You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: Tools/WinMLDashboard/README.md
+14-6Lines changed: 14 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -32,13 +32,21 @@ The **Convert** tab (see snip below) helps convert models from several different
32
32
33
33
In order to do the conversion, the tool installs a separate Python environment and a set of converter tools. This helps alleviate one of the big pain points of a typical developer - installing the right Python environment and tool chain for conversion and validating the model.
34
34
35
-
WinMLTools provides quantization feature to reduce the memory footprint of the model.
35
+
WinMLTools provides [quantization](https://docs.microsoft.com/en-us/windows/ai/convert-model-winmltools#quantize-onnx-model) feature to reduce the memory footprint of the model.
36
36
37
-
For **quantization**:
38
-
|Type |Usage |
39
-
|-----|--------|
40
-
|**Type1**|Do not use dequantize_linear option, the converted model can only be run in Win10 released before [Version 1809 (OS build 17763)](https://support.microsoft.com/en-us/help/4464619/windows-10-update-history)|
41
-
|**Type2**|Use dequantize_linear option, the converted model can also be run in Win10 release after Version 1809 (OS build 17763)|
37
+
For **quantization:**
38
+
39
+
|Type |Usage |
40
+
|------------|-------|
41
+
|**Type1**|Do not use dequantize_linear option, the converted model can only be run in Win10 released before [Version 1809 (OS build 17763)](https://support.microsoft.com/en-us/help/4464619/windows-10-update-history)|
42
+
|**Type2**|Use dequantize_linear option, the converted model can also be run in Win10 release after Version 1809 (OS build 17763) |
0 commit comments