![](https://img-blog.csdnimg.cn/20201014180756930.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
深度学习
H速写不读书H
这个作者很懒,什么都没留下…
展开
-
YOLOv4: Optimal Speed and Accuracy of Object Detection-论文阅读(2)
YOLOv4: Optimal Speed and Accuracy of Object DetectionAbstract1. Introduction2. Related work3. Methodology4. Experiments5. Results6. Conclusions7. Acknowledgements今天,yolo的共同开发者,带来了全新的目标检测算法YOLOv4!!!,...原创 2020-04-24 17:25:11 · 1863 阅读 · 0 评论 -
EfficientDet: Scalable and Efficient Object Detection---论文阅读(1)
Google最新的目标检测方法,目前应该是最快最好的深度学习目标检测器,优于YOLOv3、Mask R-cnn,能实现高帧率,低FLOPS运算。本文对该论文整体进行大致的整理。AbstractBiFPNEfficientDet实验结果对比实验 Ablation Study总结论文链接:arXiv:1911.09070v4官方源代码地址:https://github.com/google/aut...原创 2020-04-16 15:25:19 · 804 阅读 · 0 评论 -
解决ubuntu系统下使用anaconda升级慢、安装软件如scipy,conda install ***很慢,Solving environment: failed,CondaHTTPError问题
解决ubuntu系统下使用anaconda升级慢,安装软件如scipy、numpy,conda install ***很慢,Collecting package metadata (current_repodata.json): done Solving environment: failed,Solving environment: failed with initial frozen solv...原创 2020-04-13 22:27:20 · 6193 阅读 · 3 评论 -
torch.squeeze()、torch.unsqueeze()、torch.randn()、torch.nn.Linear()、torch.Tensor.expand_as
torch.squeeze()、torch.unsqueeze()、torch.randn()、torch.nn.Linear()1、torch.squeeze()torch.squeeze(input, dim=None, out=None)input (Tensor) ,input为输入的tensordim (int, optional) ,dimension,只对输入tensor的...原创 2020-04-10 20:58:57 · 953 阅读 · 0 评论