Convnext-tf - Unofficial tensorflow keras implementation of ConvNeXt

Last update: Oct 06, 2022

Related tags

Overview

ConvNeXt Tensorflow

This is unofficial tensorflow keras implementation of ConvNeXt.
Its based on official PyTorch implementation.

Pre-trained Models

name	resolution	pretrain	[email protected]	#params	FLOPs	model
`convnext_tiny_224`	224x224	ImageNet-1K	82.1	28M	4.5G	github
`convnext_small_224`	224x224	ImageNet-1K	83.1	50M	8.7G	github
`convnext_base_224`	224x224	ImageNet-21K-1K	85.8	89M	15.4G	github
`convnext_base_384`	384x384	ImageNet-21K-1K	86.8	89M	45.0G	github
`convnext_large_224`	224x224	ImageNet-21K-1K	86.6	198M	34.4G	github
`convnext_large_384`	384x384	ImageNet-21K-1K	87.5	198M	101.0G	github
`convnext_xlarge_224`	224x224	ImageNet-21K-1K	87.0	350M	60.9G	github
`convnext_xlarge_384`	384x384	ImageNet-21K-1K	87.8	350M	179.0G	github

Note

I've ported only ImageNet-21K-1K weights for base, large and xlarge models.
If you want to convert another pretrained weight in official repo, you can refer to this script or just let me know.

Examples

import tensorflow as tf
from models.convnext_tf import create_model

x = tf.zeros((1, 224, 224, 3), dtype=tf.float32)

model = create_model('convnext_tiny_224', input_shape=(224, 224), pretrained=True)
out = model(x) # (1, 1000)

model = create_model('convnext_tiny_224', input_shape=(224, 224), num_classes=1, pretrained=True)
out = model(x) # (1, 1)

model = create_model('convnext_tiny_224', input_shape=(224, 224), include_top=False, pretrained=True)
out = model(x) # (1, 16, 16, 768)

Reference

https://github.com/facebookresearch/ConvNeXt
https://github.com/rishigami/Swin-Transformer-TF

You might also like...

Unofficial Tensorflow 2 implementation of the paper Implicit Neural Representations with Periodic Activation Functions

Siren: Implicit Neural Representations with Periodic Activation Functions The unofficial Tensorflow 2 implementation of the paper Implicit Neural Repr

2 Jun 27, 2022

Implementation of ConvMixer in TensorFlow and Keras

ConvMixer ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in that it operates directly on

8 Oct 3, 2022

Implementation of ConvMixer-Patches Are All You Need? in TensorFlow and Keras

Patches Are All You Need? - ConvMixer ConvMixer, an extremely simple model that is similar in spirit to the ViT and the even-more-basic MLP-Mixer in t

8 Oct 3, 2022

A Keras implementation of YOLOv4 (Tensorflow backend)

keras-yolo4 请使用更完善的版本: https://github.com/miemie2013/Keras-YOLOv4 Please visit here for more complete model: https://github.com/miemie2013/Keras-YOLOv

384 Nov 29, 2022

A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon.

PokeGAN A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon. Dataset The model has been trained on dataset that includes 8

19 Jul 26, 2022

Human head pose estimation using Keras over TensorFlow.

RealHePoNet: a robust single-stage ConvNet for head pose estimation in the wild.

71 Jan 5, 2023

Graph Neural Networks with Keras and Tensorflow 2.

Welcome to Spektral Spektral is a Python library for graph deep learning, based on the Keras API and TensorFlow 2. The main goal of this project is to

2.2k Jan 8, 2023

QKeras: a quantization deep learning library for Tensorflow Keras

QKeras github.com/google/qkeras QKeras 0.8 highlights: Automatic quantization using QKeras; Stochastic behavior (including stochastic rouding) is disa

437 Jan 3, 2023

Hyperparameter Optimization for TensorFlow, Keras and PyTorch

Hyperparameter Optimization for Keras Talos • Key Features • Examples • Install • Support • Docs • Issues • License • Download Talos radically changes

1.6k Dec 15, 2022

Comments

Low accuracy on ImageNet1K validation

I'm using your TF-converted model (tiny) and testing on ImageNet 1K validation images, but I'm getting 78% accuracy instead of the officially published 82%.

