MetaTF
MetaTF is BrainChip's Akida development environment, delivered as a single
meta-package. Installing metatf installs the complete, validated tool set:
| Package | Description |
|---|---|
| akida | Akida Execution Engine (software simulator and hardware interface) |
| cnn2snn | Keras/TensorFlow to Akida model converter |
| akida-models | Model zoo and training pipelines |
| quantizeml | Base layers and quantization tools |
TensorFlow and tf-keras are pulled in automatically as dependencies of the set.
metatf itself contains no Python code — it only pins the packages above. There is no metatf
module to import. Import and use the four packages directly (akida, cnn2snn, akida_models,
quantizeml).
Documentation: https://doc.brainchipinc.com.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
metatf-2.19.3.tar.gz
(5.7 kB
view details)
File details
Details for the file metatf-2.19.3.tar.gz.
File metadata
- Download URL: metatf-2.19.3.tar.gz
- Upload date:
- Size: 5.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.11.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
b864454df7253ff52aeaaabf946b36c8e74ba9dcb141b9c54a7ebaaa2034b9d3
|
|
| MD5 |
cc801e5b9f36437e9dd86402845cdd3d
|
|
| BLAKE2b-256 |
78dfcb2c013ec328d32f93384814e16d290af56425f4aa9acf6f80022b12aa89
|