Skip to content
/ Quantization Public

Quantization (post-training quantization) your (custom mobilenet_v2) models .h5 or .pb models using TensorFlow Lite 2.4

3 stars 2 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

oleksandr-g-rock/Quantization

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
1_-bmgkbQNGwVkDJJq64yVxQ.gif
1_-bmgkbQNGwVkDJJq64yVxQ.gif
 
 
1_3bYW4pjMPEAN47aXLrDVvA.png
1_3bYW4pjMPEAN47aXLrDVvA.png
 
 
1_8z4lTcSfyEad87GGsf9IPw.png
1_8z4lTcSfyEad87GGsf9IPw.png
 
 
1_KvHwa5eUfyVTaNzEm3TJ8A.png
1_KvHwa5eUfyVTaNzEm3TJ8A.png
 
 
1_P6oEnzouLdQzcsDZW3SZnQ.png
1_P6oEnzouLdQzcsDZW3SZnQ.png
 
 
DEFAULT_float16.py
DEFAULT_float16.py
 
 
DEFAULT_float8.py
DEFAULT_float8.py
 
 
OPTIMIZE_FOR_LATENCY_float16.py
OPTIMIZE_FOR_LATENCY_float16.py
 
 
OPTIMIZE_FOR_LATENCY_float8.py
OPTIMIZE_FOR_LATENCY_float8.py
 
 
OPTIMIZE_FOR_SIZE_float16.py
OPTIMIZE_FOR_SIZE_float16.py
 
 
OPTIMIZE_FOR_SIZE_float8.py
OPTIMIZE_FOR_SIZE_float8.py
 
 
README.md
README.md
 
 
mobilenetv2.h5
mobilenetv2.h5
 
 
quantization.csv
quantization.csv
 
 
quantization.ipynb
quantization.ipynb
 
 
quantization_DEFAULT_8bit_model_h5_to_tflite.tflite
quantization_DEFAULT_8bit_model_h5_to_tflite.tflite
 
 
quantization_DEFAULT_float16_model_h5_to_tflite.tflite
quantization_DEFAULT_float16_model_h5_to_tflite.tflite
 
 
quantization_OPTIMIZE_FOR_LATENCY_8bit_model_h5_to_tflite.tflite
quantization_OPTIMIZE_FOR_LATENCY_8bit_model_h5_to_tflite.tflite
 
 
quantization_OPTIMIZE_FOR_LATENCY_float16_model_h5_to_tflite.tflite
quantization_OPTIMIZE_FOR_LATENCY_float16_model_h5_to_tflite.tflite
 
 
quantization_OPTIMIZE_FOR_SIZE_8bit_model_h5_to_tflite.tflite
quantization_OPTIMIZE_FOR_SIZE_8bit_model_h5_to_tflite.tflite
 
 
quantization_OPTIMIZE_FOR_SIZE_float16_model_h5_to_tflite.tflite
quantization_OPTIMIZE_FOR_SIZE_float16_model_h5_to_tflite.tflite
 
 
simple_tflite.tflite
simple_tflite.tflite
 
 
test_h5.py
test_h5.py
 
 
test_tflite.py
test_tflite.py
 
 

Repository files navigation

Project name:

Quantization (post-training quantization) your (custom mobilenet_v2) models .h5 or .pb models using TensorFlow Lite 2.4

REAME and all comments FOR THIS REPOSTITORY HERE (this article):

https://oleksandrg.medium.com/quantization-your-custom-mobilenet-v2-models-h5-models-using-tensorflow-lite-2-4-5e7046fa860e

Also

If you were interested in this code, please put a star ✰ for this repo

Also, if you were interested in my article, please subscribe to my blog

https://oleksandrg.medium.com/

Thank you 🙂

About

Quantization (post-training quantization) your (custom mobilenet_v2) models .h5 or .pb models using TensorFlow Lite 2.4

Topics

tensorflow-tutorials quantization tensorflow-examples tensorflowlite quantization-algorithms tensorflow-quantum-classification tensorflow-quantum-example

Resources

Readme
Activity

Stars

3 stars

Watchers

2 watching

Forks

2 forks
Report repository

Releases

No releases published

Packages

No packages published

Languages