DenseNet-Keras with ImageNet Pretrained Models

This is an Keras implementation of DenseNet with ImageNet pretrained weights. The weights are converted from Caffe Models. The implementation supports both Theano and TensorFlow backends.

To know more about how DenseNet works, please refer to the original paper

Densely Connected Convolutional Networks
Gao Huang, Zhuang Liu, Kilian Q. Weinberger, Laurens van der Maaten
arXiv:1608.06993

Pretrained DenseNet Models on ImageNet

The top-1/5 accuracy rates by using single center crop (crop size: 224x224, image size: 256xN)

Network	Top-1	Top-5	Theano	Tensorflow
DenseNet 121 (k=32)	74.91	92.19	model (32 MB)	model (32 MB)
DenseNet 169 (k=32)	76.09	93.14	model (56 MB)	model (56 MB)
DenseNet 161 (k=48)	77.64	93.79	model (112 MB)	model (112 MB)

Usage

First, download the above pretrained weights to the imagenet_models folder.

Run test_inference.py for an example of how to use the pretrained model to make inference.

python test_inference.py

Fine-tuning

Check this out to see example of fine-tuning DenseNet with your own dataset.

Requirements

Keras ~~1.2.2~~ 2.0.5
Theano 0.8.2 or TensorFlow ~~0.12.0~~ 1.2.1

Updates

Keras 2.0.5 and TensorFlow 1.2.1 are supported

DenseNet Implementation in Keras with ImageNet Pretrained Models

Related tags

Overview

DenseNet-Keras with ImageNet Pretrained Models

Pretrained DenseNet Models on ImageNet

Usage

Fine-tuning

Requirements

Updates

Owner

Felix Yu

OrienMask: Real-time Instance Segmentation with Discriminative Orientation Maps

EMNLP 2021 paper Models and Datasets for Cross-Lingual Summarisation.

Baseline inference Algorithm for the STOIC2021 challenge.

PyTorch implementation of Memory-based semantic segmentation for off-road unstructured natural environments.

Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth

Official Implementation of "Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras"

Pytorch Implementation of Adversarial Deep Network Embedding for Cross-Network Node Classification

GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles using deep neural networks.

PyTorch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

A novel pipeline framework for multi-hop complex KGQA task. About the paper title: Improving Multi-hop Embedded Knowledge Graph Question Answering by Introducing Relational Chain Reasoning

Unsupervised clustering of high content screen samples

PoolFormer: MetaFormer is Actually What You Need for Vision

Constructing Neural Network-Based Models for Simulating Dynamical Systems

K-FACE Analysis Project on Pytorch

SimplEx - Explaining Latent Representations with a Corpus of Examples

Fast methods to work with hydro- and topography data in pure Python.

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

A general framework for inferring CNNs efficiently. Reduce the inference latency of MobileNet-V3 by 1.3x on an iPhone XS Max without sacrificing accuracy.

This is the code for the paper "Jinkai Zheng, Xinchen Liu, Wu Liu, Lingxiao He, Chenggang Yan, Tao Mei: Gait Recognition in the Wild with Dense 3D Representations and A Benchmark. (CVPR 2022)"

An efficient framework for reinforcement learning.