u010454261的博客

3篇检测方法的文章中均包含高斯衰减相关的内容，记录一下，有问题再来看。 CSP论文: GitHub - liuwei16/CSP: High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection, CVPR, 2019High-level Semantic Feature Detection: A New Perspective for Pedestrian Detection, CVPR, 2019 -

转自博客: https://blog.csdn.net/vagrantabc2017/article/details/77507168原博主总结的很好，转载一下，不懂的时候再来复习。tf.logging.set_verbosity(tf.logging.INFO)当设置INFO级别后，tf.contrib.learn会自动每百步后输出损失度量数据到标准输出。...

参考自:https://www.tensorflow.org/api_docs/python/tf/estimator/Estimator#evaluatehttps://developers.google.com/machine-learning/glossary/#epochsteps: steps batches are processedepoch: 在训练时，整个数据集的一次完整遍历，以...

import tensorflow as tftf.__version__  # version IDtf.__path__      # installation path

假设现在有一个tensor named tensor_a:如果a是一个数组或其他类型，使用以下函数将a转换为tensor:tensor_a = tf.convert_to_tensor(a)tensor_a 的dim获取方法:shape_a = tensor_a.get_shape()dim_a = len(shape_a)假设tensor_a的dim为4，则其各维度大小分别为：tensor_a....

问题描述： tensorflow 执行时出错：FailedPreconditionError (see above for traceback): Attempting to use uninitialized value conv2d_4/kernel解释：tensorflow变量未初始化解决办法：sess = tf.Session()init_g = tf.global_variables_i...

http://www.deeplearningbook.org/         （MIT Press book） https://caffe2.ai/docs/tutorials.html#new-to-deep-learning http://neuralnetworksanddeeplearning.com/index.html http://karpa

1. 报错： fatal error: caffe/proto/caffe.pb.h: No such file or directory    解决办法： # In the directory you installed Caffe to protoc src/caffe/proto/caffe.proto --cpp_out=. mkdir include/caffe/proto

1. 下载caffe2源码包 https://github.com/caffe2/caffe2 2. 安装过程请参照https://caffe2.ai/docs/getting-started.html?platform=centos&configuration=cloud 3. 编译过程中需要的cmake指令和生成的makefile中添加的路径在”我的资源“中,相应的环境变