AI学习资源的汇总

1 TensorRT

https://developer.nvidia.com/tensorrt

developer guide & sample code

https://docs.nvidia.com/deeplearning/sdk/tensorrt-developer-guide/index.html

2 Caffe

code：

http://caffe.berkeleyvision.org/doxygen/hierarchy.html

3 Nvidia Cuda 

http://www.nvidia.cn/object/cuda_education_cn_old.html

串行并行对比

https://www.nvidia.com/object/nvision08_gpu_v_cpu.html

4 TensorRT Introducing GPU Inference Engine

https://devblogs.nvidia.com/production-deep-learning-nvidia-gpu-inference-engine/

5 AI 课程

https://www.nvidia.com/en-us/deep-learning-ai/education/

GIE Build Phase

The GIE runtime needs three files to deploy a classification neural network:

1. a network architecture file (deploy.prototxt),
2. trained weights (net.caffemodel), and
3. a label file to provide a name for each output class.

In addition, you must define the batch size and the output layer. Code Listing 1 illustrates how to convert a Caffe model to a GIE object. The builder (lines 4-7) is responsible for reading the network information. Alternatively, you can use the builder to define the network information if you don’t provide a network architecture file (deploy.prototxt).

GIE supports the following layer types.

• Convolution: 2D
• Activation: ReLU, tanh and sigmoid
• Pooling: max and average
• ElementWise: sum, product or max of two tensors
• LRN: cross-channel only
• Fully-connected: with or without bias
• SoftMax: cross-channel only
• Deconvolution

1. IBuilder* builder = createInferBuilder(gLogger);
2.  
3. // parse the caffe model to populate the network, then set the outputs
4. INetworkDefinition* network = builder->createNetwork();
5.  
6. CaffeParser parser;
7. auto blob_name_to_tensor = parser.parse(“deploy.prototxt”,
8. trained_file.c_str(),
9. *network,
10. DataType::kFLOAT);
11.  
12. // specify which tensors are outputs
13. network->markOutput(*blob_name_to_tensor->find("prob"));
14.  
15. // Build the engine
16. builder->setMaxBatchSize(1);
17. builder->setMaxWorkspaceSize(1 << 30);
18. ICudaEngine* engine = builder->buildCudaEngine(*network);