A PaddlePaddle version image model zoo.

Last update: Dec 07, 2022

Overview

Paddle-Image-Models

English | 简体中文

A PaddlePaddle version image model zoo.

Install Package

Install by pip：
```
$ pip install ppim
```
Install by wheel package：【Releases Packages】

Usage

Quick Start

import paddle
from ppim import rednet_26

# Load the model
model, val_transforms = rednet_26(pretrained=True)

# Model summary 
paddle.summary(model, input_size=(1, 3, 224, 224))

# Random a input
x = paddle.randn(shape=(1, 3, 224, 224))

# Model forword
out = model(x)

Finetune

import paddle
import paddle.nn as nn
import paddle.vision.transforms as T
from paddle.vision import Cifar100

from ppim import rexnet_1_0

# Load the model
model, val_transforms = rexnet_1_0(pretrained=True, class_dim=100)

# Use the PaddleHapi Model
model = paddle.Model(model)

# Set the optimizer
opt = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())

# Set the loss function
loss = nn.CrossEntropyLoss()

# Set the evaluate metric
metric = paddle.metric.Accuracy(topk=(1, 5))

# Prepare the model 
model.prepare(optimizer=opt, loss=loss, metrics=metric)

# Set the data preprocess
train_transforms = T.Compose([
    T.Resize(256, interpolation='bicubic'),
    T.RandomCrop(224),
    T.ToTensor(),
    T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])

# Load the Cifar100 dataset
train_dataset = Cifar100(mode='train', transform=train_transforms, backend='pil')
val_dataset = Cifar100(mode='test',  transform=val_transforms, backend='pil')

# Finetune the model 
model.fit(
    train_data=train_dataset, 
    eval_data=val_dataset, 
    batch_size=256, 
    epochs=2, 
    eval_freq=1, 
    log_freq=1, 
    save_dir='save_models', 
    save_freq=1, 
    verbose=1, 
    drop_last=False, 
    shuffle=True,
    num_workers=0
)

Model Zoo

You might also like...

Object detection and instance segmentation toolkit based on PaddlePaddle.

9.3k Jan 2, 2023

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Paddle-Adversarial-Toolbox Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle. Model Zoo Common FGS

17 Nov 8, 2022

Plaything for Autistic Children (demo for PaddlePaddle/Wechaty/Mixlab project)

星星的孩子 - 一款为孤独症孩子设计的聊天机器人游戏孤独症儿童是目前常常被忽视的一类群体。他们有着类似性格内向的特征，实际却受着广泛性发育障碍的折磨。项目背景这类儿童在与人交往时存在着沟通障碍，其特点表现在：社交交流差，互动障碍明显认知能力有限，被动认知兴趣狭窄，重复刻板，缺乏变化和想象

35 Nov 24, 2022

Official PaddlePaddle implementation of Paint Transformer

Paint Transformer: Feed Forward Neural Painting with Stroke Prediction [Paper] [Paddle Implementation] Update We have optimized the serial inference p

284 Dec 31, 2022

An implementation of paper `Real-time Convolutional Neural Networks for Emotion and Gender Classification` with PaddlePaddle.

简介通过PaddlePaddle框架复现了论文 Real-time Convolutional Neural Networks for Emotion and Gender Classification 中提出的两个模型，分别是SimpleCNN和MiniXception。利用 imdb_crop

8 Mar 11, 2022

PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

PaddlePaddle Vision Transformers State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 🤖 PaddlePaddle Visual Transformers (PaddleViT or

1k Dec 28, 2022

Remote sensing change detection tool based on PaddlePaddle

PdRSCD PdRSCD（PaddlePaddle Remote Sensing Change Detection）是一个基于飞桨PaddlePaddle的遥感变化检测的项目，pypi包名为ppcd。目前0.2版本，最新支持图像列表输入的训练和预测，如多期影像、多源影像甚至多期多源影像。可以快速完

38 Aug 31, 2022

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

Knover Knover is a toolkit for knowledge grounded dialogue generation based on PaddlePaddle. Knover allows researchers and developers to carry out eff

607 Dec 31, 2022

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

face.evoLVe: High-Performance Face Recognition Library based on PaddlePaddle & PyTorch Evolve to be more comprehensive, effective and efficient for fa

