mirror of https://github.com/tracel-ai/burn.git
4efc683df4
* Fix python main entrypoint in book example * Remove candle windows safeguards (#1178) * Bump candle-core from 0.3.3 to 0.4.1 * Remove windows current known issue |
||
|---|---|---|
| .. | ||
| model | ||
| pytorch | ||
| src | ||
| Cargo.toml | ||
| README.md | ||
| build.rs | ||
README.md
Import PyTorch Weights
This crate provides a simple example for importing PyTorch generated weights to Burn.
The .pt file is converted into a Burn consumable file (message pack format) using burn-import.
The conversation is done in the build.rs file.
The model is separated into a sub-crate because build.rs needs for conversion and build.rs cannot
import modules for the same crate.
Usage
cargo run -- 15
Output:
Finished dev [unoptimized + debuginfo] target(s) in 0.13s
Running `burn/target/debug/onnx-inference 15`
Image index: 15
Success!
Predicted: 5
Actual: 5
See the image online, click the link below:
https://datasets-server.huggingface.co/assets/mnist/--/mnist/test/15/image/image.jpg