AI Rank
中文
← Open Source
ndrplz

ConvLSTM_pytorch

Implementation of Convolutional LSTM in PyTorch.

Model DevelopmentArchitecturePython
Open on GitHub
Momentum
+0stars in 24 hours0.0%
2.27k
Stars
441
Forks
+0
This week
3
Contributors
Created 2017-08-04 · Updated 2026-10-07 · #8794 today
Top developers
ndrplzstefanopiniDansYU

ndrplz/ConvLSTM_pytorch is ranked 8,794 with 2,268 stars.

Same-category comparison

ndrplz/ConvLSTM_pytorch is ranked 8,794 among these 8 peers; aigc-apps/EasyAnimate is ranked 8,796.

Same-category comparison
NameRankMetrics
astooke/rlpyt8,782
Language:
Python
Stars:
2,278
Forks:
326
Description:
Reinforcement Learning in PyTorch.
salesforce/TransmogrifAI8,783
Language:
Scala
Stars:
2,278
Forks:
398
Description:
TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library for building modular, reusable, strongly typed machine learning workflows on Apache Spark with minimal hand-tuning.
rsennrich/subword-nmt8,785
Language:
Python
Stars:
2,276
Forks:
470
Description:
Unsupervised Word Segmentation for Neural Machine Translation and Text Generation.
MineDojo/MineDojo8,789
Language:
Java
Stars:
2,271
Forks:
195
Description:
Building Open-Ended Embodied Agents with Internet-Scale Knowledge.
aigc-apps/EasyAnimate8,796
Language:
Python
Stars:
2,266
Forks:
187
Description:
📺 An End-to-End Solution for High-Resolution and Long Video Generation Based on Transformer Diffusion.
galilai-group/stable-worldmodel8,803
Language:
Python
Stars:
2,261
Forks:
287
Description:
A platform for reproducible world model research and evaluation.
TuringLang/Turing.jl8,804
Language:
Julia
Stars:
2,260
Forks:
248
Description:
Bayesian inference with probabilistic programming.
ShoufaChen/DiffusionDet8,805
Language:
Python
Stars:
2,259
Forks:
186
Description:
[ICCV2023 Best Paper Finalist] PyTorch implementation of DiffusionDet (https://arxiv.org/abs/2211.09788).
Key parameters and specifications
Key parameters and specifications
ParameterValue
LanguagePython
CategoryModel Development
SubcategoryArchitecture
Stars2,268
Forks441
Contributors3
Created date2017-08-04
Updated date2026-10-07
Stars in 1 day0
Stars in 7 days0
Rank8,794
Previous rank8,858
Rank change64
7-day stars rank12,087
Previous 7-day stars rank12,146
7-day stars rank change59
Total stars rank5,727
Previous total stars rank5,722
Total stars rank change-5
CountryGermany
README summary

ConvLSTM_pytorch **This** file **contains the implementation of Convolutional LSTM in PyTorch** made by me and DavideA. We started from this implementation and heavily refactored it add added features to match our needs. Please note that in this repository we implement the following dynamics: which is a bit different from the one in the original paper. How to Use The module derives from so it can be used as any other PyTorch module. The ConvLSTM class supports an arbitrary number

of layers. In this case, it can be specified the hidden dimension (that is, the number of channels) and the kernel size of each layer. In the case more layers are present but a single value is provided, this is replicated for all the layers. For example, in the following snippet each of the three layers has a different hidden dimension but the same kernel size. ) Comment code Add docs Add example usage on a toy problem Implement stateful mechanism

. Disclaimer This is still a work in progress and is far from being perfect: if you find any bug please don't hesitate to open an issue.

Frequently asked questions

How many stars and forks are recorded?

ndrplz/ConvLSTM_pytorch has 2,268 stars and 441 forks.

What is the repository rank?

ndrplz/ConvLSTM_pytorch is ranked 8,794.

What language and category are recorded?

ndrplz/ConvLSTM_pytorch has 2,268 stars, uses Python and belongs to Model Development.

Which repository is closest in rank?

ndrplz/ConvLSTM_pytorch is compared with aigc-apps/EasyAnimate, ranked 8,796 with 2,266 stars.

README

ConvLSTM_pytorch

This file contains the implementation of Convolutional LSTM in PyTorch made by me and DavideA.

We started from this implementation and heavily refactored it add added features to match our needs.

Please note that in this repository we implement the following dynamics:

which is a bit different from the one in the original paper.

How to Use

The ConvLSTM module derives from nn.Module so it can be used as any other PyTorch module.

The ConvLSTM class supports an arbitrary number of layers. In this case, it can be specified the hidden dimension (that is, the number of channels) and the kernel size of each layer. In the case more layers are present but a single value is provided, this is replicated for all the layers. For example, in the following snippet each of the three layers has a different hidden dimension but the same kernel size.

Example usage:

model = ConvLSTM(input_dim=channels,
                 hidden_dim=[64, 64, 128],
                 kernel_size=(3, 3),
                 num_layers=3,
                 batch_first=True
                 bias=True,
                 return_all_layers=False)

TODO (in progress...)

  • Comment code
  • Add docs
  • Add example usage on a toy problem
  • Implement stateful mechanism
  • ...

Disclaimer

This is still a work in progress and is far from being perfect: if you find any bug please don't hesitate to open an issue.

Nearby in the ranking
Similar items