Caffe provides multimedia scientists and practitioners with a clean and modiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB binding
对比分析主流的深度学习框架：TensorFlow是相对高阶的机器学习库，用户可以方便地用它设计神经网络结构，而不必为了追求高效率的实现亲自写C++或CUDA代码;Caffe 全称为 Convolutional Architecture for Fast Feature Embedding，是一个被广泛使用的开源深度学习框架（在TensorFlow出现之前一直是深度学习领域 GitHub star 最多的项目)，目前由伯克利视觉学中心（Berkeley Vision and Learning C
以下摘自github hoszbh的回答 https://github.com/BVLC/caffe/issues/5729
modifying cudnn_conv_layer.cpp and aligning the address to be multiples of 32.
You can insert tow lines of code before size_t total_max_workspace = ... as follow:
size_t m=32;
