引導式測驗 · 中等 等級
擴散模型測驗
測試 DDPM 去噪、噪音目標、文字調節、壓縮潛在、訓練目標、更快的取樣、解碼和噪音計劃。
問題 1 的 8
經典的 DDPM 取樣如何從初始雜訊樣本產生影像?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 經典的 DDPM 取樣如何從初始雜訊樣本產生影像?
- 透過複製所需的相同訓練影像
- 透過將輸出檔名指定為其像素值
- 透過不執行任何模型運算
- 透過遵循連續學習到的反向過程步驟
- 在常見的雜訊預測 DDPM 參數化中,網路估計的訓練目標是什麼?
- 影像的市場價格
- 加入訓練範例中的高斯雜訊
- 影像的版權所有者
- 所需的最終檔案副檔名
- 在文字條件潛在擴散公式中,提示詞嵌入(prompt embeddings)如何影響去雜訊過程?
- 透過交叉注意力(cross-attention)調節
- 僅透過更改檔案副檔名
- 透過移除每一層學習到的層
- 透過保證產生與訓練影像完全一致的複本
- 為什麼潛在擴散模型要在壓縮表示中執行去雜訊?
- 為了保證與每個像素空間模型完全相同的重建
- 為了消除所有神經運算
- 為了降低繁重去雜訊運算的維度
- 為了使每個輸出必然為單色
- Which component is not required by the classic DDPM denoising training objective?
- Training examples
- An adversarial discriminator trained to distinguish real from generated samples
- A defined corruption process
- A learned reverse-process model
- What does progressive distillation of a diffusion sampler aim to reduce?
- The need to evaluate generation quality
- Every condition supplied to the model
- The number of pixels in every possible output by definition
- The number of sampling steps or model evaluations
- After denoising in a latent diffusion image model, which component reconstructs image pixels from the latent representation?
- A filename formatter
- The original training-data shuffle
- The autoencoder decoder
- An adversarial label threshold in every model
- What does a DDPM forward noise schedule specify across successive steps?
- How much noise variance is introduced
- A guarantee that every sample is factually true
- The copyright license for the training data
- The alphabetical ordering of prompt words