Update README.md

README.md

@@ -9,6 +9,23 @@ tags:
 # DS-CNN
 
 This is an exported version of DS-CNN from Aidge.
+Model from https://github.com/mlcommons/tiny/tree/master/benchmark/training/keyword_spotting
+
+ONNX version exported from `.pb` model doing
+
+```bash
+# setup environment
+python3.10 -m venv pytf
+source pytf/bin/activate
+
+# install latest officially compatible versions
+pip install tensorflow==2.15.1 tf2onnx==1.16.1
+
+# use most recent opset officially supported
+python -m tf2onnx.convert \
+  --saved-model <path/to/dir> \
+  --output ds_cnn.onnx --opset 18
+```
 
 ## Aidge support
 
@@ -16,24 +33,24 @@ This is an exported version of DS-CNN from Aidge.
 
 |   Feature   | Tested in CI |
 | :---------: | :----------: |
-| ONNX import |      ❌       |
-| Backend CPU |      ❌       |
+| ONNX import |      ✔️      |
+| Backend CPU |      ❌      |
 | Export CPP  |      ❌      |
 
 
 ## Model
 
-* Operators: 44 (10 types)
+* operators: 46 (10 types)
+  - Add: 1
+  - AvgPooling2D: 1
   - Conv2D: 4
-  - Producer: 21
-  - ReLU: 9
-  - FC: 1
-  - Transpose: 1
+  - MatMul: 1
+  - PaddedConv2D: 1
   - PaddedConvDepthWise2D: 4
+  - Producer: 22
+  - ReLU: 9
+  - Reshape: 2
   - Softmax: 1
-  - Reshape: 1
-  - PaddedConv2D: 1
-  - AvgPooling2D: 1
 
 ## Google Speech Commands v2