. Ni aijọju melo ni awọn kọja siwaju fun igbesẹ atako ṣe itọsọna ti ko ni iyasọtọ ti boṣewa nilo?
   • Odo
   • Mẹwa
   • Ọgọrun
   • Meji (ipo kan, ọkan lainidi)
5. Anfani wo ni itoni-ọfẹ classifier ni lori itọsọna classifier?
   • Ko nilo classifier ikẹkọ lọtọ
   • O nilo data ikẹkọ diẹ sii
   • O ṣiṣẹ nikan lori awọn awoṣe ọrọ
   • O ṣe imukuro ilana itankale
6. In the common classifier-free guidance formula, what does guidance scale s=0 produce?
   • The conditional prediction with extra amplification
   • The unconditional model prediction without conditioning
   • A prediction from a separately trained classifier
   • A sample with all denoising removed
7. How does classifier-free guidance combine model outputs at inference?
   • It combines two image classifiers
   • It removes the conditional prompt
   • It combines conditional and unconditional score estimates
   • It adds a learned reward model after decoding
8. What does a guidance scale of 1 generally correspond to in the common formulation?
   • The unconditional prediction only
   • A classifier-based gradient
   • A zero-noise image
   • The conditional prediction without extra guidance amplification