深度学习-Caffe 使用问题整理
2016-11-19 16:38
567 查看
深度学习-Caffe 使用问题整理
1. shape mismatch in weight initialisation (transfer). "Target shape is ..., but source shape is ...".
possible solution: (1) layer name is wrong (2) 'Eltwise' or 'Concat' fusion manner, which often tends to be 2-fold.
2. training process crashes: (1) problem about training samples (a) training sample is not in proper size.
3. NVIDIA TITAN X PASCAL GPU needsCUDA 8.0 for successful compilation of caffe.
4. Install Protobuf for caffe python interface. I choose to use Anaconda for python, and we need to install protobuf based on Anaconda, so that Anaconda can find the protobuf. There are proxy problems
with the Anaconda 2 version 4.2.0, while version 4.0.0 is ok in proxy. Install protobuf with "conda". The command is here: https://anaconda.org/anaconda/protobuf. The github issue is here:
https://github.com/conda/conda/issues/3984
1. shape mismatch in weight initialisation (transfer). "Target shape is ..., but source shape is ...".
possible solution: (1) layer name is wrong (2) 'Eltwise' or 'Concat' fusion manner, which often tends to be 2-fold.
2. training process crashes: (1) problem about training samples (a) training sample is not in proper size.
3. NVIDIA TITAN X PASCAL GPU needsCUDA 8.0 for successful compilation of caffe.
4. Install Protobuf for caffe python interface. I choose to use Anaconda for python, and we need to install protobuf based on Anaconda, so that Anaconda can find the protobuf. There are proxy problems
with the Anaconda 2 version 4.2.0, while version 4.0.0 is ok in proxy. Install protobuf with "conda". The command is here: https://anaconda.org/anaconda/protobuf. The github issue is here:
https://github.com/conda/conda/issues/3984
相关文章推荐
- 【深度学习】关于解决caffe中draw_net无法使用的问题
- 深度学习Caffe平台开发环境准备——2.使用Eclipse的插件PyDev配置Python开发环境
- 【神经网络与深度学习】Caffe使用step by step:caffe框架下的基本操作和分析
- 【深度学习】笔记6:使用caffe中的CIFAR10网络模型和自己的图片数据训练自己的模型(步骤详解)
- Linux系统下配置深度学习工具问题解决整理
- 深度学习Caffe实战笔记(10)Windows Caffe使用MATLAB接口提取和可视化特征
- Windows下使用深度学习框架caffe学习笔记(1)
- 【神经网络与深度学习】Caffe源码中各种依赖库的作用及简单使用
- 深度学习框架Caffe学习笔记(5)-使用gflags解析命令行参数
- 新增linux账户来使用深度学习框架-caffe
- 深度学习之caffe入门一一配置SSD中遇到的问题
- ubuntu 15.04 搭建caffe深度学习环境流程及遇到的问题
- 【神经网络与深度学习】【Qt开发】【VS开发】从caffe-windows-visual studio2013到Qt5.7使用caffemodel进行分类的移植过程
- ubuntu14使用python绘制caffe的深度学习网络结构
- 深度学习文章2:使用MNIST数据集验证Caffe是否安装成功
- eclipse学习使用问题整理
- ubuntu 15.04 搭建caffe深度学习环境流程及遇到的问题
- 【神经网络与深度学习】Caffe使用step by step:使用自己数据对已经训练好的模型进行finetuning
- 深度学习Caffe实战笔记(12)Caffe 使用Python接口No module named google.protobuf.internal修复方案
- 深度学习文章5:使用caffe对自己的图像数据进行训练并测试