ndrplz/ConvLSTM_pytorch

Stars
1,827
Rank 25,342 (Top 0.6 %)
Language
Python
License
MIT License
Created about 7 years ago
Updated about 4 years ago

ndrplz/ConvLSTM_pytorch

ndrplz

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Implementation of Convolutional LSTM in PyTorch.

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.

self-driving-car

Udacity Self-Driving Car Engineer Nanodegree projects.

google-drive-downloader

Minimal class to download shared files from Google Drive.

surround_vehicles_awareness

Learn to map surrounding vehicles onto a bird's eye view of the scene.

machine_learning_lectures

Collection of lectures and lab lectures on machine learning and deep learning. Lab practices in Python and TensorFlow.

dilation-tensorflow

A native Tensorflow implementation of semantic segmentation according to Multi-Scale Context Aggregation by Dilated Convolutions (2016). Optionally uses the pretrained weights by the authors.

dreyeve

[TPAMI 2018] Predicting the Driver’s Focus of Attention: the DR(eye)VE Project. A deep neural network learnt to reproduce the human driver focus of attention (FoA) in a variety of real-world driving scenarios.

differentiable-renderer

Rastering algorithm to approximate the rendering of a 3D model silhouette in a fully differentiable way.

small_norb

Python wrapper to small NORB dataset

semiparametric

[TPAMI 2020] Generating Novel Views of Vehicles via Semi-parametric Guidance. A semi-parametric approach for synthesizing novel views of a rigid object from a single monocular image.

planar-distance-estimation

This repository accompanies the laboratory practice on Planar Distance Estimation for the AI4Automotive course at University of Modena and Reggio Emilia.

transforming-autoencoders

Transforming Autoencoder (Hinton et al.) implementation in TensorFlow. A way to get hands dirty with Hinton's capsules.

computer_vision_utils

Everything that I code more than twice during my PhD will end up here.

CIFAR-10

Python plug-and-play wrapper to CIFAR-10 dataset.

eurlex-toolbox

Python toolbox to load, parse and process Official Journals of the European Union (EU).

haralick-labeling-visualized

Visual explanation and python implementation of Haralick algorithm for connected component labeling

lesser-known-python

Collection of lesser-known python features that you will love (and use).

Jupyter Notebook

micromachine

toy example of q-learning algorithm

dotfiles

just my dotfiles

pong_motion

Pong game based on motion tracking of the two players.