All Projects → zw76859420 → image-recognition

zw76859420 / image-recognition

Licence: GPL-3.0 license
采用深度学习方法进行刀具识别。

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to image-recognition

cifar-tensorflow
No description or website provided.
Stars: ✭ 18 (-5.26%)
Mutual labels:  image-classification, densenet
Awesome Computer Vision Models
A list of popular deep learning models related to classification, segmentation and detection problems
Stars: ✭ 278 (+1363.16%)
Mutual labels:  image-classification, densenet
Asr syllable
基于卷积神经网络的语音识别声学模型的研究
Stars: ✭ 127 (+568.42%)
Mutual labels:  attention, densenet
Sightseq
Computer vision tools for fairseq, containing PyTorch implementation of text recognition and object detection
Stars: ✭ 116 (+510.53%)
Mutual labels:  attention, densenet
Global Self Attention Network
A Pytorch implementation of Global Self-Attention Network, a fully-attention backbone for vision tasks
Stars: ✭ 64 (+236.84%)
Mutual labels:  image-classification, attention
Basic cnns tensorflow2
A tensorflow2 implementation of some basic CNNs(MobileNetV1/V2/V3, EfficientNet, ResNeXt, InceptionV4, InceptionResNetV1/V2, SENet, SqueezeNet, DenseNet, ShuffleNetV2, ResNet).
Stars: ✭ 374 (+1868.42%)
Mutual labels:  image-classification, densenet
pyro-vision
Computer vision library for wildfire detection
Stars: ✭ 33 (+73.68%)
Mutual labels:  image-classification, densenet
Skin Lesions Classification DCNNs
Transfer Learning with DCNNs (DenseNet, Inception V3, Inception-ResNet V2, VGG16) for skin lesions classification
Stars: ✭ 47 (+147.37%)
Mutual labels:  image-classification, densenet
Residual Attention Network
Residual Attention Network for Image Classification
Stars: ✭ 525 (+2663.16%)
Mutual labels:  image-classification, attention
Pytorch classification
利用pytorch实现图像分类的一个完整的代码,训练,预测,TTA,模型融合,模型部署,cnn提取特征,svm或者随机森林等进行分类,模型蒸馏,一个完整的代码
Stars: ✭ 395 (+1978.95%)
Mutual labels:  image-classification, densenet
Pytorch Cifar100
Practice on cifar100(ResNet, DenseNet, VGG, GoogleNet, InceptionV3, InceptionV4, Inception-ResNetv2, Xception, Resnet In Resnet, ResNext,ShuffleNet, ShuffleNetv2, MobileNet, MobileNetv2, SqueezeNet, NasNet, Residual Attention Network, SENet, WideResNet)
Stars: ✭ 2,423 (+12652.63%)
Mutual labels:  image-classification, densenet
awesome-computer-vision-models
A list of popular deep learning models related to classification, segmentation and detection problems
Stars: ✭ 419 (+2105.26%)
Mutual labels:  image-classification, densenet
deep-learning
Deep Learning Bootcamp
Stars: ✭ 60 (+215.79%)
Mutual labels:  image-classification
transformer
A PyTorch Implementation of "Attention Is All You Need"
Stars: ✭ 28 (+47.37%)
Mutual labels:  attention
LegoBrickClassification
Repository to identify Lego bricks automatically only using images
Stars: ✭ 57 (+200%)
Mutual labels:  image-classification
multi-task-learning
Multi-task learning smile detection, age and gender classification on GENKI4k, IMDB-Wiki dataset.
Stars: ✭ 154 (+710.53%)
Mutual labels:  image-classification
deeplearning-mpo
Replace FC2, LeNet-5, VGG, Resnet, Densenet's full-connected layers with MPO
Stars: ✭ 26 (+36.84%)
Mutual labels:  densenet
gnn-lspe
Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations), ICLR 2022
Stars: ✭ 165 (+768.42%)
Mutual labels:  attention
SimplePythonCNN
Only in native python & numpy with Keras interface
Stars: ✭ 31 (+63.16%)
Mutual labels:  image-classification
TNCR Dataset
Deep learning, Convolutional neural networks, Image processing, Document processing, Table detection, Page object detection, Table classification. https://www.sciencedirect.com/science/article/pii/S0925231221018142
Stars: ✭ 37 (+94.74%)
Mutual labels:  image-classification

内部包含太多东西,需要慢慢咀嚼。

1.算法
采用深度学习方法进行刀具识别;
2.项目来源
本项目基础是采用标准图像测试数据集MNIST以及江南大学项目数据集安检刀具数据集;
3.项目技术
本项目采用深度学习算法,融入比较新的深度学习技术:VGG、Resnet、Densenet、Data Augmentation、Attention等技术对算法进行优化;
4.项目运行
(1)本例中主要是对刀具进行识别,首先对数据进行预处理,可以观看 load_dataset 脚本,对数据进行处理;
(2)然后运行 knife_train 进行训练和测试;
(3)最后在测试集MNIST以及安检数据集的准确率均为1.0;
欢迎各位对此项目感兴趣的朋友批评指正!

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].