17 results found Sort:

labmlai
annotated_deep_learning_paper_implementations labmlai
5.8k
56.4k
mit
457
🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...
gan lora pytorch attention optimizers transformer transformers deep-learning neural-networks machine-learning literate-programming deep-learning-tutorial reinforcement-learning
Created 2020-08-25
829 commits to master branch, last one 2 months ago
lucidrains
lion-pytorch lucidrains
50
2.0k
mit
15
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
optimizers deep-learning evolutionary-search artificial-intelligence
Created 2023-02-15
45 commits to main branch, last one 5 months ago
elixir-nx
axon elixir-nx
103
1.6k
apache-2.0
45
Nx-powered Neural Networks
nx elixir optimizers deep-learning neural-networks
Created 2021-01-25
604 commits to main branch, last one 7 days ago
gugarosa
opytimizer gugarosa
41
606
apache-2.0
15
🐦 Opytimizer is a Python library consisting of meta-heuristic optimization algorithms.
python optimizers bioinspired optimization meta-heuristic artificial-intelligence meta-heuristic-optimization
Created 2017-11-01
821 commits to main branch, last one 3 months ago
Yonghongwei
Gradient-Centralization Yonghongwei
80
533
unknown
17
A New Optimization Technique for Deep Neural Networks
optimizers deep-neural-networks optimization-technique gradient-centralization
Created 2020-03-31
138 commits to master branch, last one 2 years ago
CyberZHG
keras-radam CyberZHG
46
325
mit
15
RAdam implemented in Keras & TensorFlow
adam keras radam optimizers tensorflow rectified-adam
This repository has been archived (exclude archived)
Created 2019-08-16
38 commits to master branch, last one 2 years ago
OverLordGoldDragon
keras-adamw OverLordGoldDragon
25
167
mit
6
Keras/TF implementation of AdamW, SGDW, NadamW, Warm Restarts, and Learning Rate multipliers
sgd adamw keras nadam adamwr optimizers tensorflow warm-restarts learning-rate-multipliers
Created 2019-09-27
53 commits to master branch, last one 2 years ago
clovaai
frostnet clovaai
18
106
mit
7
FrostNet: Towards Quantization-Aware Network Architecture Search
pytorch optimizers quantization deep-learning classification style-transfer computer-vision object-detection int8-quantization post-quantization network-architecture semantic-segmentation quantization-aware-training quantization-efficient-network
Created 2020-06-17
36 commits to master branch, last one 3 years ago
Rishit-dagli
Gradient-Centralization-TensorFlow Rishit-dagli
21
105
apache-2.0
5
Instantly improve your training performance of TensorFlow models with just 2 lines of code!
pip python python3 optimizers tensorflow tensorflow2 deep-learning neural-network python-package machine-learning deep-neural-networks optimization-technique gradient-centralization
Created 2021-02-15
104 commits to main branch, last one 3 years ago
palle-k
DL4S palle-k
13
102
mit
5
Accelerated tensor operations and dynamic neural networks based on reverse mode automatic differentiation for every device that can run Swift - from watchOS to Linux
swift tensor autograd optimizers derivatives deep-learning neural-networks gradient-descent machine-learning recurrent-networks deep-neural-networks swift-machine-learning automatic-differentiation recurrent-neural-networks convolutional-neural-networks
Created 2019-03-10
311 commits to master branch, last one 3 years ago
usef-kh
fer usef-kh
34
98
unknown
2
Code for the paper "Facial Emotion Recognition: State of the Art Performance on FER2013"
fer loss tuning vggnet fer2013 optimizers schedulers architecture saliency-maps facial-emotions
Created 2021-05-06
13 commits to master branch, last one about a year ago
lucidrains
adam-atan2-pytorch lucidrains
1
94
mit
3
Implementation of the proposed Adam-atan2 from Google Deepmind in Pytorch
adam stability optimizers deep-learning artificial-intelligence
Created 2024-07-30
21 commits to main branch, last one 28 days ago
decile-team
submodlib decile-team
36
87
mit
8
Summarize Massive Datasets using Submodular Optimization
optimizers submodular greedy-algorithms data-summarization submodular-functions submodular-optimization combinatorial-optimization submodular-information-measures
Created 2020-10-20
220 commits to master branch, last one 2 months ago
hfxunlp
transformer hfxunlp
9
63
gpl-3.0
8
Neutron: A pytorch based implementation of Transformer and its variants.
python3 pytorch seq2seq ensemble multi-gpu optimizers beam-search transformer average-models multilingual-nmt context-aware-nmt relative-position dynamic-batch-size sentential-context attention-is-all-you-need average-attention-network dynamic-sentence-sampling neural-machine-translation natural-language-processing robust-neural-machine-translation
This repository has been archived (exclude archived)
Created 2019-01-11
70 commits to master branch, last one about a year ago
warner-benjamin
optimi warner-benjamin
2
59
mit
2
Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers
pytorch optimizers deep-learning
Created 2023-10-25
85 commits to main branch, last one 4 months ago
ProudElm
solaredgeoptimizers ProudElm
13
49
unknown
5
Intergration to get optimizers information from the SolarEdge portal
python optimizers solaredge-api
Created 2022-08-03
66 commits to main branch, last one about a year ago
shreyansh26
ML-Optimizers-JAX shreyansh26
2
43
unknown
3
Toy implementations of some popular ML optimizers using Python/JAX
jax adam momentum optimizers adam-optimizer gradient-descent machine-learning optimization-algorithms
Created 2021-06-20
9 commits to master branch, last one 3 years ago