PyTorch1.9发布了！torchvision支持SSD模型！
共 1832字，需浏览 4分钟
·
2021-06-24 11:24
点蓝色字关注“机器学习算法工程师”
设为星标，干货直达！
近日，PyTorch1.9发布了，主要更新如下：
Major improvements to support scientific computing, including torch.linalg, torch.special, and Complex Autograd
Major improvements in on-device binary size with Mobile Interpreter
Native support for elastic-fault tolerance training through the upstreaming of TorchElastic into PyTorch Core
Major updates to the PyTorch RPC framework to support large scale distributed training with GPU support
New APIs to optimize performance and packaging for model inference deployment
Support for Distributed training, GPU utilization and SM efficiency in the PyTorch Profiler
另外torchvision更新至0.10版本，新增SSD模型：
import torch
import torchvision
# Original SSD variant
x = [torch.rand(3, 300, 300), torch.rand(3, 500, 400)]
m_detector = torchvision.models.detection.ssd300_vgg16(pretrained=True)
m_detector.eval()
predictions = m_detector(x)
# Mobile-friendly SSDlite variant
x = [torch.rand(3, 320, 320), torch.rand(3, 500, 400)]
m_detector = torchvision.models.detection.ssdlite320_mobilenet_v3_large(pretrained=True)
m_detector.eval()
predictions = m_detector(x)
更多详情访问：https://pytorch.org/blog/pytorch-1.9-released/
推荐阅读
谷歌AI用30亿数据训练了一个20亿参数Vision Transformer模型，在ImageNet上达到新的SOTA！
"未来"的经典之作ViT：transformer is all you need！
PVT：可用于密集任务backbone的金字塔视觉transformer！
涨点神器FixRes：两次超越ImageNet数据集上的SOTA
不妨试试MoCo，来替换ImageNet上pretrain模型！
机器学习算法工程师
一个用心的公众号
