Run Vitis AI RNN Tool and Example

Follow these steps to run the docker image, quantize and compile the model, and process the final inference on board.

Run the docker image.

./docker_run_rnn.sh -g xilinx/vitis-ai-rnn:latest

Docker image has two conda environments, vitis-ai-rnn-pytorch and vitis-ai-rnn-tensorflow, in which the RNN quantizers for pytorch and tensorflow are installed. Activate the conda environment.
- For Pytorch:
```
conda activate vitis-ai-rnn-pytorch
```
- For Tensorflow:
```
conda activate vitis-ai-rnn-tensorflow
```
```
conda activate vitis-ai-rnn
```

Copy the example to the docker environment and run the following relevant steps:

For Pytorch:

Copy example/lstm_quant_pytorch to the docker environment. The contents in the working directory look like this.

pretrained.pth: pretrained model for sentiment detection.
quantize_lstm.py: python script to run quantization of the model
run_quantizer.sh: test script to run python script

Run the test script.

cd example/lstm_quant_pytorch
sh run_quantizer.sh

Two files and one import sub-directory are generated in the output directory ./quantize_result.

Lstm_StandardLstmCell_layer_0_forward.py: converted format model
quant_info.json: quantization steps of tensors
xmodel: subdirectory that contain deployed model

For TensorFlow:

Copy example/lstm_quant_tensorflow to the docker environment. The contents in the working directory as follows:

pretrained.h5: pretrained model for sentiment detection.
quantize_lstm.py: python script to run quantization of the model
run_quantizer.sh: test script to run python script

Run the test script.

cd example/lstm_quant_tensorflow
sh run_quantizer.sh

Two files and one import sub-directory are generated in the output directory ./quantize_result.

rnn_cell_0.py: converted format model
quant_info.json: quantization steps of tensors
xmodel: subdirectory that contain deployed model

Compile the xmodel.
Compile the xmodel for DPURADR16L(U25) using batch size = 1. It generates the instructions in the output file (compiled_batch_1.xmodel).
```
vai_c_rnn -x xmodel/ -t DPURADR16L -b 1 -o output
```
Activate pytorch runtime environment.
```
conda activate rnn-pytorch-1.7.1
```
Run model on DPURADR16L(U25). For more information, see VART.
Note: Xilinx provides three prebuilt examples, Customer Satisfaction, IMDB Sentiment Analysis, and OpenIE. The steps in VART run the prebuilt xmodels. To run the xmodel you compiled, replace data/compiled_batch_1.xmodel with your output xmodel file after executing the "TARGET_DEVICE=U25 source ./setup.sh" command.

Run Vitis AI RNN Tool and Example - 2.0 English

Vitis AI RNN User Guide (UG1563)