Wanli
commited on
Commit
·
5c42fd0
1
Parent(s):
bd5223f
Re-quantify some models from per_channel mode to per_tensor mode (#90)
Browse files* re-quantize some models from per_channel mode to per_tensor mode
* remove the description about per_channel
README.md
CHANGED
|
@@ -6,8 +6,6 @@ This model detects palm bounding boxes and palm landmarks, and is converted from
|
|
| 6 |
- tf_saved_model to ONNX: https://github.com/onnx/tensorflow-onnx
|
| 7 |
- simplified by [onnx-simplifier](https://github.com/daquexian/onnx-simplifier)
|
| 8 |
|
| 9 |
-
Also note that the model is quantized in per-channel mode with [Intel's neural compressor](https://github.com/intel/neural-compressor), which gives better accuracy but may lose some speed.
|
| 10 |
-
|
| 11 |
## Demo
|
| 12 |
|
| 13 |
Run the following commands to try the demo:
|
|
|
|
| 6 |
- tf_saved_model to ONNX: https://github.com/onnx/tensorflow-onnx
|
| 7 |
- simplified by [onnx-simplifier](https://github.com/daquexian/onnx-simplifier)
|
| 8 |
|
|
|
|
|
|
|
| 9 |
## Demo
|
| 10 |
|
| 11 |
Run the following commands to try the demo:
|