3.1k Jan 2, 2023

Comments

无法引入ppim

AttributeError Traceback (most recent call last) in 1 import paddle ----> 2 from ppim import rednet_26 3 4 # 使用 PPIM whl 包加载模型 5 model, val_transforms = rednet_26(pretrained=True, return_transforms=True)

~.conda\envs\paddle\lib\site-packages\ppim_init_.py in ----> 1 import ppim.models as models 2 3 from ppim.models import * 4 from inspect import isfunction, isclass 5

~.conda\envs\paddle\lib\site-packages\ppim\models_init_.py in 3 from ppim.models.tnt import tnt_s, TNT 4 from ppim.models.t2t import t2t_vit_7, t2t_vit_10, t2t_vit_12, t2t_vit_14, t2t_vit_19, t2t_vit_24, t2t_vit_t_14, t2t_vit_t_19, t2t_vit_t_24, t2t_vit_14_384, t2t_vit_24_token_labeling ----> 5 from ppim.models.pvt import pvt_ti, pvt_s, pvt_m, pvt_l, PyramidVisionTransformer 6 from ppim.models.pit import pit_ti, pit_s, pit_xs, pit_b, pit_ti_distilled, pit_s_distilled, pit_xs_distilled, pit_b_distilled, PoolingTransformer, DistilledPoolingTransformer 7 from ppim.models.coat import coat_ti, coat_m, coat_lite_ti, coat_lite_m, CoaT

~.conda\envs\paddle\lib\site-packages\ppim\models\pvt.py in 5 import paddle.vision.transforms as T 6 ----> 7 import ppim.models.vit as vit 8 9 from ppim.models.common import add_parameter, load_model

AttributeError: module 'ppim' has no attribute 'models'

opened by hanknewbird 0

Releases(1.1.0)

1.1.0(Jun 13, 2021)

Add some models.
Source code(tar.gz)
Source code(zip)
ppim-1.1.0-py3-none-any.whl(64.89 KB)
1.0.7(Apr 12, 2021)

Add CondenseNet V2 model. DLA、TNT、HarDNet models will be released soon.
Source code(tar.gz)
Source code(zip)
ppim-1.0.7-py3-none-any.whl(34.48 KB)
1.0.6(Apr 10, 2021)

Add PVT model. DLA、TNT、HarDNet models will be released soon.
Source code(tar.gz)
Source code(zip)
ppim-1.0.6-py3-none-any.whl(23.06 KB)
1.0.5(Apr 1, 2021)

Add the PiT Model.
Source code(tar.gz)
Source code(zip)
ppim-1.0.5-py3-none-any.whl(20.03 KB)
1.0.4(Mar 31, 2021)

Source code(tar.gz)
Source code(zip)
ppim-1.0.4-py3-none-any.whl(17.29 KB)
1.0.3(Mar 31, 2021)

Source code(tar.gz)
Source code(zip)
ppim-1.0.3-py3-none-any.whl(17.17 KB)
1.0.1(Mar 30, 2021)
Add the RedNets using the Involution

Source code(tar.gz)
Source code(zip)
ppim-1.0.1-py3-none-any.whl(17.17 KB)
1.0.0(Mar 19, 2021)

Source code(tar.gz)
Source code(zip)
ppim-1.0.0-py3-none-any.whl(15.23 KB)

Owner

AgentMaker

Focus on deep learning tools

GitHub Repository

End-to-end beat and downbeat tracking in the time domain.

60 Dec 24, 2022

Improving Object Detection by Estimating Bounding Box Quality Accurately

Improving Object Detection by Estimating Bounding Box Quality Accurately Abstrac

2 Apr 14, 2022

Official repository of the paper 'Essentials for Class Incremental Learning'

Essentials for Class Incremental Learning Official repository of the paper 'Essentials for Class Incremental Learning' This Pytorch repository contain

33 Nov 27, 2022

Ensembling Off-the-shelf Models for GAN Training

Vision-aided GAN video (3m) | website | paper Can the collective knowledge from a large bank of pretrained vision models be leveraged to improve GAN t

345 Dec 28, 2022

MERLOT: Multimodal Neural Script Knowledge Models

merlot MERLOT: Multimodal Neural Script Knowledge Models MERLOT is a model for learning what we are calling "neural script knowledge" -- representatio

