liujiao111 / deep-learning
my own deep learing project
☆22Updated last year
Related projects ⓘ
Alternatives and complementary repositories for deep-learning
- 一个通用的图像分类模板,天池/CVPR AliProducts挑战赛 3/688☆82Updated 3 years ago
- 使用YOLOv3识别四个类别:红灯、绿灯、行人及行人头部☆14Updated 5 years ago
- Pytorch实践简单, 方便, 快速训练 图像分类模型☆34Updated 3 years ago
- Examples and tools for deep learning deployment☆55Updated 3 years ago
- 2019CCF BDCI-多人种人脸识别☆53Updated 4 years ago
- 【目标识别】yolo3_keras旗帜识别&&训练自己数据☆49Updated 3 years ago
- 定位综述 目前用于人脸定位的有两种主流方法,一种是基于级联形状回归模型,另一种就是基于深度学习的方法。级联形状回归方法就是使用回归模型,直接学习从人脸表征到人脸形状的映射函数,进而建立从表观到形状的对应关系。这种方法的学习依赖于训练集的选取,如果训练集中包含了复杂的姿态变化…☆97Updated 5 years ago
- 对于小目标的检测和识别☆26Updated 5 years ago
- FCN implement with densenet for VOC dataset☆24Updated 4 years ago
- 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☆26Updated 3 years ago
- CCF BDCI2019 多人种人脸识别 Baseline Pubilic LB 0.64+ (PyTorch)☆83Updated 5 years ago
- 使用LBP方法提取特征,再使用svm进行分类☆40Updated 7 years ago
- RetinaNet with backbone se_resnext50_32x4d, se_resnext101_32x4d☆24Updated 5 years ago
- 2 classes of lightweight object detection. train on VOC 、SAR☆26Updated 5 years ago
- 计算机视觉方面的分类、对象检测、图像分割、人脸检测、OCR等中文翻译☆108Updated 3 years ago
- 天气分类比赛☆21Updated 4 years ago
- TianChi 2018广东工业智造大数据创新大赛——智能算法赛(复赛baseline代码)☆18Updated 6 years ago
- yolo3 + densenet ocr☆36Updated 4 years ago
- flyai的场景分类比赛☆15Updated 5 years ago
- 第五届百度西安交大大数据竞赛 城市区域功能分类 Baseline☆91Updated 2 years ago
- Based on Learning-rich-features-for-image-manipulation-detection☆42Updated 4 years ago
- 该脚本根据语料文件生成对应的图像文件,适用于文本识别等CV任务☆29Updated 3 years ago
- MORAN: A Multi-Object Rectified Attention Network for Scene Text Recognition☆56Updated 5 years ago
- you can use dbnet to detect word or bar code,Knowledge Distillation is provided,also python tensorrt inference is provided.☆43Updated 3 years ago
- Some basic neural network implement by tf2.0☆25Updated 2 years ago
- ICPR MTWI 2018 挑战赛一☆11Updated 5 years ago
- 天池比赛,kaggle等等(Keras/PyTorch实战)☆180Updated 4 years ago
- 无监督正样本训练 检测缺陷并分割图像☆22Updated 3 years ago
- 使用CNN全卷积神经网络进行整行汉字识别,正确率90-94%,后来有朋友改成densenet做主网络,做到99%以上正确率☆30Updated 4 years ago