Pytorch Implementation for Dilated Continuous Random Field

Overview

DilatedCRF

Pytorch implementation for fully-learnable DilatedCRF.


If you find my work helpful, please consider our paper:

@article{Mo2022dilatedcrf,
    title={Dilated Continuous Random Field for Semantic Segmentation},  
    author={Xi Mo, Xiangyu Chen, Cuncong Zhong, Rui Li, Kaidong Li, Sajid Usman},
    booktitle={IEEE International Conference on Robotics and Automation}, 
    year={2022}  
}

Easy Setup

Please install these required packages by official guidance:

python >= 3.6
pytorch >= 1.0.0
torchvision
pillow
numpy

How to Use

1. Prepare dataset

  • Dowload suction-based-grasping-dataset.zip (1.6GB) [link]. Please cite relevant paper:
@article{zeng2018robotic, 
    title={Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching},  
    author={Zeng, Andy and Song, Shuran and Yu, Kuan-Ting and Donlon, Elliott and Hogan, Francois Robert and Bauza, Maria and Ma, Daolin and Taylor, Orion and Liu,     Melody and Romo, Eudald and Fazeli, Nima and Alet, Ferran and Dafle, Nikhil Chavan and Holladay, Rachel and Morona, Isabella and Nair, Prem Qu and Green, Druck and Taylor, Ian and Liu, Weber and Funkhouser, Thomas and Rodriguez, Alberto},  
    booktitle={Proceedings of the IEEE International Conference on Robotics and Automation}, 
    year={2018}  
}
  • Train your own semantic segmentation classifers on the suction dataset, generate training samples and test samples for DilatedCRF. You can also download my training set and test set (872MB) [link], extract the default folder dataset to the main directory.
    NOTE: Customized training and test samples must be organized the same as the default dataset format.

2. Train network

  • If you want to customize training process, modify utils/configuration.py parameters according to its instructions.

  • Train DilatedCRF use default dataset folder, or customized dataset path by -d argument.
    NOTE: checkpoints will be written to the default folder checkpoint.

    python DialatedCRF.py -train
    

    or restore training using the lattest .pt file stored in default folder checkpoint:

    python DialatedCRF.py -train -r
    

    or you may want to use specified checkpoint:

    python DialatedCRF.py -train -r -c path/to/your/ckpt
    

    Note that checkpoint file must match the parameter "SCALE" specified in utils/configuration.py. To specify customized dataset folder, use:

    python RGANet.py -train -d your/dataset/path
    

3. Validation

  • Complete dataset folder mentioned above and a valid checkpoint are required. You can download my checkpoint for "SCALE" = 0.25 (42.4MB) [link], be sure to adjust corresponding configurations beforehand. Then run:

    python DialatedCRF.py -v
    

    or you may specify dataset folder by -d:

    python DialatedCRF.py -v -d your/path/to/dataset/folder
    
  • Final results will be written to folder results. Metrics including Jaccard, F1-score, accuracy, etc., will be gathered as evaluation.txt in the folder results/evaluation


Contributed by Xi Mo,
License: Apache 2.0

Owner
DunnoCoding_Plus
CODE HARD, LIVE HAPPY.
DunnoCoding_Plus
N-Omniglot is a large neuromorphic few-shot learning dataset

N-Omniglot [Paper] || [Dataset] N-Omniglot is a large neuromorphic few-shot learning dataset. It reconstructs strokes of Omniglot as videos and uses D

11 Dec 05, 2022
Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)

Certified Robustness to Adversarial Word Substitutions This is the official GitHub repository for the following paper: Certified Robustness to Adversa

Robin Jia 38 Oct 16, 2022
CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation

CoTr: Efficient 3D Medical Image Segmentation by bridging CNN and Transformer This is the official pytorch implementation of the CoTr: Paper: CoTr: Ef

218 Dec 25, 2022
Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks

LMMNN Using Random Effects to Account for High-Cardinality Categorical Features and Repeated Measures in Deep Neural Networks This is the working dire

