弄浪的鱼

Caffe

Caffe 安装看 Installation, 第一个例子可以看 Training LeNet on MNIST with caffe 的示例.跟着示例做一遍,精确度能有 98% 左右,做完很有成就感.跑完之后可以跑更多的官方示例,它包括 Notebook Example 和 Command Line Example.

Caffe Tutorial介绍了 Caffe 的基础,其中也包括各种数据结构 http://caffe.berkeleyvision.org/tutorial/

Model Zoo有很多实现的网络和训练好的模型

接下来重点看一下 Caffe Tutorial 了解基本数据结构

Caffe

Deep networks are compositional models that are naturally represented as a collection of inter-connected layers that work on chunks of data. Caffe defines a net layer-by-layer in its own model schema. The network defines the entire model bottom-to-top from input data to loss. As data and derivatives flow through the network in the forward and backward passes Caffe stores, communicates, and manipulates the information as blobs: the blob is the standard array and unified memory interface for the framework. The layer comes next as the foundation of both model and computation. The net follows as the collection and connection of layers. The details of blob describe how information is stored and communicated in and across layers and nets.

Solving is configured separately to decouple modeling and optimization.

We will go over the details of these components in more detail.

https://caffe.berkeleyvision.org/tutorial/net_layer_blob.html

darknet

Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.

—— https://pjreddie.com/darknet/

本文是对使用 darknet 进行目标检测的小结,包括:

  1. 数据集准备:如何使用 labelimage 对数据进行标注,注意事项,文件格式转换
  2. darknet 使用:如何编译和修改配置文件
  3. 模型评估:如何查看 loss、计算 IoU、recall、mAP