The AIMET project provides a library of advanced compression and quantization techniques for trained neural network models. It provides features that have been proven to improve run-time performance of deep learning neural network models with lower memory requirements and minimal impact to task accuracy.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
|
Model compression for generative models (GAN or VAE)
|
1 | 664 | June 13, 2023 | |
|
Bert, Transformers
|
3 | 994 | April 20, 2021 | |
|
Efficient-Net-B0 AIMET quantization
|
2 | 1159 | July 28, 2021 | |
|
AIMET & TFLITE optimizations
|
9 | 1531 | May 29, 2020 | |
|
Compress Keras (TF) model
|
1 | 1047 | July 22, 2021 |