Guide-yakabatana mibvunzo · Pakati Nhanho

GLIDE Diffusion Model Quiz

Ongorora chizvarwa chinotungamirwa nemavara cheGLIDE uye pendi, kudzidziswa kwezvimiso, kuenzanisa-yemahara sampling, uye nhoroondo yayo yemhando yezvivakwa.

Nzira dzekutungamira dzinoenderanaGlide Diffusion Model
Mubvunzo 1 ye 8

Ndeipi nzira yekutungamira iyo GLIDE yakawana yakagadzira zvirinani, zvakanyanya kukurumidza-yakavimbika mifananidzo?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Ndeipi nzira yekutungamira iyo GLIDE yakawana yakagadzira zvirinani, zvakanyanya kukurumidza-yakavimbika mifananidzo?
    • Classifier-yemahara kutungamira
    • CLIP nhungamiro
    • Hapana kutungamirirwa
    • Manual editing
  2. What size did the published full GLIDE base diffusion model have, before counting its upsampler?
    • About 3.5 thousand parameters
    • About 350 billion parameters
    • About 3.5 billion parameters
    • No trainable parameters
  3. Kutungamira-yemahara kutungamira kunoshanda sei panguva yekudzidziswa?
    • Iyo modhi inongoona iyo chaiyo kukurumidza
    • Mumwe akaparadzana mufananidzo classifier anodzidziswa pamwe chete
    • Mazano anoturikirwa kunhamba zvisina tsarukano
    • Iyo modhi dzimwe nguva inoona iyo chaiyo kukurumidza uye dzimwe nguva isina chinhu
  4. Which later system describes its diffusion decoder as modifying the GLIDE architecture in the DALL-E 2 research paper?
    • The original text-only GPT-2 model
    • The unCLIP system associated with DALL-E 2
    • The Whisper speech recognizer
    • The CLIP contrastive encoder alone
  5. Sei OpenAI yangoburitsa kavhezheni diki, akasefa eGLIDE pachena?
    • Iyo yakazara modhi yakarasika
    • Yaingomhanya pamakomputa makuru
    • Kunetseka pamusoro pekushandiswa zvisizvo kwejenareta rine simba remufananidzo
    • Rezinesi kubva kune wechitatu bato
  6. Ndechipi chinoshanda chekugadzirisa chakatsigirwa neGLIDE?
    • Text-driven inpainting
    • Kunyoreswa kweaudio
    • Spreadsheet formulas
    • Video rendering
  7. How did GLIDE's upsampler complement its base text-conditioned diffusion model?
    • It replaced the text prompt with an audio transcript
    • It increased the resolution of the image produced by the base model
    • It converted the image into the training tokenizer's vocabulary
    • It supplied manual labels for every generated object
  8. At GLIDE sampling time, how does classifier-free guidance strengthen prompt conditioning?
    • It retrains the model weights after every generated pixel
    • It requires a separate class-label classifier to score every step
    • It replaces the conditional prediction with the unconditional one
    • It combines conditional and unconditional predictions, extrapolating toward the conditional one