labmlai/annotated_deep_learning_paper_implementations

Issues

• Training code or references for training the latent diffusion model on a custom dataset

  #195 opened 10 months ago by risejl
  3

• this is regarding a doubt in diffusion/ddpm/experiment.py

  #250 opened 2 months ago by AbhinavJangra29
  1

• "pip install labml-nn" generated errors. How to resolve it and complete the installation?

  #247 opened 2 months ago by jxwanguab
  0

• question about RotaryPEMultiHeadAttention: rotary_percentage

  #246 opened 2 months ago by YOONSEOKHEO
  0

• which one is the implementation of "NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis"?

  #200 opened 3 months ago by guyuezuntinggithub
  1

• Implement new models/architectures:

  #197 opened 3 months ago by Adesoji1
  0

• Make my own annotations

  #236 opened 3 months ago by sonderlau
  4

• ppo code running error

  #245 opened 3 months ago by cxw-droid
  0

• Bug in rotary positional embedding

  #244 opened 3 months ago by scv11
  0

• Wrong Image Scale in DDPM

  #241 opened 3 months ago by ww-rm
  0

• DDPM interpolation formula error

  #238 opened 4 months ago by jjjuuuun
  0

• Scripts Scripts_ Img2img get is empty

  #217 opened 7 months ago by fu-jianhua
  1

• :kr: Korean Translation

  #237 opened 4 months ago by movie5
  0

• 翻译翻译

  #225 opened 4 months ago by Vector-Cross
  0

• question about RoPE code

  #227 opened 6 months ago by yukyeongmin
  3

• Question about gatv2 code

  #228 opened 6 months ago by XiaokangORCA
  0

• Bug in implementation of Rotary Positional Embeddings

  #215 opened 8 months ago by Inkorak
  1

• Wrong output of shift right example in the commnets?

  #218 opened 6 months ago by harveyaot
  1

• Network connection issues during training

  #194 opened 6 months ago by XYTriste
  3

• Request for Paper Implementation - Neural Operators

  #219 opened 7 months ago by Robertboy18
  0

• Incorrect expression in explanation

  #220 opened 6 months ago by adrshsrvstv
  1

• Is there some errors in transformers mha.py

  #216 opened 8 months ago by lqzzy
  1

• Stride = 2 only for the first block of the entire ResNet

  #205 opened 9 months ago by PavelShtykov
  0

• Small issue in nucleus sampling explanation + implementation

  #203 opened 9 months ago by ascher8
  0

• q,k,v have different shape but torch.stack works?

  #202 opened 9 months ago by junsukha
  0

• b

  #199 opened 10 months ago by AmIevil71
  0

• Bug in Transformer-XL shift method

  #185 opened a year ago by Bearnardd
  1

• can not run ViT(vision transformer) experiment file (failed to connect to https://api.labml.ai/api/vl/track?run%20wuid-87829.c05191leeae2db06088ee9ee4&labml%20version=0.4.162)

  #189 opened a year ago by HiFei4869
  2

• Dimension of subsequent layers in Hypernetwork

  #169 opened a year ago by Simply-Adi
  3

• want to use CelebA dataset，but there is an issue

  #190 opened a year ago by Z0Victor
  2

• Como

  #188 opened a year ago by chinoresioe
  0

• do you have code for BERT?

  #187 opened a year ago by Sandy4321
  1

• MultiHeadAttention parameter setting

  #180 opened a year ago by LXXiaogege
  2

• The classifier-free guidance of diffusion models is wrong.

  #177 opened a year ago by luowyang
  0

• is the kld not in ppo total loss?

  #171 opened a year ago by pandaupc
  1

• Where are the weights? Where is the .pt file for the trained model?

  #170 opened a year ago by MotorCityCobra
  2

• Missing activation for the time embedding inside ResidualBlock for DDPM?

  #165 opened a year ago by EliasNehme
  3

• Request for Paper Implementation

  #167 opened a year ago by TruongNhanNguyen
  1

• Crashed on labml_nn/neox/samples/finetune.py

  #166 opened a year ago by Keith-Hon
  2

• StyleGAN2: ToRGB module with activation?

  #162 opened a year ago by Dao007forever
  2

• A tiny bug in unet.py

  #184 opened a year ago by lwb2099
  0

• Where can I get the sample

  #186 opened a year ago by yaoysyao
  0

• mah

  #179 opened a year ago by LXXiaogege
  0

• Unable to run In-paint images script

  #178 opened a year ago by Vikramank
  1

• StyleGAN2: Why don't you multiply path length penalty by the lazy regularization interval?

  #161 opened a year ago by yanisnotavocado
  0

• Error displaying widget: model not found

  #156 opened a year ago by zhuyb00
  1

• What is get_eps in DDIM code?

  #163 opened a year ago by cjfghk5697
  0

• Papers

  #160 opened a year ago by horndoc
  0

• The problem with the description of the output in the code of Prepare for multi-head attention

  #157 opened a year ago by JosieChen1214
  2

• How to instantiate the module

  #155 opened a year ago by hailuu684
  1