项目类型

项目类别

最新

热搜企业:

opencv C
Fork 0 关注 0

原始仓库地址:https://github.com/opencv/opencv.git

浏览量:1227 下载量:943 项目类别: 图像分类
almost 2 years前更新
Fork 0 关注 0

A fast tool to do image augmentation by CUDA on GPU(especially elastic deform), can be helpful to research on Medical Image.

原始仓库地址:https://github.com/qsyao/cuda_spatial_deform.git

浏览量:1964 下载量:805 项目类别: 图像分类
almost 2 years前更新
dindnf C
Fork 0 关注 0

原始仓库地址:https://github.com/weinformatics/dindnf.git

浏览量:1602 下载量:600 项目类别: 图像分类
almost 2 years前更新
Fork 0 关注 0

这个存储库包含了论文“Deep Residual Learning for Image Recognition”中描述的原始模型(ResNet-50、ResNet-101和ResNet-152)。这些模型分别在ILSVRC和COCO 2015竞赛中使用,分别在ImageNet分类、ImageNet检测、ImageNet定位、COCO检测、COCO分割中获得第一名。

原始仓库地址:https://github.com/KaimingHe/deep-residual-networks.git

浏览量:1976 下载量:260 项目类别: 图像分类
almost 2 years前更新
SIXray Python
Fork 0 关注 0

浏览量:331 下载量:2 项目类别: 图像分类
almost 2 years前更新

使用nvidia-dali实现的PyTorch的dataloaders,我们已经实现了CIFAR-10和ImageNet的dataloaders,未来还会添加更多。使用Intel(R) Xeon(R) Gold 6154 CPU 2个处理器,Tesla V100 GPU 1个处理器,所有数据集存储在内存磁盘中,我们可以用DALI极大地加快图像预处理。 # PyTorch DataLoaders with DALI PyTorch DataLoaders implemented with [nvidia-dali](https://docs.nvidia.com/deeplearning/sdk/dali-developer-guide/docs/index.html), we've implemented **CIFAR-10** and **ImageNet** dataloaders, more dataloaders will be added in the future. With 2 processors of Intel(R) Xeon(R) Gold 6154 CPU, 1 Tesla V100 GPU and all dataset in memory disk, we can **extremely** **accelerate image preprocessing** with DALI. | Iter Training Data Cost(bs=256) | CIFAR-10 | ImageNet | | :-----------------------------: | :------: | :------: | | DALI | 1.4s(2 processors) | 625s(8 processors) | | torchvision | 280.1s(2 processors) | 13400s(8 processors) | In CIFAR-10 training, we can reduce tranining time **from** **1 day to 1 hour** with our hardware setting. ## Requirements You only need to install nvidia-dali package and version should be >= 0.12, we've tested version 0.11 and it didn't work ```bash #for cuda9.0 pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/cuda/9.0 nvidia-dali #for cuda10.0 pip install --extra-index-url https://developer.download.nvidia.com/compute/redist/cuda/10.0 nvidia-dali ``` More details and documents can be found [here](https://docs.nvidia.com/deeplearning/sdk/dali-developer-guide/docs/index.html#) ## Usage You can use these dataloaders easily as the following example ```python from cifar10 import get_cifar_iter_dali train_loader = get_cifar_iter_dali(type='train', image_dir='/userhome/memory_data/cifar10', batch_size=256,num_threads=4) for i, data in enumerate(train_loader): images = data[0]["data"].cuda(non_blocking=True) labels = data[0]["label"].squeeze().long().cuda(non_blocking=True) ``` If you have large enough memory for storing dataset, we strongly recommend you to mount a memory disk and put the whole dataset in it to accelerate I/O, like this ```bash mount -t tmpfs -o size=20g tmpfs /userhome/memory_data ``` It's noteworthy that `20g` above is a ceiling but **not** occupying `20g` memory at the moment you mount the tmpfs, memories are occupied as you putting dataset in it. Compressed files should **not** be extracted before you've copied them into memory, otherwise it could be much slower.

浏览量:2177 下载量:289 项目类别: 图像分类
over 1 year前更新
opencv C
Fork 0 关注 0

原始仓库地址:https://github.com/opencv/opencv.git

浏览量:1413 下载量:891 项目类别: 图像分类
over 1 year前更新
Fork 0 关注 2

本仓库是关于OpenCV-Python图像处理教程(源码及素材)。

原始仓库地址:https://github.com/ex2tron/OpenCV-Python-Tutorial.git

浏览量:1595 下载量:398 项目类别: 图像分类
over 1 year前更新
opencv C
Fork 0 关注 0

**opencv**是关于计算机视觉的开源库。 - 主页:https://opencv.org - 说明文件:https://docs.opencv.org/master/ - 论坛问答:http://answers.opencv.org - 问题跟踪:https://github.com/opencv/opencv/issues

原始仓库地址:https://github.com/opencv/opencv.git

浏览量:2458 下载量:75 项目类别: 图像分类
over 1 year前更新
Fork 0 关注 0

**torchvision**包由流行的数据集、模型架构和常见的计算机视觉图像转换组成。

原始仓库地址:https://github.com/pytorch/vision.git

浏览量:2086 下载量:918 项目类别: 图像分类
over 1 year前更新

ihub@pcl.ac.cn 鹏城实验室人工智能研究中心

版权所有:鹏城实验室    粤ICP备18066427号-6    Powerd by 国防科技大学Trustie