Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# Model Quantization Notebook
|
| 2 |
|
| 3 |
This notebook converts a pre-trained Keras violence detection model into TensorFlow Lite (TFLite) format using three different quantization strategies, making it suitable for deployment on edge/mobile devices.
|
|
@@ -91,4 +96,4 @@ Open and run the notebook cells in order:
|
|
| 91 |
|---|---|---|
|
| 92 |
| `model_dynamic_quant.tflite` | Dynamic Range | Weights: INT8, Activations: float32 |
|
| 93 |
| `model_fp16_quant.tflite` | Float16 | Weights & Activations: float16 |
|
| 94 |
-
| `model_full_int8.tflite` | Full Integer | Weights & Activations: INT8 |
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
---
|
| 6 |
# Model Quantization Notebook
|
| 7 |
|
| 8 |
This notebook converts a pre-trained Keras violence detection model into TensorFlow Lite (TFLite) format using three different quantization strategies, making it suitable for deployment on edge/mobile devices.
|
|
|
|
| 96 |
|---|---|---|
|
| 97 |
| `model_dynamic_quant.tflite` | Dynamic Range | Weights: INT8, Activations: float32 |
|
| 98 |
| `model_fp16_quant.tflite` | Float16 | Weights & Activations: float16 |
|
| 99 |
+
| `model_full_int8.tflite` | Full Integer | Weights & Activations: INT8 |
|