2020-7-20 20:19
official website class torch.nn. GroupNorm ( num_groups: int , num_channels: int , eps: float = 1e-05 , affine: bool = True ) ...
个人分类: DeepLearning|2470 次阅读|没有评论
2020-5-18 16:04
Depth (d) : Scaling network depth is the most common way used by many ConvN. The intuition is that deeper ConvNet can capture richer and more complex features, and generalize well on new tasks . However, deeper networks are also more difficult to train due to the vanishing gradient problem ...
个人分类: DeepLearning|1096 次阅读|没有评论
feature fusion network
2020-4-18 10:54
feature pyramid network Lin, Tsung-Yi, et al. Feature pyramid networks for object detection. Proceedings of the IEEE conference on computer vision and pattern recognition . 2017. (FPN) Chao, Hanqing, et al. Gaitset: Regarding gait as a set for cross-view ga ...
个人分类: DeepLearning|834 次阅读|没有评论
[转载]several blocks of Deep learning
2019-8-22 16:32
Deep learning is like a black box. Its learning process takes the inputs and the desired outputs, and then updates its internal states, so that the calculated outputs get as close as possible from the desired output. So machine learning sometimes is called model fitting. Decompose the learning pro ...
个人分类: DeepLearning|1318 次阅读|没有评论
2019-7-26 12:18
标准差的定义: 其中, 为平均值。同时,有如下变形: 因此,标准差简化为: 故有: From:
个人分类: DeepLearning|1485 次阅读|没有评论
Pycharm professional安装及激活
热度 1 2019-7-19 20:21
1、下载并安装Pycharm professional 1)官网: 若需要对远程解释器与调试器进行设置,必须下载并安装Pycharm professional版本。若仅在本地使用,即可安装Community版本。   ...
个人分类: DeepLearning|13523 次阅读|2 个评论 热度 1
Pytorch bugs
2019-7-19 19:05
when running at the code of self.criterion(outputs, labels), where I use CrossEntropy as my loss function, I meet the bug of D imension out of range (expected to be in range of , but got 1) Solution: From the doc of CrossEntropy ( ...
个人分类: DeepLearning|1631 次阅读|没有评论
2019-7-7 13:30
在windows或者Ubuntu上安装Pytorch 理论参考资料 1) Stanford U. CS231课程 (中文资料) (英文网站) 2) Coursera上Andrew N.g的《Deep Learning》课程 ...
个人分类: DeepLearning|1077 次阅读|没有评论

本页有 2 篇博文因作者的隐私设置或未通过审核而隐藏

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2022-1-29 10:42

Powered by

Copyright © 2007- 中国科学报社