e8653a776d
* add: mobilenetv2 Python network definition API * add: mobilenetv3 base code * add: mobilenetv2 Python network definition API * restructure: mobilenetv2 code * add: Alexnet Python Network Definition API * update: README according to new folder architecture * add: mobilenetv3 small and large python network definition API * add: DenseNet121 Python Network Definition API |
||
|---|---|---|
| .. | ||
| alex.cpp | ||
| alexnet.py | ||
| CMakeLists.txt | ||
| logging.h | ||
| README.md | ||
alexnet
AlexNet model architecture from the "One weird trick..." https://arxiv.org/abs/1404.5997`_ paper.
For the details, you can refer to pytorchx/alexnet
This alexnet is just several conv-relu-pool blocks followed by several fc-relu, nothing special. All layers can be implemented by tensorrt api, including addConvolution, addActivation, addPooling, addFullyConnected.
// 1. generate alexnet.wts from [pytorchx/alexnet](https://github.com/wang-xinyu/pytorchx/tree/master/alexnet)
// 2. put alexnet.wts into tensorrtx/alexnet
// 3. build and run
cd tensorrtx/alexnet
mkdir build
cd build
cmake ..
make
sudo ./alexnet -s // serialize model to plan file i.e. 'alexnet.engine'
sudo ./alexnet -d // deserialize plan file and run inference
// 4. see if the output is same as pytorchx/alexnet