190 Dec 22, 2022

Alfred-Restore-Iterm-Arrangement - An Alfred workflow to restore iTerm2 window Arrangements

Alfred-Restore-Iterm-Arrangement This alfred workflow will list avaliable iTerm2

7 May 10, 2022

TSIT: A Simple and Versatile Framework for Image-to-Image Translation

TSIT: A Simple and Versatile Framework for Image-to-Image Translation This repository provides the official PyTorch implementation for the following p

255 Nov 23, 2022

Efficient Training of Audio Transformers with Patchout

PaSST: Efficient Training of Audio Transformers with Patchout This is the implementation for Efficient Training of Audio Transformers with Patchout Pa

165 Dec 26, 2022

Pytorch implementation of Depth-conditioned Dynamic Message Propagation forMonocular 3D Object Detection

DDMP-3D Pytorch implementation of Depth-conditioned Dynamic Message Propagation forMonocular 3D Object Detection, a paper on CVPR2021. Instroduction T

32 Nov 09, 2022

This code is for our paper "VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers"

ICCV Workshop 2021 VTGAN This code is for our paper "VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers"

25 Dec 08, 2022

This repository contains numerical implementation for the paper Intertemporal Pricing under Reference Effects: Integrating Reference Effects and Consumer Heterogeneity.

6 Nov 18, 2022

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

Adversrial Machine Learning Benchmarks This code belongs to the papers: Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness? Det

9 Nov 27, 2022

Semi-supervised Transfer Learning for Image Rain Removal. In CVPR 2019.

Semi-supervised Transfer Learning for Image Rain Removal This package contains the Python implementation of "Semi-supervised Transfer Learning for Ima

59 Dec 26, 2022

An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wheat Detection (2021).

Global-Wheat-Detection An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wh

11 Sep 25, 2022

A PaddlePaddle version image model zoo.

Related tags

Overview

Paddle-Image-Models

Install Package

Usage

Model Zoo

You might also like...

Object detection and instance segmentation toolkit based on PaddlePaddle.

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Plaything for Autistic Children (demo for PaddlePaddle/Wechaty/Mixlab project)

Official PaddlePaddle implementation of Paint Transformer

An implementation of paper `Real-time Convolutional Neural Networks for Emotion and Gender Classification` with PaddlePaddle.

PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+

Remote sensing change detection tool based on PaddlePaddle

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Comments

无法引入ppim

Releases(1.1.0)

1.1.0(Jun 13, 2021)

1.0.7(Apr 12, 2021)

1.0.6(Apr 10, 2021)

1.0.5(Apr 1, 2021)

1.0.4(Mar 31, 2021)

1.0.3(Mar 31, 2021)

1.0.1(Mar 30, 2021)

1.0.0(Mar 19, 2021)

Owner

AgentMaker

End-to-end beat and downbeat tracking in the time domain.

Improving Object Detection by Estimating Bounding Box Quality Accurately

Official repository of the paper 'Essentials for Class Incremental Learning'

Ensembling Off-the-shelf Models for GAN Training

MERLOT: Multimodal Neural Script Knowledge Models

Alfred-Restore-Iterm-Arrangement - An Alfred workflow to restore iTerm2 window Arrangements

TSIT: A Simple and Versatile Framework for Image-to-Image Translation

Efficient Training of Audio Transformers with Patchout

Pytorch implementation of Depth-conditioned Dynamic Message Propagation forMonocular 3D Object Detection

This code is for our paper "VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers"

This repository contains numerical implementation for the paper Intertemporal Pricing under Reference Effects: Integrating Reference Effects and Consumer Heterogeneity.

Is RobustBench/AutoAttack a suitable Benchmark for Adversarial Robustness?

Semi-supervised Transfer Learning for Image Rain Removal. In CVPR 2019.

An efficient PyTorch library for Global Wheat Detection using YOLOv5. The project is based on this Kaggle competition Global Wheat Detection (2021).

Table-Extractor 表格抽取

Hyperbolic Procrustes Analysis Using Riemannian Geometry

Database Reasoning Over Text project for ACL paper

Weakly Supervised Posture Mining with Reverse Cross-entropy for Fine-grained Classification

Code repository for our paper regarding the L3D dataset.

QueryDet: Cascaded Sparse Query for Accelerating High-Resolution SmallObject Detection