PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

Last update: Jan 07, 2023

Overview

pytorch-fcn

PyTorch implementation of Fully Convolutional Networks.

Requirements

pytorch >= 0.2.0
torchvision >= 0.1.8
fcn >= 6.1.5
Pillow
scipy
tqdm

Installation

git clone https://github.com/wkentaro/pytorch-fcn.git
cd pytorch-fcn
pip install .

# or

pip install torchfcn

Training

See VOC example.

Accuracy

At 10fdec9.

Model	Implementation	epoch	iteration	Mean IU	Pretrained Model
FCN32s	Original	-	-	63.63	Download
FCN32s	Ours	11	96000	62.84
FCN16s	Original	-	-	65.01	Download
FCN16s	Ours	11	96000	64.91
FCN8s	Original	-	-	65.51	Download
FCN8s	Ours	7	60000	65.49
FCN8sAtOnce	Original	-	-	65.40
FCN8sAtOnce	Ours	11	96000	64.74

Visualization of validation result of FCN8s.

Cite This Project

If you use this project in your research or wish to refer to the baseline results published in the README, please use the following BibTeX entry.

@misc{pytorch-fcn2017,
  author =       {Ketaro Wada},
  title =        {{pytorch-fcn: PyTorch Implementation of Fully Convolutional Networks}},
  howpublished = {\url{https://github.com/wkentaro/pytorch-fcn}},
  year =         {2017}
}

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

Related tags

Overview

pytorch-fcn

Requirements

Installation

Training

Accuracy

Cite This Project

Owner

Kentaro Wada

Official PyTorch Implementation of SSMix (Findings of ACL 2021)

This repository collects 100 papers related to negative sampling methods.

SpinalNet: Deep Neural Network with Gradual Input

Using modified BiSeNet for face parsing in PyTorch

[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer

Unicorn can be used for performance analyses of highly configurable systems with causal reasoning

Graph Analysis From Scratch

Official implementation of "Watermarking Images in Self-Supervised Latent-Spaces"

Code Release for ICCV 2021 (oral), "AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds"

This is the unofficial code of Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes. which achieve state-of-the-art trade-off between accuracy and speed on cityscapes and camvid, without using inference acceleration and extra data

Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.

Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation

Modeling CNN layers activity with Gaussian mixture model

CATE: Computation-aware Neural Architecture Encoding with Transformers

Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data

fklearn: Functional Machine Learning

Code and training data for our ECCV 2016 paper on Unsupervised Learning

an implementation of Video Frame Interpolation via Adaptive Separable Convolution using PyTorch

Effect of Deep Transfer and Multi task Learning on Sperm Abnormality Detection

HandFoldingNet ✌️ : A 3D Hand Pose Estimation Network Using Multiscale-Feature Guided Folding of a 2D Hand Skeleton