搜索资源列表
visulize
- caffe-window matlab 接口训练mnist后权重、特征可视化(Caffe-window Matlab interface training MNIST.M file, MATLAB platform training MNIST model)
faster_rcnn
- windows下faster_RCNN 方法用训练好的model进行目标检测的测试工程(under OS Windows , use the faster_RCNN method with a trained model for the target test of the test project)
MTCNN_face_detection_alignment-master
- 人脸检测 matlab+caffe+cuda(face detection: matlab+caffe+cuda)
binaryproto2npy
- 将二进制形式的图片均值文件转换成python形式的一个工具(# "source" is the binary file converted by the command shell # "des" is the binary file with python format converted from "source")
re
- 可用于 caffe环境，适于初学者,包括了五个类别，每个类别100张图片 ，有公交 恐龙 鲜花 马 大象。(it can be used in caffe environment. suitable for new learner)
network
- 深度学习网络收集，每年Imagenet获奖网络(A deep learning network is collected annually at Imagenet award-winning network)
resnet
- 深度残差网络ResNet，分别有50,101,152,200层(The depth residual network ResNet, respectively, has 50101152200 layers)
YOLO-master
- yolo算法的caffe实现，在darknet框架下，基于UNIX平台(Yolo algorithm Caffe implementation, in the Darknet framework, based on the UNIX platform)
SRCNN
- 高分辨率重建图像，通过训练后输入的图像重建质量高，基于Caffe开发(High resolution reconstructed image)
20160909013603523 (1)
- 清晰、高效的深度学习框架，它是开源的，核心语言是C++，它支持命令行、Python和Matlab接口，它既可以在CPU上运行也可以在GPU上运行(Clear and efficient depth learning framework, which is open source, the core language is c + + support command line, python, and MATLAB interface, which can run on the CPU and r
train_resnet18_r2
- caffe C3D-v1.1 resnet18 更改(caffe C3D-v1.1 train_val prototxt which is changed from resnet18)
FaceTools-master
- 本次作业使用的是汤晓鸥团队的DeepID第一代的网络，通过Caffe训练模型参数，经过LFW二分类得到人脸识别准确率。(This job is used by the Tang Xiaoou team's DeepID first generation network. Through the Caffe training model parameters, the accuracy of face recognition is obtained through the LFW two clas
caffe
- 卷积神经网络的一种开源代码，可以对图像数据库自动提取特征(An open source code of the convolution neural network that automatically extracts features of an image database. (one open source code of CNN which can extract features other image dataset.))
图片文字识别crnn-master
- 由于是别人的代码，这个图片文字识别是和我上传过的文字定位模块一起组成的caffe深度学习框架做的一个图像文字识别，这个模块没怎么看懂，都是一些lua脚本。(Because it is someone else's code, the image character recognition is with words that I uploaded positioning module of caffe deep learning framework for an image of charact
caffe-cvprw15-master
- 基于深度学习框架构建用于快速图像检索的二值哈希编码(Construction of binary hash codes for fast image retrieval based on depth learning framework)
lisa-caffe-public-lstm_video_deploy
- 深度学习，循环神经网络LSTM，常用于语音识别，翻译，预测等(Deep learning, recurrent neural network LSTM)
深度学习 21天实战Caffe 547458
- 深度学习资料,深度学习实战21天的PDF版本(Some datasheet about the deep learning and this can be very efficient.)
CNN
- 使用cnn提取图像特征，然后用SVM分类，此处没有给出训练集，另外imagenet-caffe-alex部分代码需要注意，需要下载的话把注释掉的代码打开(Using CNN image feature extraction, and then use the SVM classification, there were no given training set, also need to pay attention to imagenet-caffe-alex part of the code
unet
- 为图像分割任务中Unet网络结构，可以自行根据需求进行修改(this is the network of Unet)
caffe-cvpr
- 显着区域检测是计算机视觉中长期存在的问题。它旨在找到最能吸引人眼睛注意的图像中的像素或区域。准确和可靠的显着性检测可以从视觉追踪和识别到图形图像处理等众多任务中受益。例如，成功的对象检测算法有助于自动图像分割，更可靠的对象检测，有效的图像缩略和重定位(Significant regional detection is a long-term problem in computer vision. It aims to find the pixels or regions of the most