Merge pull request #3 from coolguy525/dev

Update project documentation and task organization

Author: CodeVoyager15

README.md

@@ -1,27 +1,71 @@
-# rknpu2-rs
+# RKNN
 
-Rust bindings for the [Rockchip RKNN API (rknpu2)](https://github.com/airockchip/rknn-toolkit2), targeting deployment of deep learning models on Rockchip NPUs.
+Rust bindings for the Rockchip RKNN Runtime API (librknnrt.so), enabling deployment of deep learning models on Rockchip NPUs. This library is a key component of the rknpu2 SDK, providing efficient integration between Rust applications and Rockchip's neural processing unit for optimized AI model execution.
 
 > These bindings do **not** require redistributing the C headers from the Rockchip rknpu2 SDK. The sys crate contains bindgen bindings, but bindgen is not part of the build process.
 
 ## Requirements
 
-- Rockchip NPU compatible with librknnrt or librknnmrt libraries.
+- Rockchip NPU compatible with `librknnrt` or `librknnmrt` libraries
+- Rust 1.70+ (edition 2021)
 
 ## Features
 
 - Safe and idiomatic Rust abstractions over the `librknnrt.so` C API
 - Support for loading models, setting inputs, running inference, and reading outputs
-- There will be Zero-copy input/output buffer support
+- Zero-copy input/output buffer support (planned)
 - Includes both low-level `-sys` bindings and higher-level wrappers
 - Based on the **rknpu2 SDK v2.3.2**
+- Comprehensive error handling with custom error types
+- Memory-safe tensor operations and buffer management
 
-## Version Compatibility
 
-These bindings are aligned with the **2.3.2** release of the RKNN API.
-[rknn C API v2.3.2 PDF](https://github.com/airockchip/rknn-toolkit2/blob/42aa1d426c0a9e0869b6374edba009f7208a1926/doc/04_Rockchip_RKNPU_API_Reference_RKNNRT_V2.3.2_EN.pdf)
+## Project Structure
 
+```
+crates/
+├── rknpu2/          # High-level Rust API wrapper
+├── rknpu2-sys/      # Low-level FFI bindings
+└── rktensor/        # Tensor operations and utilities
+```
+
+## Installation
+
+Add the following to your `Cargo.toml`:
+
+```toml
+[dependencies]
+rknpu2 = { git = "https://github.com/CodeVoyager15/RKNN", package = "rknpu2" }
+rktensor = { git = "https://github.com/CodeVoyager15/RKNN", package = "rktensor" }
+```
 
 ## Usage
 
-Coming soon!
+Coming soon! The library will provide a simple and intuitive API for:
+
+- Loading RKNN models
+- Setting input tensors
+- Running inference
+- Retrieving output results
+- Managing memory and buffers efficiently
+
+## Examples
+
+Check out the examples in `crates/rknpu2/examples/` for usage demonstrations.
+
+## Development Status
+
+This project is actively maintained and follows Rust best practices. Contributions are welcome!
+
+## License
+
+This project is licensed under either of
+
+- Apache License, Version 2.0 ([LICENSE-APACHE](LICENSE-APACHE) or http://www.apache.org/licenses/LICENSE-2.0)
+- MIT license ([LICENSE-MIT](LICENSE-MIT) or http://opensource.org/licenses/MIT)
+
+at your option.
+
+## Contributing
+
+Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.

TODOS.md

@@ -1,19 +1,34 @@
-## TODO
-
-### Ergonomics
-
-- Some of the error types have integers as part of their error message. I should have a way to match these integers to strings.
-
-### Documentation
-
-- Most docstrings are missing
-
-### Testing
-
-- I should use cargo-tarpaulin to ensure code coverage
-
-### API coverage
-
-- Missing coverage of custom_ops, matmul_api
-- Re-look at the API design of Tensor and TensorBuilder for Zero-Copy tensors
-- Need TensorType implementations for all supported data types
+# TODOs
+
+## High Priority
+- [ ] Complete custom_ops and matmul_api coverage
+- [ ] Implement zero-copy tensor operations
+- [ ] Add all RKNN data types support
+- [ ] Map integer error codes to readable messages
+- [ ] Add comprehensive docstrings
+
+## Medium Priority
+- [ ] Set up cargo-tarpaulin for code coverage
+- [ ] Add more examples beyond mobilenet
+- [ ] Implement async/await support
+- [ ] Add performance monitoring hooks
+- [ ] Create API reference documentation
+
+## Low Priority
+- [ ] Add logging and tracing support
+- [ ] Create CLI tools for model validation
+- [ ] Integrate with Rust ML ecosystem
+- [ ] Add ONNX model format support
+- [ ] Implement batch inference
+
+## Completed ✅
+- [x] Basic RKNN API bindings
+- [x] Model loading and inference
+- [x] Input/output tensor handling
+- [x] Error handling framework
+- [x] Basic examples (mobilenet)
+
+## Notes
+- Focus on stability before advanced features
+- Maintain backward compatibility
+- Align with upstream RKNN API updates