Giora Simchoni 10 Nov 02, 2022
Unbalanced Feature Transport for Exemplar-based Image Translation (CVPR 2021)

UNITE and UNITE+ Unbalanced Feature Transport for Exemplar-based Image Translation (CVPR 2021) Unbalanced Intrinsic Feature Transport for Exemplar-bas

Fangneng Zhan 183 Nov 09, 2022
Simple API for UCI Machine Learning Dataset Repository (search, download, analyze)

A simple API for working with University of California, Irvine (UCI) Machine Learning (ML) repository Table of Contents Introduction About Page of the

Tirthajyoti Sarkar 223 Dec 05, 2022
tf2onnx - Convert TensorFlow, Keras and Tflite models to ONNX.

tf2onnx converts TensorFlow (tf-1.x or tf-2.x), tf.keras and tflite models to ONNX via command line or python api.

Open Neural Network Exchange 1.8k Jan 08, 2023
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

[ICLR 2022] Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity by Shiwei Liu, Tianlong Chen, Zahra Atashgahi, Xiaohan Chen, Ghada Sokar, Elen

VITA 18 Dec 31, 2022
The code of "Dependency Learning for Legal Judgment Prediction with a Unified Text-to-Text Transformer".

Code data_preprocess.py: preprocess data for Dependent-T5. parameters.py: define parameters of Dependent-T5. train_tools.py: traning and evaluation co

1 Apr 21, 2022
This program presents convolutional kernel density estimation, a method used to detect intercritical epilpetic spikes (IEDs)

Description This program presents convolutional kernel density estimation, a method used to detect intercritical epilpetic spikes (IEDs) in [Gardy et

Ludovic Gardy 0 Feb 09, 2022
Python library to receive live stream events like comments and gifts in realtime from TikTok LIVE.

TikTokLive A python library to connect to and read events from TikTok's LIVE service A python library to receive and decode livestream events such as

Isaac Kogan 277 Dec 23, 2022
Extracting and filtering paraphrases by bridging natural language inference and paraphrasing

nli2paraphrases Source code repository accompanying the preprint Extracting and filtering paraphrases by bridging natural language inference and parap

Matej Klemen 1 Mar 09, 2022
End-to-end image segmentation kit based on PaddlePaddle.

English | 简体中文 PaddleSeg PaddleSeg has released the new version including the following features: Our team won the 6.2k Jan 02, 2023

HomeAssitant custom integration for dyson

HomeAssistant Custom Integration for Dyson This custom integration is still under development. This is a HA custom integration for dyson. There are se

Xiaonan Shen 232 Dec 31, 2022
A embed able annotation tool for end to end cross document co-reference

CoRefi CoRefi is an emebedable web component and stand alone suite for exaughstive Within Document and Cross Document Coreference Anntoation. For a de

PythicCoder 39 Dec 12, 2022
Mall-Customers-Segmentation - Customer Segmentation Using K-Means Clustering

Overview Customer Segmentation is one the most important applications of unsupervised learning. Using clustering techniques, companies can identify th

NelakurthiSudheer 2 Jan 03, 2022
Implements VQGAN+CLIP for image and video generation, and style transfers, based on text and image prompts. Emphasis on ease-of-use, documentation, and smooth video creation.

VQGAN-CLIP-GENERATOR Overview This is a package (with available notebook) for running VQGAN+CLIP locally, with a focus on ease of use, good documentat

Ryan Hamilton 98 Dec 30, 2022
2nd solution of ICDAR 2021 Competition on Scientific Literature Parsing, Task B.

TableMASTER-mmocr Contents About The Project Method Description Dependency Getting Started Prerequisites Installation Usage Data preprocess Train Infe

Jianquan Ye 298 Dec 21, 2022
Use stochastic processes to generate samples and use them to train a fully-connected neural network based on Keras

Use stochastic processes to generate samples and use them to train a fully-connected neural network based on Keras which will then be used to generate residuals

Federico Lopez 2 Jan 14, 2022
Open standard for machine learning interoperability

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides

Open Neural Network Exchange 13.9k Dec 30, 2022