pytorch-crnn实践以及内置ctc_loss使用小结 最近开始深入OCR这块, 以前倒是训练过开源的Keras-CRNN, 但是它和原文还是不一样, 今天参照Keras-CRNN代码和CRNN论文用pytorch实现CRNN, 由于没有GPU, 自己造了100多张只包含数字的小图片来训练模型, 验证模型能否收敛CRNN流程在这儿不再详细谈CRNN论文了, 主要按照原文做一个流程描述:输入图片要求高度为32, 使用VGG提取特征，高度32倍下采...
YOLOv4: Optimal Speed and Accuracy of Object Detection论文解读 最近目标检测又出了yolo-v4，作为一个做目标检测的不可不膜拜膜拜。首先由于约瑟夫大神已经退出CV，yolo-v4 的一作是DarkNet的维护者，但还是加入了DarkNet官方。个人觉得这篇文章的对我的最大意义在于对现有的目标检测算法的结构以及各种训练trick作了对比，读完之后又加深了对该领域的一些理解。总之，论文结合各种最新trick来改进yolo-v3，效果还是很强的. 我的个人博客贡...
Anchor free 目标检测修炼之路: DenseBox : Unifying Landmark Localization with End to End Object Detection Anchor free 目标检测修炼之路: DenseBox : Unifying Landmark Localization with End to End Object Detection
目标检测之RFB模块: Receptive Field Block Net for Accurate and Fast Object Detection 目标检测之RFB模块: Receptive Field Block Net for Accurate and Fast Object Detection
Facenet: A Unified Embedding for Face Recognition and Clustering 总结 Facenet: A Unified Embedding for Face Recognition and Clustering总结
人脸检测网络: SSH: Single Stage Headless Face Detector总结 人脸检测网络: SSH: Single Stage Headless Face Detector总结
图像修复3: Free-Form Image Inpainting with Gated Convolution 图像修复3: Free-Form Image Inpainting with Gated Convolution总结
图像修复2: Generative Image Inpainting with Contextual Attention总结与应用 Generative Image Inpainting with Contextual Attention总结与应用
图像修复1: Image Inpainting for Irregular Holes Using Partial Convolutions Image Inpainting for Irregular Holes Using Partial Convolutions论文总结
Accelerating Object Detection by Erasing Background Activations 阅读 Accelerating Object Detection by Erasing Background Activations 阅读
关注
