Train and evaluate Neural Frame Rate Upscaling models using Model Gym
Introduction
Understand neural graphics and Model Gym
Set up your environment
Launch the training notebook
Fine-tune and export a quantized model
Visualize your model with Model Explorer
Next Steps
Train and evaluate Neural Frame Rate Upscaling models using Model Gym
What Model Explorer is
Model Explorer is a visualization tool for inspecting neural network structures and execution graphs. Arm provides a VGF adapter for Model Explorer, so you can visualize .vgf models created from your training and export pipeline.
With Model Explorer, you can inspect model architecture, tensor shapes, and graph connectivity before deployment. This can be a powerful way to debug and understand your exported neural graphics models.
Set up the VGF adapter
The VGF adapter extends Model Explorer to support .vgf files exported from the Model Gym toolchain.
Install the VGF adapter with pip:
pip install vgf-adapter-model-explorer
The VGF adapter model explorer source code is available on GitHub .
Install Model Explorer
The next step is to make sure the Model Explorer itself is installed. Use pip to set it up:
pip install torch ai-edge-model-explorer
Launch Model Explorer
After installing Model Explorer, launch the tool with the VGF adapter:
model-explorer --extensions=vgf_adapter_model_explorer
Use the file browser to open the .vgf model exported earlier in your training workflow.
What you’ve accomplished
You’ve trained and evaluated an NFRU model, fine-tuned and exported an INT8 VGF model, and inspected its graph with Model Explorer.
Continue to Next Steps for related neural graphics resources.