Skip to content
View Roundbeann's full-sized avatar
😀
Out sick
😀
Out sick

Block or report Roundbeann

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Popular repositories Loading

  1. DeepLearning-Basic DeepLearning-Basic Public

    包含对梯度下降、矩阵求导、最小二乘法、图像分类、文本分类、文本生成、seq2seq机器翻译、RNN、LSTM、transformer(位置编码、attention机制)等任务和算法的实现。

    Python

  2. DDPM DDPM Public

    1.forward:DDPM的一次性加噪过程。2.backward:Unet根据【a.噪声图像 b.噪声图片的加噪步长】预测【当前图片在上一个加噪步长中添加的噪声含量】。3.sample:从N(0~1)的噪声中,根据末态步长,利用去噪公式逐步预测上一步添加的噪声,生成t=0时的“干净图像”。

    Python

  3. Nerf Nerf Public

    1.创建Nerf的dataloader:返回每张图像1024个随机像素位置对应真实三维世界的1024条光线上的64个均匀采样点(1024*64*(x,y,x)) 2.利用MLP,以这些空间位置作为输入,输出每个空间点的体密度和颜色值 3.利用体渲染公式,对一条光线上的点进行加权求和,渲染得到光线对应像素的颜色值 4.使用像素真实的颜色值 和 体渲染加权求和得到的颜色值做损失优化网络参数

    Python

  4. Test-On-Diffusers Test-On-Diffusers Public

    利用Diffuser库,对扩散模型的噪声分配、加噪、噪声预测、去噪过程进行实现。(调用封装好的API)

    Jupyter Notebook