Do you think that a 4 percent drop could be because of Torch/Tensorflow difference? Another converted model (https://github.com/sayakpaul/ConvNeXt-TF) attains 81% and the only difference between you and sayakpaul is the implementation of depthwise convolution. Have you tested your model on validation and if so, can you share the steps so that I could figure out the problem?

opened by app2scale 2

Releases(v0.1)

v0.1(Jan 12, 2022)

Source code(tar.gz)
Source code(zip)
convnext_base_22k_1k_224.h5(338.30 MB)
convnext_base_22k_1k_384.h5(338.31 MB)
convnext_large_22k_1k_224.h5(754.79 MB)
convnext_large_22k_1k_384.h5(754.78 MB)
convnext_small_1k_224_ema.h5(191.98 MB)
convnext_tiny_1k_224_ema.h5(109.27 MB)
convnext_xlarge_22k_1k_224_ema.h5(1336.26 MB)
convnext_xlarge_22k_1k_384_ema.h5(1336.26 MB)

Owner

GitHub Repository

An unofficial personal implementation of UM-Adapt, specifically to tackle joint estimation of panoptic segmentation and depth prediction for autonomous driving datasets.

Semisupervised Multitask Learning This repository is an unofficial and slightly modified implementation of UM-Adapt[1] using PyTorch. This code primar

11 Nov 25, 2022

[NeurIPS-2020] Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID.

Self-paced Contrastive Learning (SpCL) The official repository for Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID

286 Dec 21, 2022

Adaptation through prediction: multisensory active inference torque control

Adaptation through prediction: multisensory active inference torque control Submitted to IEEE Transactions on Cognitive and Developmental Systems Abst

1 Nov 07, 2022

NR-GAN: Noise Robust Generative Adversarial Networks

Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter Code and checkpoints for the ACL2021 paper "Lexicon Enhanced Chinese Sequence Labelling

59 Dec 11, 2022

Disturbing Target Values for Neural Network regularization: attacking the loss layer to prevent overfitting

Disturbing Target Values for Neural Network regularization: attacking the loss layer to prevent overfitting 1. Classification Task PyTorch implementat

0 Apr 24, 2022

Automatic voice-synthetised summaries of latest research papers on arXiv

PaperWhisperer PaperWhisperer is a Python application that keeps you up-to-date with research papers. How? It retrieves the latest articles from arXiv

124 Dec 20, 2022

Object Detection Projekt in GKI WS2021/22

tfObjectDetection Object Detection Projekt with tensorflow in GKI WS2021/22 Docker Container: docker run -it --name --gpus all -v path/to/project:p

1 Jul 18, 2022

Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.

TS-CAM: Token Semantic Coupled Attention Map for Weakly SupervisedObject Localization This is the official implementaion of paper TS-CAM: Token Semant

112 Jan 02, 2023

[CVPR2022] Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos Created by Muheng Li, Lei Chen, Yueqi Duan, Zhilan Hu, Jianjiang Feng, Jie

58 Dec 23, 2022

Utility tools for the "Divide and Remaster" dataset, introduced as part of the Cocktail Fork problem paper

Divide and Remaster Utility Tools Utility tools for the "Divide and Remaster" dataset, introduced as part of the Cocktail Fork problem paper The DnR d

46 Dec 11, 2022

This repository contains the code used for the implementation of the paper "Probabilistic Regression with HuberDistributions"

Public_prob_regression_with_huber_distributions This repository contains the code used for the implementation of the paper "Probabilistic Regression w

1 Dec 04, 2021