labmlai/annotated_deep_learning_paper_implementations
๐งโ๐ซ 60 Implementations/tutorials of deep learning papers with side-by-side notes ๐; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), ๐ฎ reinforcement learning (ppo, dqn), capsnet, distillation, ... ๐ง
Jupyter NotebookMIT
Issues
- 3
Training code or references for training the latent diffusion model on a custom dataset
#195 opened by risejl - 1
- 0
"pip install labml-nn" generated errors. How to resolve it and complete the installation?
#247 opened by jxwanguab - 0
- 1
which one is the implementation of "NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis"?
#200 opened by guyuezuntinggithub - 0
Implement new models/architectures:
#197 opened by Adesoji1 - 4
Make my own annotations
#236 opened by sonderlau - 0
ppo code running error
#245 opened by cxw-droid - 0
Bug in rotary positional embedding
#244 opened by scv11 - 0
Wrong Image Scale in DDPM
#241 opened by ww-rm - 0
DDPM interpolation formula error
#238 opened by jjjuuuun - 1
Scripts Scripts_ Img2img get is empty
#217 opened by fu-jianhua - 0
:kr: Korean Translation
#237 opened by movie5 - 0
็ฟป่ฏ็ฟป่ฏ
#225 opened by Vector-Cross - 3
question about RoPE code
#227 opened by yukyeongmin - 0
Question about gatv2 code
#228 opened by XiaokangORCA - 1
Bug in implementation of Rotary Positional Embeddings
#215 opened by Inkorak - 1
- 3
Network connection issues during training
#194 opened by XYTriste - 0
- 1
Incorrect expression in explanation
#220 opened by adrshsrvstv - 1
Is there some errors in transformers mha.py
#216 opened by lqzzy - 0
- 0
- 0
q,k,v have different shape but torch.stack works?
#202 opened by junsukha - 0
- 1
Bug in Transformer-XL shift method
#185 opened by Bearnardd - 2
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 by HiFei4869 - 3
Dimension of subsequent layers in Hypernetwork
#169 opened by Simply-Adi - 2
want to use CelebA dataset๏ผbut there is an issue
#190 opened by Z0Victor - 0
Como
#188 opened by chinoresioe - 1
do you have code for BERT?
#187 opened by Sandy4321 - 2
MultiHeadAttention parameter setting
#180 opened by LXXiaogege - 0
- 1
is the kld not in ppo total loss?
#171 opened by pandaupc - 2
- 3
- 1
Request for Paper Implementation
#167 opened by TruongNhanNguyen - 2
Crashed on labml_nn/neox/samples/finetune.py
#166 opened by Keith-Hon - 2
StyleGAN2: ToRGB module with activation?
#162 opened by Dao007forever - 0
A tiny bug in unet.py
#184 opened by lwb2099 - 0
Where can I get the sample
#186 opened by yaoysyao - 0
mah
#179 opened by LXXiaogege - 1
Unable to run In-paint images script
#178 opened by Vikramank - 0
StyleGAN2: Why don't you multiply path length penalty by the lazy regularization interval?
#161 opened by yanisnotavocado - 1
Error displaying widget: model not found
#156 opened by zhuyb00 - 0
What is get_eps in DDIM code?
#163 opened by cjfghk5697 - 0
- 2
The problem with the description of the output in the code of Prepare for multi-head attention
#157 opened by JosieChen1214 - 1
How to instantiate the module
#155 opened by hailuu684